Mise à jour du Makefile pour corriger les chemins des fichiers journaux et ajouter la cible tp2

- Created a Docker Compose file to set up a MySQL container named M2_SQL_COURSE with an empty password and a database named TP.
- Added a Makefile with a target to execute a SQL script (TP1.sql) inside the MySQL container and log the output.
- Implemented the TP1.sql script to create tables for Magasin and Localite, insert initial data, and perform several queries.

.gitignore

@@ -1,3 +1,15 @@
 .DS_Store
 
 .Rproj.user
+
+.idea
+.vscode
+
+.RData
+.RHistory
+*.pdf
+
+.ipynb_checkpoints
+
+*.log
+logs

.python-version

@@ -0,0 +1 @@
+3.13

L3/Analyse Matricielle/TP1_Methode_de_Gauss.ipynb

@@ -76,24 +76,40 @@
    ],
    "source": [
     "import numpy as np\n",
+    "\n",
     "%matplotlib inline\n",
-    "import matplotlib.pyplot as plt\n",
     "\n",
     "\n",
-    "u = np.array([1,2,3,4,5])\n",
-    "v = np.array([[1,2,3,4,5]])\n",
-    "su=u.shape\n",
-    "sv=v.shape\n",
+    "u = np.array([1, 2, 3, 4, 5])\n",
+    "v = np.array([[1, 2, 3, 4, 5]])\n",
+    "su = u.shape\n",
+    "sv = v.shape\n",
     "ut = np.transpose(u)\n",
     "vt = np.transpose(v)\n",
-    "vt2 = np.array([[1],[2],[3],[4],[5]])\n",
-    "A = np.array([[1,2,0,0,0],[0,2,0,0,0],[0,0,3,0,0],[0,0,0,4,0],[0,0,0,0,5]])\n",
-    "B = np.array([[1,2,3,4,5],[2,3,4,5,6],[3,4,5,6,7],[4,5,6,7,8],[5,6,7,8,9]])\n",
-    "d=np.diag(A)\n",
-    "dd=np.array([np.diag(A)])\n",
-    "dt=np.transpose(d)\n",
-    "ddt=np.transpose(dd)\n",
-    "Ad=np.diag(np.diag(A))\n",
+    "vt2 = np.array([[1], [2], [3], [4], [5]])\n",
+    "A = np.array(\n",
+    "    [\n",
+    "        [1, 2, 0, 0, 0],\n",
+    "        [0, 2, 0, 0, 0],\n",
+    "        [0, 0, 3, 0, 0],\n",
+    "        [0, 0, 0, 4, 0],\n",
+    "        [0, 0, 0, 0, 5],\n",
+    "    ]\n",
+    ")\n",
+    "B = np.array(\n",
+    "    [\n",
+    "        [1, 2, 3, 4, 5],\n",
+    "        [2, 3, 4, 5, 6],\n",
+    "        [3, 4, 5, 6, 7],\n",
+    "        [4, 5, 6, 7, 8],\n",
+    "        [5, 6, 7, 8, 9],\n",
+    "    ]\n",
+    ")\n",
+    "d = np.diag(A)\n",
+    "dd = np.array([np.diag(A)])\n",
+    "dt = np.transpose(d)\n",
+    "ddt = np.transpose(dd)\n",
+    "Ad = np.diag(np.diag(A))\n",
     "\n",
     "print(np.dot(np.linalg.inv(A), A))"
    ]
@@ -138,11 +154,11 @@
     "    x = 0 * b\n",
     "    n = len(b)\n",
     "    if np.allclose(A, np.triu(A)):\n",
-    "        for i in range(n-1, -1, -1):\n",
-    "            x[i] = (b[i] - np.dot(A[i,i+1:], x[i+1:])) / A[i,i]\n",
+    "        for i in range(n - 1, -1, -1):\n",
+    "            x[i] = (b[i] - np.dot(A[i, i + 1 :], x[i + 1 :])) / A[i, i]\n",
     "    elif np.allclose(A, np.tril(A)):\n",
     "        for i in range(n):\n",
-    "            x[i] = (b[i] - np.dot(A[i,:i], x[:i])) / A[i,i]\n",
+    "            x[i] = (b[i] - np.dot(A[i, :i], x[:i])) / A[i, i]\n",
     "    else:\n",
     "        raise ValueError(\"A est ni triangulaire supérieure ni triangulaire inférieure\")\n",
     "    return x"
@@ -171,7 +187,7 @@
     "b = np.dot(A, xe)\n",
     "x = remontee_descente(A, b)\n",
     "\n",
-    "print(np.dot(x - xe, x-xe))"
+    "print(np.dot(x - xe, x - xe))"
    ]
   },
   {
@@ -263,9 +279,9 @@
     "    U = A\n",
     "    n = len(A)\n",
     "    for j in range(n):\n",
-    "        for i in range(j+1, n):\n",
-    "            beta = U[i,j]/U[j,j]\n",
-    "            U[i,j:] = U[i,j:] - beta * U[j, j:]\n",
+    "        for i in range(j + 1, n):\n",
+    "            beta = U[i, j] / U[j, j]\n",
+    "            U[i, j:] = U[i, j:] - beta * U[j, j:]\n",
     "    return U"
    ]
   },
@@ -282,14 +298,16 @@
     "    if n != m:\n",
     "        raise ValueError(\"Erreur de dimension : A doit etre carré\")\n",
     "    if n != b.size:\n",
-    "        raise valueError(\"Erreur de dimension : le nombre de lignes de A doit être égal au nombr ede colonnes de b\")\n",
-    "    U = np.zeros((n, n+1))\n",
+    "        raise valueError(\n",
+    "            \"Erreur de dimension : le nombre de lignes de A doit être égal au nombr ede colonnes de b\"\n",
+    "        )\n",
+    "    U = np.zeros((n, n + 1))\n",
     "    U = A\n",
     "    V = b\n",
     "    for j in range(n):\n",
-    "        for i in range(j+1, n):\n",
-    "            beta = U[i,j]/U[j,j]\n",
-    "            U[i,j:] = U[i,j:] - beta * U[j, j:]\n",
+    "        for i in range(j + 1, n):\n",
+    "            beta = U[i, j] / U[j, j]\n",
+    "            U[i, j:] = U[i, j:] - beta * U[j, j:]\n",
     "            V[i] = V[i] - beta * V[j]\n",
     "    return remontee_descente(U, V)"
    ]

L3/Analyse Multidimensionnelle/ADN/ADN.iml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="R_MODULE" version="4">
+  <component name="NewModuleRootManager" inherit-compiler-output="true">
+    <exclude-output />
+    <content url="file://$MODULE_DIR$" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+</module>

L3/Analyse Multidimensionnelle/ADN/main.rmd

@@ -0,0 +1,6 @@
+```{r}
+library(FactoMineR)
+data(iris)
+res.test <- PCA(iris[,1:4], scale.unit=TRUE, ncp=4)
+res.test
+```

L3/Analyse Multidimensionnelle/DM ACP/DM_ACP.Rmd

@@ -1,12 +1,12 @@
 ---
 title: "DM Statistique exploratoire multidimensionelle - Arthur DANJOU"
 output:
-  pdf_document: default
-  html_document:
-    df_print: paged
-editor_options: 
-  markdown: 
-    wrap: 72
+pdf_document: default
+html_document:
+df_print: paged
+editor_options:
+markdown:
+wrap: 72
 ---
 
 ------------------------------------------------------------------------
@@ -28,23 +28,23 @@ knitr::opts_chunk$set(include = FALSE)
 # PARTIE 1 : Calcul de composantes principales sous R (Sans FactoMineR)
 
 -   Vide l'environnement de travail, initialise la matrice avec laquelle
-    vous allez travailler
+vous allez travailler
 
 ```{r}
-rm(list=ls())
+rm(list = ls())
 ```
 
 -   Importation du jeu de données (compiler ce qui est ci-dessous mais
-    NE SURTOUT PAS MODIFIER)
+NE SURTOUT PAS MODIFIER)
 
 ```{r}
 library(dplyr)
-notes_MAN <- read.table("notes_MAN.csv", sep=";", dec=",", row.names=1, header=TRUE)
+notes_MAN <- read.table("notes_MAN.csv", sep = ";", dec = ",", row.names = 1, header = TRUE)
 # on prépare le jeu de données en retirant la colonne des Mentions
 # qui est une variable catégorielle
-notes_MAN_prep <- notes_MAN[,-1]
+notes_MAN_prep <- notes_MAN[, -1]
 
-X <- notes_MAN[1:6,]%>%select(c("Probas","Analyse","Anglais","MAN.Stats","Stats.Inférentielles"))
+X <- notes_MAN[1:6,] %>% select(c("Probas", "Analyse", "Anglais", "MAN.Stats", "Stats.Inférentielles"))
 # on prépare le jeu de données en retirant la colonne des Mentions
 # qui est une variable catégorielle
 # View(X)
@@ -52,19 +52,19 @@ X <- notes_MAN[1:6,]%>%select(c("Probas","Analyse","Anglais","MAN.Stats","Stats.
 ```
 
 ```{r}
-X <- scale(X,center=TRUE,scale=TRUE)
+X <- scale(X, center = TRUE, scale = TRUE)
 X
 ```
 
 -   Question 1 : que fait la fonction “scale” dans la cellule ci-dessus
-    ? (1 point)
+? (1 point)
 
 La fonction *scale* permet de normaliser et de réduire notre matrice X.
 
 -   Question 2: utiliser la fonction eigen afin de calculer les valeurs
-    propres et vecteurs propres de la matrice de corrélation de X. Vous
-    stockerez les valeurs propres dans un vecteur nommé lambda et les
-    vecteurs propres dans une matrice nommée vect (1 point).
+propres et vecteurs propres de la matrice de corrélation de X. Vous
+stockerez les valeurs propres dans un vecteur nommé lambda et les
+vecteurs propres dans une matrice nommée vect (1 point).
 
 ```{r}
 cor_X <- cor(X)
@@ -78,7 +78,7 @@ lambda
 ```
 
 -   Question 3 : quelle est la part d’inertie expliquée par les 2
-    premières composantes principales ? (1 point)
+premières composantes principales ? (1 point)
 
 ```{r}
 inertie_total_1 <- sum(diag(cor_X)) # Inertie est égale à la trace de la matrice de corrélation
@@ -90,26 +90,26 @@ inertie_axes
 ```
 
 -   Question 4 : calculer les coordonnées des individus sur les deux
-    premières composantes principales (1 point)
+premières composantes principales (1 point)
 
 ```{r}
 C <- X %*% vect
-C[,1:2]
+C[, 1:2]
 ```
 
 -   Question 5 : représenter les individus sur le plan formé par les
-    deux premières composantes principales (1 point)
+deux premières composantes principales (1 point)
 
 ```{r}
 colors <- c('blue', 'red', 'green', 'yellow', 'purple', 'orange')
 plot(
-  C[,1],C[,2], 
-  main="Coordonnées des individus par rapport \n aux deux premières composantes principales",
+  C[, 1], C[, 2],
+  main = "Coordonnées des individus par rapport \n aux deux premières composantes principales",
   xlab = "Première composante principale",
   ylab = "Deuxieme composante principale",
   panel.first = grid(),
   col = colors,
-  pch=15
+  pch = 15
 )
 legend(x = 'topleft', legend = rownames(X), col = colors, pch = 15)
 ```
@@ -122,7 +122,7 @@ legend(x = 'topleft', legend = rownames(X), col = colors, pch = 15)
 étudiants.
 
 -   Question 1 : Écrire maximum 2 lignes de code qui renvoient le nombre
-    d’individus et le nombre de variables.
+d’individus et le nombre de variables.
 
 ```{r}
 nrow(notes_MAN_prep) # Nombre d'individus
@@ -161,7 +161,7 @@ summary(res.notes, nbind = Inf, nbelements = Inf, nb.dec = 2)
 eigen_values <- res.notes$eig
 
 bplot <- barplot(
-  eigen_values[, 1], 
+  eigen_values[, 1],
   names.arg = 1:nrow(eigen_values),
   main = "Eboulis des valeurs propres",
   xlab = "Principal Components",
@@ -169,11 +169,11 @@ bplot <- barplot(
   col = "lightblue"
 )
 lines(x = bplot, eigen_values[, 1], type = "b", col = "red")
-abline(h=1, col = "darkgray", lty = 5)
+abline(h = 1, col = "darkgray", lty = 5)
 ```
 
 -   Question 4 : Quelles sont les coordonnées de la variable MAN.Stats
-    sur le cercle des corrélations ?
+sur le cercle des corrélations ?
 
 La variable **MAN.Stats** est la **9-ième** variable de notre dataset. Les
 coordonnées de cette variable sont : $(corr(C_1, X_9), corr(C_2, X_9))$
@@ -198,12 +198,12 @@ Les coordonnées de la variable **MAN.Stats** sont donc environ
 **(0.766,-0.193)**
 
 -   Question 5 : Quelle est la contribution moyenne des individus ?
-    Quelle est la contribution de Thérèse au 3e axe principal ?
+Quelle est la contribution de Thérèse au 3e axe principal ?
 
 ```{r}
 contribs <- res.notes$ind$contrib
 contrib_moy_ind <- mean(contribs) # 100 * 1/42
-contrib_therese <- res.notes$ind$contrib["Thérèse",3]
+contrib_therese <- res.notes$ind$contrib["Thérèse", 3]
 
 contrib_moy_ind
 contrib_therese
@@ -213,7 +213,7 @@ La contribution moyenne est donc environ égale à **2,38%**. La
 contribution de Thérèse au 3e axe principal est environ égal à **5.8%**
 
 -   Question 6 : Quelle est la qualité de représentation de Julien sur
-    le premier plan factoriel (constitué du premier et deuxième axe) ?
+le premier plan factoriel (constitué du premier et deuxième axe) ?
 
 La qualité de représentation de 'Julien' sur le premier plan factoriel
 est donné par la formule :
@@ -236,8 +236,8 @@ principales. On a donc une qualité environ égale à **0.95** soit
 **95%.**
 
 -   Question 7 : Discuter du nombre d’axes à conserver selon les deux
-    critères vus en cours. Dans toutes la suite on gardera néanmoins 2
-    axes.
+critères vus en cours. Dans toutes la suite on gardera néanmoins 2
+axes.
 
 Nous avons vu deux critères principaux: le critère de Kaiser et le
 critère du coude. Le critère de Kaiser dit de garder uniquement les
@@ -253,7 +253,7 @@ plus grandes valeurs propres ou bien les quatre plus grandes**, donc
 conserver ou bien **deux axes principaux, ou bien quatre**.
 
 -   Question 8 : Effectuer l’étude des individus. Être en particulier
-    vigilant aux étudiants mal représentés et commenter.
+vigilant aux étudiants mal représentés et commenter.
 
 ## Contribution moyenne
 
@@ -266,7 +266,7 @@ La contribution moyenne est donc environ égale à **2,38%**
 ## Axe 1
 
 ```{r}
-indiv_contrib_axe_1 <- sort(res.notes$ind$contrib[,1], decreasing = TRUE)
+indiv_contrib_axe_1 <- sort(res.notes$ind$contrib[, 1], decreasing = TRUE)
 head(indiv_contrib_axe_1, 3)
 ```
 
@@ -278,7 +278,7 @@ sur l'axe 1.
 ## Axe 2
 
 ```{r}
-indiv_contrib_axe_2 <- sort(res.notes$ind$contrib[,2], decreasing = TRUE)
+indiv_contrib_axe_2 <- sort(res.notes$ind$contrib[, 2], decreasing = TRUE)
 head(indiv_contrib_axe_2, 3)
 ```
 
@@ -294,12 +294,12 @@ axes, c'est à dire ceux qui se distinguent ni par l'axe 1, ni par l'axe
 2.
 
 ```{r}
-mal_representes <- rownames(res.notes$ind$cos2)[rowSums(res.notes$ind$cos2[,1:2]) <= mean(res.notes$ind$cos2[,1:2])]
+mal_representes <- rownames(res.notes$ind$cos2)[rowSums(res.notes$ind$cos2[, 1:2]) <= mean(res.notes$ind$cos2[, 1:2])]
 mal_representes
 ```
 
 -   Question 9 : Relancer une ACP en incluant la variable catégorielle
-    des mentions comme variable supplémentaire.
+des mentions comme variable supplémentaire.
 
 ```{r}
 res.notes_sup <- PCA(notes_MAN, scale.unit = TRUE, quali.sup = c("Mention"))
@@ -311,7 +311,7 @@ summary(res.notes_sup, nb.dec = 2, nbelements = Inf, nbind = Inf)
 ```
 
 -   Question 10 : Déduire des deux questions précédentes une
-    interprétation du premier axe principal.
+interprétation du premier axe principal.
 
 La prise en compte de la variable supplémentaire **Mentions**, montre en outre que la
 première composante principale est liée à la mention obtenue par les étudiants.
@@ -320,7 +320,7 @@ réussite des étudiants.
 
 
 -   Question 11 : Effectuer l’analyse des variables. Commenter les UE
-    mal représentées.
+mal représentées.
 
 ## Contribution moyenne
 
@@ -340,7 +340,7 @@ toutes une coordonnée positive.
 ## Axe 2
 
 ```{r}
-var_contrib_axe_2 <- sort(res.notes_sup$var$contrib[,2], decreasing = TRUE)
+var_contrib_axe_2 <- sort(res.notes_sup$var$contrib[, 2], decreasing = TRUE)
 head(var_contrib_axe_2, 3)
 ```
 
@@ -351,9 +351,9 @@ et **Options.S6**, corrélées négativement.
 ## Qualité de la représentation
 
 ```{r}
-mal_representes <- rownames(res.notes_sup$var$cos2[,1:2])[rowSums(res.notes_sup$var$cos2[,1:2]) <= 0.6]
+mal_representes <- rownames(res.notes_sup$var$cos2[, 1:2])[rowSums(res.notes_sup$var$cos2[, 1:2]) <= 0.6]
 mal_representes
-mal_representes_moy <- rownames(res.notes_sup$var$cos2[,1:2])[rowSums(res.notes_sup$var$cos2[,1:2]) <= mean(res.notes_sup$var$cos2[,1:2])]
+mal_representes_moy <- rownames(res.notes_sup$var$cos2[, 1:2])[rowSums(res.notes_sup$var$cos2[, 1:2]) <= mean(res.notes_sup$var$cos2[, 1:2])]
 mal_representes_moy
 ```
 
@@ -364,7 +364,7 @@ sauf 4 variables : l'**Anglais**, **MAN.PPEI.Projet**, **Options.S5** et
 On remarque également que l'**Options.S5** est la variable la moins bien représentée dans le plan car sa qualité de représentation dans le plan est inférieure à la moyenne des qualités de représentation des variables dans le plan.
 
 -   Question 12 : Interpréter les deux premières composantes
-    principales.
+principales.
 
 On dira que la première composante principale définit un “facteur de taille” car
 toutes les variables sont corrélées positivement entre elles. Ce phénomène
@@ -379,5 +379,5 @@ moyenne), c'est à dire selon leur réussite, donc leur moyenne générale de le
 
 Le deuxième axe définit un “facteur de forme” : il y a deux groupes de variables
 opposées, celles qui contribuent positivement à l’axe, celles qui contribuent
-négativement. Vu les variables en question, la deuxième composante principale 
+négativement. Vu les variables en question, la deuxième composante principale
 s’interprète aisément comme opposant les matières du semestre 5 à celles du semestre 6.

L3/Analyse Multidimensionnelle/TP1/TP2_Enonce_2024.Rmd

@@ -3,6 +3,7 @@ title: "TP2 : ACP "
 output:
   pdf_document: default
   html_document: default
+output: rmarkdown::html_vignette
 ---
 
 ```{r setup, include=FALSE}
@@ -59,7 +60,7 @@ help(PCA)
 
 
 ```{r,echo=FALSE}
-res.autos<-PCA(autos, scale.unit=TRUE, quanti.sup = c("PRIX"))
+res.autos<-PCA(autos, scale.unit=TRUE, quanti.sup = "PRIX")
 ```
 ```{r}
 summary(res.autos, nb.dec=2, nb.elements =Inf, nbind = Inf, ncp=3) #les résultats avec deux décimales, pour tous les individus, toutes les variables, sur les 3 premières CP

L3/Analyse Multidimensionnelle/TP4/TP4.Rproj

@@ -0,0 +1,13 @@
+Version: 1.0
+
+RestoreWorkspace: Default
+SaveWorkspace: Default
+AlwaysSaveHistory: Default
+
+EnableCodeIndexing: Yes
+UseSpacesForTab: Yes
+NumSpacesForTab: 2
+Encoding: UTF-8
+
+RnwWeave: Sweave
+LaTeX: pdfLaTeX

L3/Analyse Multidimensionnelle/TP4/depsau.csv

@@ -0,0 +1,9 @@
+;INF05;S0510;S1020;S2035;S3550;SUP50
+ARIE;870;330;730;680;470;890
+AVER;820;1260;2460;3330;2170;2960
+H.G.;2290;1070;1420;1830;1260;2330
+GERS;1650;890;1350;2540;2090;3230
+LOT;1940;1130;1750;1660;770;1140
+H.P.;2110;1170;1640;1500;550;430
+TARN;1770;820;1260;2010;1680;2090
+T.G;1740;920;1560;2210;990;1240

L3/Analyse Multidimensionnelle/TP5/TP5.Rproj

@@ -0,0 +1,13 @@
+Version: 1.0
+
+RestoreWorkspace: Default
+SaveWorkspace: Default
+AlwaysSaveHistory: Default
+
+EnableCodeIndexing: Yes
+UseSpacesForTab: Yes
+NumSpacesForTab: 2
+Encoding: UTF-8
+
+RnwWeave: Sweave
+LaTeX: pdfLaTeX

L3/Analyse Multidimensionnelle/TP5/TP5_Enonce.Rmd

@@ -0,0 +1,249 @@
+---
+title: "TP5_Enonce"
+author: ''
+date: ''
+output:
+  pdf_document: default
+  html_document: default
+---
+
+```{r setup, include=FALSE}
+knitr::opts_chunk$set(echo = TRUE)
+```
+
+```{r}
+rm(list=ls())
+library(FactoMineR)
+```
+
+----------------------------------------------------------------------------------------
+
+Exercice 1
+
+AFC sur le lien entre couleur des cheveux et ceux des yeux 
+
+```{r}
+data("HairEyeColor")
+```
+
+```{r}
+HairEyeColor
+```
+```{r}
+data <- apply(HairEyeColor, c(1, 2), sum)
+n <- sum(data)
+data
+```
+```{r}
+barplot(data,beside=TRUE,legend.text =rownames(data),main="Effectifs observés",col=c("black","brown","red","yellow"))
+```
+
+  1) Commentez le barplot ci-dessus ? S'attend on à une situation d'indépendance ?
+  
+On voit que la couleur des yeux a une incidence sur la couleur des cheveux car il n'y a pas la même proportion de blond pour les yeux bleus que pour les autres couleurs de yeux. On peut donc s'attendre à une situation de dépendance entre ces deux variables.
+  
+  2) Etudiez cette situation par un test du chi-deux d'indépendance
+  
+```{r}
+test <- chisq.test(data)
+test
+```
+  3) Affichez le tableau des effectifs théoriques et la contribution moyenne
+```{r}
+test$expected
+
+n_cases <- ncol(data) * nrow(data)
+contrib_moy <- 100/n_cases
+contrib_moy
+```
+  4) Calculer le tableau des contributions au khi-deux  
+  
+```{r}
+contribs <- (test$observed - test$expected)**2 / test$expected * 100/test$statistic
+contribs 
+```
+  5) Calculer le tableau des probabilités associé au tableau de contingence.
+  
+```{r}
+prob <- data/sum(data)
+prob
+```
+  6) Calculer le tableau des profils lignes et le profil moyen associé.
+  
+-> Le profil ligne est une probabilité conditionnelle.
+  
+```{r}
+marginale_ligne <- apply(prob, 1, sum)
+profil_ligne <- prob / marginale_ligne
+profil_ligne_moyen <- apply(prob, 2, sum)
+
+marginale_ligne
+profil_ligne
+profil_ligne_moyen
+```
+
+  7) Calculer le tableau des profils colonnes et le profil moyen associé.
+```{r}
+marginale_colonne <- apply(prob, 2, sum)
+profil_colonne <- t(t(prob) / marginale_colonne)
+profil_colonne_moyen <- apply(prob, 1, sum)
+
+marginale_colonne
+profil_colonne
+profil_colonne_moyen
+```
+ 
+  8) Que vaut l’inertie du nuage des profils lignes ? Celle du nuage des profils colonnes ?
+
+-> inertie : la variance des profils par rapport au profil moyen. l'inertie des lignes et la même que celle des colonnes. I = chi2/Nombre d'individus
+
+```{r}
+inertie <- test$statistic/sum(data)
+inertie
+```
+
+  9) Lancer une AFC avec FactoMineR
+  
+```{r}
+library(FactoMineR)
+res.afc<-CA(data)
+
+summary(res.afc)
+
+plot(res.afc, invisible = "row")
+plot(res.afc, invisible = "col")
+
+```
+```{r}
+
+```
+  
+  
+  10) Faire la construcution des éboulis des valeurs propres
+  
+```{r}
+eigen_values <- res.afc$eig
+
+bplot <- barplot(
+  eigen_values[, 1], 
+  names.arg = 1:nrow(eigen_values),
+  main = "Eboulis des valeurs propres",
+  xlab = "Principal Components",
+  ylab = "Eigenvalues",
+  col = "lightblue"
+)
+lines(x = bplot, eigen_values[, 1], type = "b", col = "red")
+abline(h=1, col = "darkgray", lty = 5)
+```
+  11) Effectuer l'analyse des correspondances 
+  
+  ----------------------------------------------------------------------------------------
+
+Exercice 2
+
+AFC sur la répartition des tâches ménagères dans un foyer
+
+```{r}
+data<-read.table("housetasks.csv",sep=";",header = TRUE)
+data
+```
+
+```{r}
+
+barplot(as.matrix(data),beside=TRUE,legend.text=rownames(data),main="Effectifs observés",col=rainbow(length(rownames(data))))
+```
+
+  1) Commentez le barplot ci-dessus ? S'attend on à une situation d'indépendance ?
+  
+On voit que la place dans la famille a une incidence sur les taches de la famille car il n'y a pas la même proportion de Laundry chez la femme que pour les autres membres de la famille. On peut donc s'attendre à une situation de dépendance entre ces deux variables.
+  
+  
+  2) Etudiez cette situation par un test du chi-deux d'indépendance
+  
+```{r}
+data_house <- apply(data, c(1, 2), sum)
+test_house <- chisq.test(data_house)
+test_house
+```
+  3) Affichez le tableau des effectifs théoriques et la contribution moyenne
+```{r}
+test_house$expected
+
+n_cases <- ncol(data_house) * nrow(data_house)
+contrib_moy_house <- 100/n_cases
+contrib_moy_house
+```
+  4) Calculer le tableau des contributions au khi-deux  
+  
+```{r}
+contrib_house <- (test_house$observed - test_house$expected)**2 / test_house$expected * 100/test_house$statistic
+contrib_house
+```
+  5) Calculer le tableau des probabilités associé au tableau de contingence.
+  
+```{r}
+proba_house <- data_house / sum(data_house)
+proba_house
+```
+  6) Calculer le tableau des profils lignes et le profil moyen associé.
+  
+```{r}
+marginale_ligne <- apply(proba_house, 1, sum)
+profil_ligne <- proba_house / marginale_ligne
+profil_ligne_moyen <- apply(proba_house, 2, sum)
+
+marginale_ligne
+profil_ligne
+profil_ligne_moyen
+```
+  7) Calculer le tableau des profils colonnes et le profil moyen associé.
+```{r}
+marginale_colonne <- apply(proba_house, 2, sum)
+profil_colonne <- t(t(proba_house) / marginale_colonne)
+profil_colonne_moyen <- apply(proba_house, 1, sum)
+
+marginale_colonne
+profil_colonne
+profil_colonne_moyen
+```
+  8) Que vaut l’inertie du nuage des profils lignes ? Celle du nuage des profils colonnes ?
+
+
+```{r}
+inertie <- test_house$statistic / sum(data_house)
+inertie
+```
+
+  9) Lancer une AFC avec FactoMineR
+  
+```{r}
+res.afc<-CA(data)
+
+summary(res.afc,nbelements = Inf)
+
+plot(res.afc, invisible = "row")
+plot(res.afc, invisible = "col")
+
+```
+  
+  
+  10) Faire la construcution des éboulis des valeurs propres
+  
+```{r}
+eigen_values <- res.afc$eig
+
+bplot <- barplot(
+  eigen_values[, 1], 
+  names.arg = 1:nrow(eigen_values),
+  main = "Eboulis des valeurs propres",
+  xlab = "Principal Components",
+  ylab = "Eigenvalues",
+  col = "lightblue"
+)
+lines(x = bplot, eigen_values[, 1], type = "b", col = "red")
+abline(h=1, col = "darkgray", lty = 5)
+```
+  
+  11) Effectuer l'analyse des correspondances 
+Axe 1 : taches pour les femmes a gauche et les maris a droite
+Axe 2 : taches individuelles en haut, taches collectives au milieu et en bas

L3/Analyse Multidimensionnelle/TP5/housetasks.csv

@@ -0,0 +1,14 @@
+"Wife";"Alternating";"Husband";"Jointly"
+"Laundry";156;14;2;4
+"Main_meal";124;20;5;4
+"Dinner";77;11;7;13
+"Breakfeast";82;36;15;7
+"Tidying";53;11;1;57
+"Dishes";32;24;4;53
+"Shopping";33;23;9;55
+"Official";12;46;23;15
+"Driving";10;51;75;3
+"Finances";13;13;21;66
+"Insurance";8;1;53;77
+"Repairs";0;3;160;2
+"Holidays";0;1;6;153

L3/Calculs Numériques/DM1.ipynb

@@ -9,9 +9,9 @@
     "%matplotlib inline\n",
     "%config InlineBackend.figure_format = 'retina'\n",
     "\n",
-    "import numpy as np                       # pour les numpy array\n",
-    "import matplotlib.pyplot as plt          # librairie graphique\n",
-    "from scipy.integrate import odeint       # seulement odeint"
+    "import matplotlib.pyplot as plt  # librairie graphique\n",
+    "import numpy as np  # pour les numpy array\n",
+    "from scipy.integrate import odeint  # seulement odeint"
    ]
   },
   {
@@ -103,13 +103,14 @@
    "source": [
     "# Initialisation des variables\n",
     "T = 130\n",
-    "t = np.arange(0, T+1)\n",
+    "t = np.arange(0, T + 1)\n",
     "\n",
-    "K = 50       # capacité d'accueil maximale du milieu\n",
+    "K = 50  # capacité d'accueil maximale du milieu\n",
     "K_star = 50  # capacité minimale pour maintenir l'espèce\n",
-    "r = 0.1      # taux de  corissance de la capacité d'accueil du milieu.\n",
-    "t_fl = 30    # la find ed la période de formation.\n",
-    "K0 = 1       # Valeur initiale de la capacité d'accueil du milieu.\n",
+    "r = 0.1  # taux de  corissance de la capacité d'accueil du milieu.\n",
+    "t_fl = 30  # la find ed la période de formation.\n",
+    "K0 = 1  # Valeur initiale de la capacité d'accueil du milieu.\n",
+    "\n",
     "\n",
     "def C(t):\n",
     "    \"\"\"\n",
@@ -117,11 +118,12 @@
     "    \"\"\"\n",
     "    return K_star + K / (1 + (K / K0 - 1) * np.exp(-r * (t - t_fl)))\n",
     "\n",
+    "\n",
     "# On trace le graphique de la solution exacte\n",
     "plt.plot(t, C(t), label=\"C(t)\")\n",
-    "plt.hlines(K_star, 0, T, linestyle='dotted', label=\"C = K*\", color='red')\n",
-    "plt.hlines(K + K_star, 0, T, linestyle='dotted', label=\"C = K + K*\", color='green')\n",
-    "plt.plot(t_fl, K0 + K_star, 'o', label=\"(t_fl, K0 + K*)\")\n",
+    "plt.hlines(K_star, 0, T, linestyle=\"dotted\", label=\"C = K*\", color=\"red\")\n",
+    "plt.hlines(K + K_star, 0, T, linestyle=\"dotted\", label=\"C = K + K*\", color=\"green\")\n",
+    "plt.plot(t_fl, K0 + K_star, \"o\", label=\"(t_fl, K0 + K*)\")\n",
     "plt.legend()\n",
     "plt.xlim(0, 130)\n",
     "plt.suptitle(\"Courbe de la solution exacte du problème\")\n",
@@ -133,14 +135,16 @@
     "N0 = 10\n",
     "r_N = 0.2\n",
     "\n",
+    "\n",
     "def dN(N, t, C_sol):\n",
     "    \"\"\"\n",
     "    Fonction calculant la dérivée de la solution approchée du problème à l'instant t dépendant de N(t) et de C(t)\n",
     "    \"\"\"\n",
     "    return r_N * N * (1 - N / C_sol(t))\n",
     "\n",
+    "\n",
     "t = np.linspace(0, T, 200)\n",
-    "N_sol = odeint(dN, N0, t, args=(C,)) # On calcule la solution a l'aide de odeint\n",
+    "N_sol = odeint(dN, N0, t, args=(C,))  # On calcule la solution a l'aide de odeint\n",
     "\n",
     "# On trace le graphique de la solution approchée en comparaison à la solution exacte\n",
     "plt.plot(t, N_sol, label=\"Solution approchée\")\n",
@@ -219,42 +223,47 @@
     "T, N = 200, 100\n",
     "H0, P0 = 1500, 500\n",
     "\n",
+    "\n",
     "def F(X, t, a, b, c, d, p):\n",
     "    \"\"\"Fonction second membre pour le système\"\"\"\n",
     "    x, y = X\n",
-    "    return np.array([x * (a - p - b*y), y * (-c - p + d*x)])\n",
+    "    return np.array([x * (a - p - b * y), y * (-c - p + d * x)])\n",
     "\n",
-    "t = np.linspace(0, T, N+1)\n",
-    "sardines, requins = np.meshgrid(\n",
-    "    np.linspace(0.1, 3000, 20),\n",
-    "    np.linspace(0.1, 4500, 30)\n",
-    ")\n",
+    "\n",
+    "t = np.linspace(0, T, N + 1)\n",
+    "sardines, requins = np.meshgrid(np.linspace(0.1, 3000, 20), np.linspace(0.1, 4500, 30))\n",
     "fsardines = F((sardines, requins), t, a, b, c, d, 0)[0]\n",
     "frequins = F((sardines, requins), t, a, b, c, d, 0)[1]\n",
-    "n_sndmb = np.sqrt(fsardines**2 + frequins**2)  \n",
+    "n_sndmb = np.sqrt(fsardines**2 + frequins**2)\n",
     "\n",
     "# On crée une figure à trois graphiques\n",
     "fig = plt.figure(figsize=(12, 6))\n",
-    "ax = fig.add_subplot(1, 2, 2) # subplot pour le champ de vecteurs et le graphe sardines vs requins\n",
-    "axr = fig.add_subplot(2, 2, 1) # subplot pour le graphe du nombre de requins en fonction du temps\n",
-    "axs = fig.add_subplot(2, 2, 3) # subplot pour le graphe du nombre de sardines en fonction du temps  \n",
-    "ax.quiver(sardines, requins, fsardines/n_sndmb, frequins/n_sndmb)\n",
+    "ax = fig.add_subplot(\n",
+    "    1, 2, 2\n",
+    ")  # subplot pour le champ de vecteurs et le graphe sardines vs requins\n",
+    "axr = fig.add_subplot(\n",
+    "    2, 2, 1\n",
+    ")  # subplot pour le graphe du nombre de requins en fonction du temps\n",
+    "axs = fig.add_subplot(\n",
+    "    2, 2, 3\n",
+    ")  # subplot pour le graphe du nombre de sardines en fonction du temps\n",
+    "ax.quiver(sardines, requins, fsardines / n_sndmb, frequins / n_sndmb)\n",
     "\n",
     "list_p = [0, 0.02, 0.04, 0.06]\n",
     "for k, pk in enumerate(list_p):\n",
-    "    couleur = (0, k/len(list_p), 1-k/len(list_p))\n",
+    "    couleur = (0, k / len(list_p), 1 - k / len(list_p))\n",
     "    X = odeint(F, np.array([H0, P0]), t, args=(a, b, c, d, pk))\n",
-    "    \n",
-    "    # Tracer la courbe parametrée (H(t),P(t)) \n",
+    "\n",
+    "    # Tracer la courbe parametrée (H(t),P(t))\n",
     "    ax.plot(X[:, 0], X[:, 1], linewidth=2, color=couleur, label=f\"$p={pk}$\")\n",
-    "    \n",
-    "    # Tracer H en fonction du temps \n",
+    "\n",
+    "    # Tracer H en fonction du temps\n",
     "    axs.plot(t, X[:, 0], label=f\"Sardines pour p={pk}\", color=couleur)\n",
-    "    \n",
+    "\n",
     "    # Tracer P en fonction du temps\n",
     "    axr.plot(t, X[:, 1], label=f\"Requins pour p={pk}\", color=couleur)\n",
-    "    \n",
-    "ax.axis('equal')\n",
+    "\n",
+    "ax.axis(\"equal\")\n",
     "ax.set_title(\"Champ de vecteur du problème de Lotka-Volterra\")\n",
     "ax.set_xlabel(\"Sardines\")\n",
     "ax.set_ylabel(\"Requins\")\n",
@@ -266,8 +275,8 @@
     "axs.set_xlabel(\"Temps t\")\n",
     "axs.set_ylabel(\"Sardines\")\n",
     "\n",
-    "axs.set_title('Evolution des sardines')\n",
-    "axr.set_title('Evolution des requins')\n",
+    "axs.set_title(\"Evolution des sardines\")\n",
+    "axr.set_title(\"Evolution des requins\")\n",
     "plt.show()"
    ]
   },
@@ -309,11 +318,11 @@
    "source": [
     "def crank_nicolson(y0, T, N, r):\n",
     "    \"\"\"\n",
-    "    schéma de Crank-Nicolson pour le modèle de Malthus \n",
-    "    \n",
+    "    schéma de Crank-Nicolson pour le modèle de Malthus\n",
+    "\n",
     "    Parameters\n",
     "    ----------\n",
-    "    \n",
+    "\n",
     "    y0: float\n",
     "        donnée initiale\n",
     "    T: float\n",
@@ -325,34 +334,35 @@
     "\n",
     "    Returns\n",
     "    -------\n",
-    "    \n",
+    "\n",
     "    t: ndarray\n",
     "        les instants où la solution approchée est calculée\n",
     "    y: ndarray\n",
     "        les valeurs de la solution approchée par le theta-schema\n",
     "    \"\"\"\n",
-    "    \n",
+    "\n",
     "    dt = T / N\n",
-    "    t = np.zeros(N+1)\n",
-    "    y = np.zeros(N+1)\n",
+    "    t = np.zeros(N + 1)\n",
+    "    y = np.zeros(N + 1)\n",
     "    tk, yk = 0, y0\n",
     "    y[0] = yk\n",
-    "    \n",
+    "\n",
     "    for n in range(N):\n",
     "        tk += dt\n",
     "        yk *= (2 + dt * r) / (2 - dt * r)\n",
-    "        y[n+1] = yk\n",
-    "        t[n+1] = tk\n",
-    "        \n",
+    "        y[n + 1] = yk\n",
+    "        t[n + 1] = tk\n",
+    "\n",
     "    return t, y\n",
     "\n",
+    "\n",
     "def euler_explicit(y0, T, N, r):\n",
     "    \"\"\"\n",
-    "    schéma de d'Euler pour le modèle de Malthus \n",
-    "    \n",
+    "    schéma de d'Euler pour le modèle de Malthus\n",
+    "\n",
     "    Parameters\n",
     "    ----------\n",
-    "    \n",
+    "\n",
     "    y0: float\n",
     "        donnée initiale\n",
     "    T: float\n",
@@ -364,29 +374,30 @@
     "\n",
     "    Returns\n",
     "    -------\n",
-    "    \n",
+    "\n",
     "    t: ndarray\n",
     "        les instants où la solution approchée est calculée\n",
     "    y: ndarray\n",
     "        les valeurs de la solution approchée par le theta-schema\n",
     "    \"\"\"\n",
     "    dt = T / N\n",
-    "    t = np.zeros(N+1)\n",
-    "    y = np.zeros(N+1)\n",
+    "    t = np.zeros(N + 1)\n",
+    "    y = np.zeros(N + 1)\n",
     "    tk, yk = 0, y0\n",
     "    y[0] = yk\n",
-    "    \n",
+    "\n",
     "    for n in range(N):\n",
     "        tk += dt\n",
     "        yk += dt * r * yk\n",
-    "        y[n+1] = yk\n",
-    "        t[n+1] = tk\n",
-    "        \n",
+    "        y[n + 1] = yk\n",
+    "        t[n + 1] = tk\n",
+    "\n",
     "    return t, y\n",
     "\n",
+    "\n",
     "def solution_exacte(t):\n",
     "    \"\"\"\n",
-    "    Fonction calculant la solution exacte du modèle de Malthus à l'instant t \n",
+    "    Fonction calculant la solution exacte du modèle de Malthus à l'instant t\n",
     "    \"\"\"\n",
     "    return y0 * np.exp(r * t)"
    ]
@@ -436,23 +447,25 @@
     "# Schéma d'Euler explicite\n",
     "ax = fig.add_subplot(1, 2, 1)\n",
     "for n in liste_N:\n",
-    "    t, y = euler_explicit(y0, T, n, r) # On calcule la fonction Euler pour chaque n\n",
+    "    t, y = euler_explicit(y0, T, n, r)  # On calcule la fonction Euler pour chaque n\n",
     "    ax.scatter(t, y, label=f\"Solution approchée pour N={n}\")\n",
-    "    \n",
-    "ax.plot(t_exact, solution_exacte(t_exact), label='Solution exacte')\n",
+    "\n",
+    "ax.plot(t_exact, solution_exacte(t_exact), label=\"Solution exacte\")\n",
     "ax.legend()\n",
-    "ax.axis('equal')\n",
+    "ax.axis(\"equal\")\n",
     "ax.set_title(\"Schéma d'Euler explicite\")\n",
     "ax.set_xlabel(\"Temps t\")\n",
     "ax.set_ylabel(\"y\")\n",
-    "    \n",
+    "\n",
     "\n",
     "# Schéma de Crank-Nicolson\n",
     "ax = fig.add_subplot(1, 2, 2)\n",
     "for n in liste_N:\n",
-    "    t, y = crank_nicolson(y0, T, n, r) # On calcule la fonction Crank-Nicolson pour chaque n\n",
+    "    t, y = crank_nicolson(\n",
+    "        y0, T, n, r\n",
+    "    )  # On calcule la fonction Crank-Nicolson pour chaque n\n",
     "    ax.scatter(t, y, label=f\"Solution approchée pour N={n}\")\n",
-    "ax.plot(t_exact, solution_exacte(t_exact), label='Solution exacte')\n",
+    "ax.plot(t_exact, solution_exacte(t_exact), label=\"Solution exacte\")\n",
     "ax.legend()\n",
     "ax.set_title(\"Schéma de Crank-Nicolson\")\n",
     "ax.set_xlabel(\"Temps t\")\n",
@@ -504,7 +517,7 @@
     "    t, sol_appr = crank_nicolson(y0, T, n, r)\n",
     "    sol_ex = solution_exacte(t)\n",
     "    erreur = np.max(np.abs(sol_appr - sol_ex))\n",
-    "    #erreur = np.linalg.norm(sol_appr - sol_ex, np.inf)\n",
+    "    # erreur = np.linalg.norm(sol_appr - sol_ex, np.inf)\n",
     "    print(f\"Delta_t = {T / N:10.3e}, e = {erreur:10.3e}\")\n",
     "    liste_erreur[k] = erreur\n",
     "\n",
@@ -514,7 +527,7 @@
     "ax.scatter(liste_delta, liste_erreur, color=\"black\")\n",
     "for p in [0.5, 1, 2]:\n",
     "    C = liste_erreur[-1] / (liste_delta[-1] ** p)\n",
-    "    plt.plot(liste_delta, C * liste_delta ** p, label=f\"$p={p}$\")\n",
+    "    plt.plot(liste_delta, C * liste_delta**p, label=f\"$p={p}$\")\n",
     "ax.set_title(\"Erreur du schéma de Crank-Nicolson\")\n",
     "ax.set_xlabel(r\"$\\Delta t$\")\n",
     "ax.set_ylabel(r\"$e(\\Delta t)$\")\n",

L3/Calculs Numériques/DM2.ipynb

@@ -19,8 +19,8 @@
    },
    "outputs": [],
    "source": [
-    "import numpy as np\n",
-    "import matplotlib.pyplot as plt"
+    "import matplotlib.pyplot as plt\n",
+    "import numpy as np"
    ]
   },
   {
@@ -153,22 +153,27 @@
     "def M(x):\n",
     "    \"\"\"\n",
     "    Retourne la matrice du système (2)\n",
-    "    \n",
+    "\n",
     "    Parameters\n",
     "    ----------\n",
-    "    \n",
+    "\n",
     "    x: ndarray\n",
     "        vecteurs contenant les valeurs [x0, x1, ..., xN]\n",
-    "        \n",
+    "\n",
     "    Returns\n",
     "    -------\n",
-    "    \n",
+    "\n",
     "    out: ndarray\n",
     "        matrice du système (2)\n",
     "    \"\"\"\n",
-    "    h = x[1:] - x[:-1] # x[i+1] - x[i]\n",
-    "    return np.diag(2*(1/h[:-1] + 1/h[1:])) + np.diag(1/h[1:-1], k=-1) + np.diag(1/h[1:-1], k=1)\n",
-    "    \n",
+    "    h = x[1:] - x[:-1]  # x[i+1] - x[i]\n",
+    "    return (\n",
+    "        np.diag(2 * (1 / h[:-1] + 1 / h[1:]))\n",
+    "        + np.diag(1 / h[1:-1], k=-1)\n",
+    "        + np.diag(1 / h[1:-1], k=1)\n",
+    "    )\n",
+    "\n",
+    "\n",
     "# Test\n",
     "print(M(np.array([0, 1, 2, 3, 4])))"
    ]
@@ -191,10 +196,10 @@
     "def sprime(x, y, p0, pN):\n",
     "    \"\"\"\n",
     "    Retourne la solution du système (2)\n",
-    "    \n",
+    "\n",
     "    Parameters\n",
     "    ----------\n",
-    "    \n",
+    "\n",
     "    x: ndarray\n",
     "        vecteurs contenant les valeurs [x0, x1, ..., xN]\n",
     "    y: ndarray\n",
@@ -203,18 +208,18 @@
     "        première valeur du vecteur p\n",
     "    pN: int\n",
     "        N-ième valeur du vecteur p\n",
-    "        \n",
+    "\n",
     "    Returns\n",
     "    -------\n",
-    "    \n",
+    "\n",
     "    out: ndarray\n",
     "        solution du système (2)\n",
     "    \"\"\"\n",
     "    h = x[1:] - x[:-1]\n",
     "    delta_y = (y[1:] - y[:-1]) / h\n",
-    "    c = 3 * (delta_y[1:]/h[1:] + delta_y[:-1]/h[:-1])\n",
-    "    c[0] -= p0/h[0]\n",
-    "    c[-1] -= pN/h[-1]\n",
+    "    c = 3 * (delta_y[1:] / h[1:] + delta_y[:-1] / h[:-1])\n",
+    "    c[0] -= p0 / h[0]\n",
+    "    c[-1] -= pN / h[-1]\n",
     "    return np.linalg.solve(M(x), c)"
    ]
   },
@@ -273,52 +278,54 @@
     "def f(x):\n",
     "    \"\"\"\n",
     "    Retourne la fonction f évaluée aux points x\n",
-    "    \n",
+    "\n",
     "    Parameters\n",
     "    ----------\n",
-    "    \n",
+    "\n",
     "    x: ndarray\n",
     "        vecteurs contenant les valeurs [x0, x1, ..., xN]\n",
-    "        \n",
+    "\n",
     "    Returns\n",
     "    -------\n",
-    "    \n",
+    "\n",
     "    out: ndarray\n",
     "        Valeur de la fonction f aux points x\n",
     "    \"\"\"\n",
     "    return 1 / (1 + x**2)\n",
     "\n",
+    "\n",
     "def fprime(x):\n",
     "    \"\"\"\n",
     "    Retourne la fonction dérivée de f évaluée aux points x\n",
-    "    \n",
+    "\n",
     "    Parameters\n",
     "    ----------\n",
-    "    \n",
+    "\n",
     "    x: ndarray\n",
     "        vecteurs contenant les valeurs [x0, x1, ..., xN]\n",
-    "        \n",
+    "\n",
     "    Returns\n",
     "    -------\n",
-    "    \n",
+    "\n",
     "    out: ndarray\n",
     "        Valeur de la fonction dérivée de f aux points x\n",
     "    \"\"\"\n",
-    "    return -2*x/((1+x**2)**2)\n",
+    "    return -2 * x / ((1 + x**2) ** 2)\n",
     "\n",
-    "# Paramètres \n",
+    "\n",
+    "# Paramètres\n",
     "xx = np.linspace(-5, 5, 200)\n",
     "x = np.linspace(-5, 5, 21)\n",
     "pi = sprime(x, f(x), fprime(-5), fprime(5))\n",
     "\n",
     "# Graphique\n",
     "fig, ax = plt.subplots(figsize=(6, 6))\n",
-    "ax.plot(xx, fprime(xx), label=f'$f\\'$', color='red')\n",
-    "ax.scatter(x[1:-1], pi, label=f'$p_i$')\n",
+    "ax.plot(xx, fprime(xx), label=\"$f'$\", color=\"red\")\n",
+    "ax.scatter(x[1:-1], pi, label=\"$p_i$\")\n",
     "ax.legend()\n",
-    "ax.set_xlabel(f'$x$')\n",
-    "ax.set_ylabel(f'$f(x)$')\n",
-    "ax.set_title('Les pentes de la spline cubique')"
+    "ax.set_xlabel(\"$x$\")\n",
+    "ax.set_ylabel(\"$f(x)$\")\n",
+    "ax.set_title(\"Les pentes de la spline cubique\")"
    ]
   },
   {
@@ -363,10 +370,10 @@
     "def splines(x, y, p0, pN):\n",
     "    \"\"\"\n",
     "    Retourne la matrice S de taille (4, N)\n",
-    "    \n",
+    "\n",
     "    Parameters\n",
     "    ----------\n",
-    "    \n",
+    "\n",
     "    x: ndarray\n",
     "        vecteurs contenant les valeurs [x0, x1, ..., xN]\n",
     "    y: ndarray\n",
@@ -375,20 +382,20 @@
     "        première valeur du vecteur p\n",
     "    pN: int\n",
     "        N-ième valeur du vecteur p\n",
-    "        \n",
+    "\n",
     "    Returns\n",
     "    -------\n",
-    "    \n",
+    "\n",
     "    out: ndarray\n",
     "        Matrice S de taille (4, N) tel que la i-ième ligne contient les valeurs a_i, b_i, c_i et d_i\n",
     "    \"\"\"\n",
     "    h = x[1:] - x[:-1]\n",
     "    delta_y = (y[1:] - y[:-1]) / h\n",
-    "    \n",
+    "\n",
     "    a = y\n",
     "    b = np.concatenate((np.array([p0]), sprime(x, y, p0, pN), np.array([pN])))\n",
-    "    c = 3/h * delta_y - (b[1:] + 2*b[:-1]) / h\n",
-    "    d = 1/h**2 * (b[1:] + b[:-1]) - 2/h**2 * delta_y\n",
+    "    c = 3 / h * delta_y - (b[1:] + 2 * b[:-1]) / h\n",
+    "    d = 1 / h**2 * (b[1:] + b[:-1]) - 2 / h**2 * delta_y\n",
     "    return np.transpose([a[:-1], b[:-1], c, d])"
    ]
   },
@@ -412,34 +419,38 @@
    },
    "outputs": [],
    "source": [
-    "def spline_eval( x, xx, S ):\n",
+    "def spline_eval(x, xx, S):\n",
     "    \"\"\"\n",
     "    Evalue une spline définie par des noeuds équirepartis\n",
-    "    \n",
+    "\n",
     "    Parameters\n",
     "    ----------\n",
-    "    \n",
+    "\n",
     "    x: ndarray\n",
     "        noeuds définissant la spline\n",
-    "        \n",
+    "\n",
     "    xx: ndarray\n",
     "        abscisses des points d'évaluation\n",
-    "    \n",
+    "\n",
     "    S: ndarray\n",
     "        de taille (x.size-1, 4)\n",
     "        tableau dont la i-ème ligne contient les coéficients du polynome cubique qui est la restriction\n",
     "        de la spline à l'intervalle [x_i, x_{i+1}]\n",
-    "        \n",
+    "\n",
     "    Returns\n",
     "    -------\n",
-    "    \n",
+    "\n",
     "    ndarray\n",
     "        ordonnées des points d'évaluation\n",
     "    \"\"\"\n",
-    "    ind = ( np.floor( ( xx - x[ 0 ] ) / ( x[ 1 ] - x[ 0 ] ) ) ).astype( int )\n",
-    "    ind = np.where( ind == x.size-1, ind - 1 , ind )\n",
-    "    yy = S[ ind, 0 ] + S[ ind, 1 ] * ( xx - x[ ind ] ) + \\\n",
-    "        S[ ind, 2 ] * ( xx - x[ ind ] )**2 + S[ ind, 3 ] * ( xx - x[ ind ] )**3\n",
+    "    ind = (np.floor((xx - x[0]) / (x[1] - x[0]))).astype(int)\n",
+    "    ind = np.where(ind == x.size - 1, ind - 1, ind)\n",
+    "    yy = (\n",
+    "        S[ind, 0]\n",
+    "        + S[ind, 1] * (xx - x[ind])\n",
+    "        + S[ind, 2] * (xx - x[ind]) ** 2\n",
+    "        + S[ind, 3] * (xx - x[ind]) ** 3\n",
+    "    )\n",
     "    return yy"
    ]
   },
@@ -472,21 +483,21 @@
     }
    ],
    "source": [
-    "# Paramètres \n",
+    "# Paramètres\n",
     "x = np.linspace(-5, 5, 6)\n",
-    "y = np.random.rand(5+1)\n",
+    "y = np.random.rand(5 + 1)\n",
     "xx = np.linspace(-5, 5, 200)\n",
     "s = splines(x, y, 0, 0)\n",
     "s_eval = spline_eval(x, xx, s)\n",
     "\n",
     "# Graphique\n",
     "fig, ax = plt.subplots(figsize=(6, 6))\n",
-    "ax.plot(xx, s_eval, label='spline cubique interpolateur', color='red')\n",
-    "ax.scatter(x, y, label=f'$(x_i, y_i)$')\n",
+    "ax.plot(xx, s_eval, label=\"spline cubique interpolateur\", color=\"red\")\n",
+    "ax.scatter(x, y, label=\"$(x_i, y_i)$\")\n",
     "ax.legend()\n",
-    "ax.set_xlabel(f'$x$')\n",
-    "ax.set_ylabel(f'$f(x)$')\n",
-    "ax.set_title('Evaluation de la spline cubique')"
+    "ax.set_xlabel(\"$x$\")\n",
+    "ax.set_ylabel(\"$f(x)$\")\n",
+    "ax.set_title(\"Evaluation de la spline cubique\")"
    ]
   },
   {
@@ -525,7 +536,7 @@
     }
    ],
    "source": [
-    "# Paramètres \n",
+    "# Paramètres\n",
     "a, b = -5, 5\n",
     "N_list = [4, 9, 19]\n",
     "\n",
@@ -533,17 +544,17 @@
     "fig, ax = plt.subplots(figsize=(15, 6))\n",
     "\n",
     "for N in N_list:\n",
-    "    x = np.linspace(a, b, N+1)\n",
+    "    x = np.linspace(a, b, N + 1)\n",
     "    xx = np.linspace(a, b, 200)\n",
     "    s = splines(x, f(x), 0, 0)\n",
     "    s_eval = spline_eval(x, xx, s)\n",
-    "    ax.plot(xx, s_eval, label=f'Spline cubique interpolateur pour N={N}')\n",
-    "    ax.scatter(x, f(x), label=f'f(x) pour N={N}')\n",
-    "    \n",
+    "    ax.plot(xx, s_eval, label=f\"Spline cubique interpolateur pour N={N}\")\n",
+    "    ax.scatter(x, f(x), label=f\"f(x) pour N={N}\")\n",
+    "\n",
     "ax.legend()\n",
-    "ax.set_xlabel(f'$x$')\n",
-    "ax.set_ylabel(f'$f(x)$')\n",
-    "ax.set_title('Evaluation de la spline cubique')"
+    "ax.set_xlabel(\"$x$\")\n",
+    "ax.set_ylabel(\"$f(x)$\")\n",
+    "ax.set_title(\"Evaluation de la spline cubique\")"
    ]
   },
   {

L3/Calculs Numériques/DM3.ipynb

@@ -19,10 +19,10 @@
    },
    "outputs": [],
    "source": [
+    "import matplotlib.pyplot as plt\n",
     "import numpy as np\n",
-    "from scipy.special import roots_legendre\n",
     "from scipy.integrate import quad\n",
-    "import matplotlib.pyplot as plt"
+    "from scipy.special import roots_legendre"
    ]
   },
   {
@@ -60,17 +60,20 @@
    },
    "outputs": [],
    "source": [
-    "def f0(x): \n",
+    "def f0(x):\n",
     "    return np.exp(x)\n",
     "\n",
+    "\n",
     "def f1(x):\n",
-    "    return 1 / (1 + 16*np.power(x, 2))\n",
+    "    return 1 / (1 + 16 * np.power(x, 2))\n",
+    "\n",
     "\n",
     "def f2(x):\n",
-    "    return np.power(np.abs(x**2 - 1/4), 3)\n",
+    "    return np.power(np.abs(x**2 - 1 / 4), 3)\n",
+    "\n",
     "\n",
     "def f3(x):\n",
-    "    return np.power(np.abs(x+1/2), 1/2)"
+    "    return np.power(np.abs(x + 1 / 2), 1 / 2)"
    ]
   },
   {
@@ -176,10 +179,12 @@
    ],
    "source": [
     "for f in [f0, f1, f2, f3]:\n",
-    "    print(f'Calcule de I(f) par la méthode de gauss et par la formule quadratique pour la fonction {f.__name__}')\n",
+    "    print(\n",
+    "        f\"Calcule de I(f) par la méthode de gauss et par la formule quadratique pour la fonction {f.__name__}\"\n",
+    "    )\n",
     "    for n in range(1, 11):\n",
     "        print(f\"Pour n = {n}, gauss = {gauss(f, n)} et quad = {quad(f, -1, 1)[0]}\")\n",
-    "    print('')"
+    "    print(\"\")"
    ]
   },
   {
@@ -211,10 +216,10 @@
     "def simpson(f, N):\n",
     "    if N % 2 == 0:\n",
     "        raise ValueError(\"N doit est impair.\")\n",
-    "    \n",
+    "\n",
     "    h = 2 / (2 * (N - 1) // 2)\n",
     "    fx = f(np.linspace(-1, 1, N))\n",
-    "    \n",
+    "\n",
     "    return (h / 3) * (fx[0] + 4 * fx[1:-1:2].sum() + 2 * fx[2:-1:2].sum() + fx[-1])"
    ]
   },
@@ -270,10 +275,12 @@
    ],
    "source": [
     "for f in [f0, f1, f2, f3]:\n",
-    "    print(f'Calcule de I(f) par la méthode de simpson et par la formule quadratique pour la fonction {f.__name__}')\n",
+    "    print(\n",
+    "        f\"Calcule de I(f) par la méthode de simpson et par la formule quadratique pour la fonction {f.__name__}\"\n",
+    "    )\n",
     "    for n in range(3, 16, 2):\n",
     "        print(f\"Pour n = {n}, simpson = {simpson(f, n)} et quad = {quad(f, -1, 1)[0]}\")\n",
-    "    print('')"
+    "    print(\"\")"
    ]
   },
   {
@@ -336,7 +343,7 @@
     "    elif N == 1:\n",
     "        return x\n",
     "    else:\n",
-    "        return 2 * x * poly_tchebychev(x, N-1) - poly_tchebychev(x, N-2)"
+    "        return 2 * x * poly_tchebychev(x, N - 1) - poly_tchebychev(x, N - 2)"
    ]
   },
   {
@@ -346,7 +353,7 @@
    "outputs": [],
    "source": [
     "def points_tchebychev(N):\n",
-    "    k = np.arange(1, N+1)\n",
+    "    k = np.arange(1, N + 1)\n",
     "    return np.cos((2 * k - 1) * np.pi / (2 * N))"
    ]
   },
@@ -449,7 +456,7 @@
     "    lamk = np.zeros(N)\n",
     "    for k in range(N):\n",
     "        s = 0\n",
-    "        for m in range(1, N//2+1):\n",
+    "        for m in range(1, N // 2 + 1):\n",
     "            T = poly_tchebychev(xk[k], 2 * m)\n",
     "            s += 2 * T / (4 * np.power(m, 2) - 1)\n",
     "        lamk[k] = 2 / N * (1 - s)\n",
@@ -529,10 +536,12 @@
    ],
    "source": [
     "for f in [f0, f1, f2, f3]:\n",
-    "    print(f'Calcule de I(f) par la méthode de fejer et par la formule quadratique pour la fonction {f.__name__}')\n",
+    "    print(\n",
+    "        f\"Calcule de I(f) par la méthode de fejer et par la formule quadratique pour la fonction {f.__name__}\"\n",
+    "    )\n",
     "    for n in range(1, 11):\n",
     "        print(f\"Pour n = {n}, fejer = {fejer(f, n)} et quad = {quad(f, -1, 1)[0]}\")\n",
-    "    print('')"
+    "    print(\"\")"
    ]
   },
   {
@@ -568,26 +577,44 @@
     "figure = plt.figure(figsize=(15, 10))\n",
     "for fi, f in enumerate([f0, f1, f2, f3]):\n",
     "    error_gauss = np.zeros((N,))\n",
-    "    error_simp = np.zeros(((N-1)//2,))\n",
+    "    error_simp = np.zeros(((N - 1) // 2,))\n",
     "    error_fejer = np.zeros((N,))\n",
     "    I_quad, _ = quad(f, -1, 1)\n",
-    "    \n",
-    "    for n in range(1, N+1):\n",
+    "\n",
+    "    for n in range(1, N + 1):\n",
     "        I_gauss = gauss(f, n)\n",
-    "        error_gauss[n-1]  = np.abs(I_gauss - I_quad)\n",
+    "        error_gauss[n - 1] = np.abs(I_gauss - I_quad)\n",
     "        I_fejer = fejer(f, n)\n",
-    "        error_fejer[n-1]  = np.abs(I_fejer - I_quad)\n",
-    "    \n",
-    "    for n in range( 3, N+1, 2 ):\n",
+    "        error_fejer[n - 1] = np.abs(I_fejer - I_quad)\n",
+    "\n",
+    "    for n in range(3, N + 1, 2):\n",
     "        I_simp = simpson(f, n)\n",
-    "        error_simp[(n-2)//2] = np.abs(I_simp - I_quad)\n",
-    "    \n",
+    "        error_simp[(n - 2) // 2] = np.abs(I_simp - I_quad)\n",
+    "\n",
     "    ax = figure.add_subplot(2, 2, fi + 1)\n",
-    "    ax.scatter(np.arange(1, N+1), np.log10(error_gauss, out = -16. * np.ones(error_gauss.shape), \n",
-    "                                          where = (error_gauss > 1e-16)), label = 'Gauss', marker=\"+\")\n",
-    "    ax.scatter(np.arange(3, N+1, 2), np.log10( error_simp ), label = 'Simpson', marker=\"+\")\n",
-    "    ax.scatter(np.arange(1, N+1), np.log10(error_fejer, out = -16. * np.ones(error_fejer.shape), \n",
-    "                                          where = (error_fejer > 1e-16)), label = 'Fejer', marker=\"+\")\n",
+    "    ax.scatter(\n",
+    "        np.arange(1, N + 1),\n",
+    "        np.log10(\n",
+    "            error_gauss,\n",
+    "            out=-16.0 * np.ones(error_gauss.shape),\n",
+    "            where=(error_gauss > 1e-16),\n",
+    "        ),\n",
+    "        label=\"Gauss\",\n",
+    "        marker=\"+\",\n",
+    "    )\n",
+    "    ax.scatter(\n",
+    "        np.arange(3, N + 1, 2), np.log10(error_simp), label=\"Simpson\", marker=\"+\"\n",
+    "    )\n",
+    "    ax.scatter(\n",
+    "        np.arange(1, N + 1),\n",
+    "        np.log10(\n",
+    "            error_fejer,\n",
+    "            out=-16.0 * np.ones(error_fejer.shape),\n",
+    "            where=(error_fejer > 1e-16),\n",
+    "        ),\n",
+    "        label=\"Fejer\",\n",
+    "        marker=\"+\",\n",
+    "    )\n",
     "    ax.legend()\n",
     "    ax.set_title(f\"Erreur de différentes méthodes de quadrature pour {f.__name__}\")\n",
     "    ax.set_xlabel(\"n\")\n",
@@ -672,18 +699,26 @@
     "def f(x, k):\n",
     "    return x**k\n",
     "\n",
+    "\n",
     "print(\"-----------------------------------------------------------------------\")\n",
-    "print(\"{:>5s}     | {:>7s} {:>9s} {:>9s} {:>9s} {:>9s} {:>9s}\".format(\"N\", \"x^0\", \"x^2\", \"x^4\", \"x^6\", \"x^8\", \"x^10\"))\n",
+    "print(\n",
+    "    \"{:>5s}     | {:>7s} {:>9s} {:>9s} {:>9s} {:>9s} {:>9s}\".format(\n",
+    "        \"N\", \"x^0\", \"x^2\", \"x^4\", \"x^6\", \"x^8\", \"x^10\"\n",
+    "    )\n",
+    ")\n",
     "print(\"-----------------------------------------------------------------------\")\n",
     "\n",
     "for N in range(1, 11):\n",
     "    approx_errors = []\n",
-    "    for k in [x for x in range(0, 11, 2)]:\n",
+    "    for k in list(range(0, 11, 2)):\n",
     "        I_approx = gauss(lambda x: f(x, k), N)\n",
     "        I_exact = 2 / (k + 1) if k % 2 == 0 else 0\n",
     "        approx_error = np.abs(I_approx - I_exact)\n",
     "        approx_errors.append(approx_error)\n",
-    "    print(\"{:5d}     |    \".format(N) + \" \".join(\"{:.3f}    \".format(e) for e in approx_errors))"
+    "    print(\n",
+    "        f\"{N:5d}     |    \"\n",
+    "        + \" \".join(f\"{e:.3f}    \" for e in approx_errors)\n",
+    "    )"
    ]
   },
   {
@@ -722,18 +757,26 @@
     "def f(x, k):\n",
     "    return x**k\n",
     "\n",
+    "\n",
     "print(\"-----------------------------------------------------------------------\")\n",
-    "print(\"{:>5s}     | {:>7s} {:>9s} {:>9s} {:>9s} {:>9s} {:>9s}\".format(\"N\", \"x^0\", \"x^2\", \"x^4\", \"x^6\", \"x^8\", \"x^10\"))\n",
+    "print(\n",
+    "    \"{:>5s}     | {:>7s} {:>9s} {:>9s} {:>9s} {:>9s} {:>9s}\".format(\n",
+    "        \"N\", \"x^0\", \"x^2\", \"x^4\", \"x^6\", \"x^8\", \"x^10\"\n",
+    "    )\n",
+    ")\n",
     "print(\"-----------------------------------------------------------------------\")\n",
     "\n",
     "for N in range(1, 11):\n",
     "    approx_errors = []\n",
-    "    for k in [x for x in range(0, 11, 2)]:\n",
+    "    for k in list(range(0, 11, 2)):\n",
     "        I_approx = fejer(lambda x: f(x, k), N)\n",
     "        I_exact = 2 / (k + 1) if k % 2 == 0 else 0\n",
     "        approx_error = np.abs(I_approx - I_exact)\n",
     "        approx_errors.append(approx_error)\n",
-    "    print(\"{:5d}     |    \".format(N) + \" \".join(\"{:.3f}    \".format(e) for e in approx_errors))"
+    "    print(\n",
+    "        f\"{N:5d}     |    \"\n",
+    "        + \" \".join(f\"{e:.3f}    \" for e in approx_errors)\n",
+    "    )"
    ]
   },
   {

L3/Calculs Numériques/Interpolation_2.ipynb

@@ -22,8 +22,8 @@
     "%matplotlib inline\n",
     "%config InlineBackend.figure_format = 'retina'\n",
     "\n",
-    "import numpy as np                       # pour les numpy array\n",
-    "import matplotlib.pyplot as plt          # librairie graphique"
+    "import matplotlib.pyplot as plt  # librairie graphique\n",
+    "import numpy as np  # pour les numpy array"
    ]
   },
   {
@@ -72,11 +72,11 @@
     "    N = len(x)\n",
     "    M = len(xx)\n",
     "    L = np.ones((M, N))\n",
-    "    \n",
+    "\n",
     "    for i in range(N):\n",
     "        for j in range(N):\n",
     "            if i != j:\n",
-    "                L[:, i] *= (xx - x[j])/(x[i]-x[j])\n",
+    "                L[:, i] *= (xx - x[j]) / (x[i] - x[j])\n",
     "    return L.dot(y)"
    ]
   },
@@ -119,7 +119,7 @@
     "y = np.random.rand(N)\n",
     "xx = np.linspace(0, 1, 200)\n",
     "\n",
-    "plt.scatter(x,y)\n",
+    "plt.scatter(x, y)\n",
     "plt.plot(xx, interp_Lagrange(x, y, xx))"
    ]
   },
@@ -155,10 +155,16 @@
    "outputs": [],
    "source": [
     "def equirepartis(a, b, N):\n",
-    "    return np.array([a + (b-a) * (i-1)/(N-1) for i in range(1, N+1)])\n",
-    "    \n",
+    "    return np.array([a + (b - a) * (i - 1) / (N - 1) for i in range(1, N + 1)])\n",
+    "\n",
+    "\n",
     "def tchebychev(a, b, N):\n",
-    "    return np.array([(a+b)/2 + (b-a)/2 * np.cos((2*i-1)/(2*N)*np.pi) for i in range(1, N+1)])"
+    "    return np.array(\n",
+    "        [\n",
+    "            (a + b) / 2 + (b - a) / 2 * np.cos((2 * i - 1) / (2 * N) * np.pi)\n",
+    "            for i in range(1, N + 1)\n",
+    "        ]\n",
+    "    )"
    ]
   },
   {
@@ -188,7 +194,7 @@
     "    L = np.ones_like(xx)\n",
     "    for j in range(N):\n",
     "        if i != j:\n",
-    "            L *= (xx-x[j])/(x[i]-x[j]) \n",
+    "            L *= (xx - x[j]) / (x[i] - x[j])\n",
     "    return L"
    ]
   },
@@ -271,16 +277,16 @@
     "    ax[0].set_title(f\"Points équi-repartis (N={n})\")\n",
     "    xeq = equirepartis(a, b, n)\n",
     "    for i in range(n):\n",
-    "        ax[0].scatter(xeq[i], 0, color='black')\n",
-    "        ax[0].scatter(xeq[i], 1, color='black')\n",
+    "        ax[0].scatter(xeq[i], 0, color=\"black\")\n",
+    "        ax[0].scatter(xeq[i], 1, color=\"black\")\n",
     "        ax[0].plot(xx, Li(i, xeq, xx))\n",
     "    ax[0].grid()\n",
-    "    \n",
+    "\n",
     "    ax[1].set_title(f\"Points de Tchebychev (N={n})\")\n",
     "    xchev = tchebychev(a, b, n)\n",
     "    for i in range(n):\n",
-    "        ax[1].scatter(xchev[i], 0, color='black')\n",
-    "        ax[1].scatter(xchev[i], 1, color='black')\n",
+    "        ax[1].scatter(xchev[i], 0, color=\"black\")\n",
+    "        ax[1].scatter(xchev[i], 1, color=\"black\")\n",
     "        ax[1].plot(xx, Li(i, xchev, xx))\n",
     "    ax[1].grid()"
    ]
@@ -325,20 +331,21 @@
     }
    ],
    "source": [
-    "f = lambda x: 1/(1+x**2)\n",
+    "def f(x):\n",
+    "    return 1 / (1 + x**2)\n",
     "a, b = -5, 5\n",
     "xx = np.linspace(a, b, 200)\n",
     "\n",
-    "plt.plot(xx, f(xx), label='Courbe de f')\n",
+    "plt.plot(xx, f(xx), label=\"Courbe de f\")\n",
     "for n in [5, 10, 20]:\n",
     "    xeq = equirepartis(a, b, n)\n",
     "    for i in range(n):\n",
     "        plt.scatter(xeq[i], f(xeq[i]))\n",
     "        plt.plot(xx, Li(i, xeq, xx))\n",
-    "        \n",
+    "\n",
     "plt.ylim(-1, 1)\n",
     "plt.legend()\n",
-    "plt.title('Interpolation de f avec Lagrange pour N points répartis')\n",
+    "plt.title(\"Interpolation de f avec Lagrange pour N points répartis\")\n",
     "plt.grid()"
    ]
   },
@@ -366,20 +373,21 @@
     }
    ],
    "source": [
-    "f = lambda x: 1/(1+x**2)\n",
+    "def f(x):\n",
+    "    return 1 / (1 + x**2)\n",
     "a, b = -5, 5\n",
     "xx = np.linspace(a, b, 200)\n",
     "\n",
-    "plt.plot(xx, f(xx), label='Courbe de f')\n",
+    "plt.plot(xx, f(xx), label=\"Courbe de f\")\n",
     "\n",
     "for n in [5, 10, 20]:\n",
     "    xchev = tchebychev(a, b, n)\n",
     "    for i in range(n):\n",
     "        plt.scatter(xchev[i], f(xchev[i]))\n",
     "        plt.plot(xx, Li(i, xchev, xx))\n",
-    "           \n",
+    "\n",
     "plt.legend()\n",
-    "plt.title('Interpolation de f avec Lagrange pour N points de Tchebychev')\n",
+    "plt.title(\"Interpolation de f avec Lagrange pour N points de Tchebychev\")\n",
     "plt.grid()"
    ]
   },
@@ -437,9 +445,11 @@
    "source": [
     "N = np.arange(5, 101, 5)\n",
     "\n",
+    "\n",
     "def n_inf(f, p):\n",
     "    return np.max([f, p])\n",
     "\n",
+    "\n",
     "# Norme inf en fct de N\n",
     "for n in N:\n",
     "    xeq = equirepartis(a, b, n)\n",

L3/Calculs Numériques/Point_Fixe.ipynb

@@ -20,8 +20,8 @@
     "%matplotlib inline\n",
     "%config InlineBackend.figure_format = 'retina'\n",
     "\n",
-    "import numpy as np\n",
-    "import matplotlib.pyplot as plt"
+    "import matplotlib.pyplot as plt\n",
+    "import numpy as np"
    ]
   },
   {
@@ -63,11 +63,16 @@
    },
    "outputs": [],
    "source": [
-    "f1 = lambda x: np.exp(x) - 1 - x\n",
-    "f2 = lambda x: x - np.sin(x)\n",
-    "f3 = lambda x: x + np.sin(x)\n",
-    "f4 = lambda x: x + np.cos(x) - 1\n",
-    "f5 = lambda x: x - np.cos(x) + 1"
+    "def f1(x):\n",
+    "    return np.exp(x) - 1 - x\n",
+    "def f2(x):\n",
+    "    return x - np.sin(x)\n",
+    "def f3(x):\n",
+    "    return x + np.sin(x)\n",
+    "def f4(x):\n",
+    "    return x + np.cos(x) - 1\n",
+    "def f5(x):\n",
+    "    return x - np.cos(x) + 1"
    ]
   },
   {
@@ -98,16 +103,16 @@
     "\n",
     "x = np.linspace(-1, 1, 200)\n",
     "ax = fig.add_subplot(3, 3, 1)\n",
-    "ax.plot(x, f1(x), label='Courbe f')\n",
-    "ax.plot(x, x, label=f'$y=x$')\n",
+    "ax.plot(x, f1(x), label=\"Courbe f\")\n",
+    "ax.plot(x, x, label=\"$y=x$\")\n",
     "ax.scatter([i for i in x if f1(i) == i], [f1(i) for i in x if f1(i) == i])\n",
     "ax.legend()\n",
     "\n",
-    "x = np.linspace(-np.pi / 2, 5*np.pi / 2)\n",
+    "x = np.linspace(-np.pi / 2, 5 * np.pi / 2)\n",
     "for fk, f in enumerate([f2, f3, f4, f5]):\n",
-    "    ax = fig.add_subplot(3, 3, fk+2)\n",
-    "    ax.plot(x, f(x), label='Courbe f')\n",
-    "    ax.plot(x, x, label=f'$y=x$')\n",
+    "    ax = fig.add_subplot(3, 3, fk + 2)\n",
+    "    ax.plot(x, f(x), label=\"Courbe f\")\n",
+    "    ax.plot(x, x, label=\"$y=x$\")\n",
     "    ax.scatter([i for i in x if f(i) == i], [f(i) for i in x if f(i) == i])\n",
     "    ax.legend()"
    ]
@@ -129,13 +134,13 @@
    },
    "outputs": [],
    "source": [
-    "def point_fixe(f, x0, tol=1.e-6, itermax=5000):\n",
+    "def point_fixe(f, x0, tol=1.0e-6, itermax=5000):\n",
     "    \"\"\"\n",
     "    Recherche de point fixe : méthode brute x_{n+1} = f(x_n)\n",
-    "    \n",
+    "\n",
     "    Parameters\n",
     "    ----------\n",
-    "    \n",
+    "\n",
     "    f: function\n",
     "        la fonction dont on cherche le point fixe\n",
     "    x0: float\n",
@@ -144,10 +149,10 @@
     "        critère d'arrêt : |x_{n+1} - x_n| < tol\n",
     "    itermax: int\n",
     "        le nombre maximal d'itérations autorisées\n",
-    "        \n",
+    "\n",
     "    Returns\n",
     "    -------\n",
-    "    \n",
+    "\n",
     "    x: float\n",
     "        la valeur trouvée pour le point fixe\n",
     "    niter: int\n",
@@ -225,14 +230,14 @@
    "source": [
     "# F1\n",
     "\n",
-    "fig, ax = plt.subplots(figsize=(6,6))\n",
+    "fig, ax = plt.subplots(figsize=(6, 6))\n",
     "\n",
     "x, niter, xL = point_fixe(f1, -0.5)\n",
     "xx = np.linspace(-1, 1, 200)\n",
     "\n",
-    "ax.plot(xx, f1(xx), label='Courbe f1')\n",
-    "ax.plot(xx, xx, label=f'$y=x$')\n",
-    "ax.scatter(x, f1(x), label='Point Fixe')\n",
+    "ax.plot(xx, f1(xx), label=\"Courbe f1\")\n",
+    "ax.plot(xx, xx, label=\"$y=x$\")\n",
+    "ax.scatter(x, f1(x), label=\"Point Fixe\")\n",
     "ax.legend()\n",
     "ax.set_title(f\"Nombre d'itérations : {niter}\")"
    ]

L3/Equations Différentielles/TP1_EDO_EulerExp.ipynb

@@ -100,41 +100,48 @@
    ],
    "source": [
     "%matplotlib inline\n",
-    "import numpy as np\n",
     "import matplotlib.pyplot as plt\n",
+    "import numpy as np\n",
+    "\n",
     "\n",
     "# Fonction f définissant l'EDO\n",
-    "def f1(t,y):\n",
-    "    return -t*y\n",
+    "def f1(t, y):\n",
+    "    return -t * y\n",
+    "\n",
+    "\n",
+    "# Solution exacte\n",
+    "def uex1(t, y0):\n",
+    "    return y0 * np.exp(-(t**2) / 2)\n",
     "\n",
-    "# Solution exacte \n",
-    "def uex1(t,y0):\n",
-    "    return y0 * np.exp(-t**2 /2)\n",
     "\n",
     "plt.figure(1)\n",
     "\n",
     "## Solutions de l'EDO 1 telles que y(0)=1 et y(0)=2\n",
     "\n",
-    "tt=np.linspace(-3, 3, 100) # vecteur représentant l'intervalle de temps\n",
-    "y1=uex1(tt, 1) # sol. exacte avec y_0=1\n",
-    "y2=uex1(tt, 2)  # sol. exacte avec y_0=2\n",
-    "plt.plot(tt,y1,label='y(0)=1')\n",
-    "plt.plot(tt,y2,label='y(0)=2')\n",
+    "tt = np.linspace(-3, 3, 100)  # vecteur représentant l'intervalle de temps\n",
+    "y1 = uex1(tt, 1)  # sol. exacte avec y_0=1\n",
+    "y2 = uex1(tt, 2)  # sol. exacte avec y_0=2\n",
+    "plt.plot(tt, y1, label=\"y(0)=1\")\n",
+    "plt.plot(tt, y2, label=\"y(0)=2\")\n",
     "\n",
     "##Tracé du champ de vecteurs\n",
     "\n",
-    "plt.title('Solution exacte pour y0 et y1')\n",
+    "plt.title(\"Solution exacte pour y0 et y1\")\n",
     "plt.legend()\n",
-    "plt.xlabel('t')\n",
-    "plt.ylabel('y')\n",
+    "plt.xlabel(\"t\")\n",
+    "plt.ylabel(\"y\")\n",
     "\n",
-    "t=np.linspace(-5,5,35) # abcisse des points de la grille  \n",
-    "y=np.linspace(0,2.1,23) # ordonnées des points de la grille  \n",
-    "T,Y=np.meshgrid(t,y) # grille de points dans le plan (t,y)  \n",
-    "U=np.ones(T.shape)/np.sqrt(1+f1(T,Y)**2) # matrice avec les composantes horizontales des vecteurs (1), normalisées  \n",
-    "V=f1(T,Y)/np.sqrt(1+f1(T,Y)**2) # matrice avec les composantes verticales des vecteurs (f(t,y)), normalisées  \n",
-    "plt.quiver(T,Y,U,V,angles='xy',scale=20,color='cyan')\n",
-    "plt.axis([-5,5,0,2.1])"
+    "t = np.linspace(-5, 5, 35)  # abcisse des points de la grille\n",
+    "y = np.linspace(0, 2.1, 23)  # ordonnées des points de la grille\n",
+    "T, Y = np.meshgrid(t, y)  # grille de points dans le plan (t,y)\n",
+    "U = np.ones(T.shape) / np.sqrt(\n",
+    "    1 + f1(T, Y) ** 2\n",
+    ")  # matrice avec les composantes horizontales des vecteurs (1), normalisées\n",
+    "V = f1(T, Y) / np.sqrt(\n",
+    "    1 + f1(T, Y) ** 2\n",
+    ")  # matrice avec les composantes verticales des vecteurs (f(t,y)), normalisées\n",
+    "plt.quiver(T, Y, U, V, angles=\"xy\", scale=20, color=\"cyan\")\n",
+    "plt.axis([-5, 5, 0, 2.1])"
    ]
   },
   {
@@ -182,43 +189,50 @@
    ],
    "source": [
     "%matplotlib inline\n",
-    "import numpy as np\n",
     "import matplotlib.pyplot as plt\n",
+    "import numpy as np\n",
+    "\n",
     "\n",
     "# Fonction f définissant l'EDO\n",
-    "def f2(t,y):\n",
+    "def f2(t, y):\n",
     "    return t * y**2\n",
     "\n",
-    "# Solution exacte \n",
-    "def uex2(t,y0):\n",
+    "\n",
+    "# Solution exacte\n",
+    "def uex2(t, y0):\n",
     "    return y0 / (1 - y0 * t**2 / 2)\n",
     "\n",
+    "\n",
     "plt.figure(1)\n",
     "\n",
     "## Solutions de l'EDO 1 telles que y(0)=1 et y(0)=2\n",
     "\n",
-    "tt=np.linspace(-3, 3, 100) # vecteur représentant l'intervalle de temps\n",
-    "y1=uex2(tt, 1) # sol. exacte avec y_0=1\n",
-    "y2=uex2(tt, 2)  # sol. exacte avec y_0=2\n",
-    "plt.plot(tt,y1,label='y(0)=1')\n",
-    "plt.plot(tt,y2,label='y(0)=2')\n",
+    "tt = np.linspace(-3, 3, 100)  # vecteur représentant l'intervalle de temps\n",
+    "y1 = uex2(tt, 1)  # sol. exacte avec y_0=1\n",
+    "y2 = uex2(tt, 2)  # sol. exacte avec y_0=2\n",
+    "plt.plot(tt, y1, label=\"y(0)=1\")\n",
+    "plt.plot(tt, y2, label=\"y(0)=2\")\n",
     "\n",
     "##Tracé du champ de vecteurs\n",
     "\n",
-    "plt.title('Solution exacte pour y0 et y1')\n",
+    "plt.title(\"Solution exacte pour y0 et y1\")\n",
     "plt.legend()\n",
-    "plt.xlabel('t')\n",
-    "plt.ylabel('y')\n",
+    "plt.xlabel(\"t\")\n",
+    "plt.ylabel(\"y\")\n",
     "\n",
     "xmin, xmax = -2, 2\n",
     "ymin, ymax = -4, 4\n",
     "\n",
-    "t=np.linspace(xmin, xmax,35) # abcisse des points de la grille  \n",
-    "y=np.linspace(ymin, ymax) # ordonnées des points de la grille  \n",
-    "T,Y=np.meshgrid(t,y) # grille de points dans le plan (t,y)  \n",
-    "U=np.ones(T.shape)/np.sqrt(1+f2(T,Y)**2) # matrice avec les composantes horizontales des vecteurs (1), normalisées  \n",
-    "V=f1(T,Y)/np.sqrt(1+f2(T,Y)**2) # matrice avec les composantes verticales des vecteurs (f(t,y)), normalisées  \n",
-    "plt.quiver(T,Y,U,V,angles='xy',scale=20,color='cyan')\n",
+    "t = np.linspace(xmin, xmax, 35)  # abcisse des points de la grille\n",
+    "y = np.linspace(ymin, ymax)  # ordonnées des points de la grille\n",
+    "T, Y = np.meshgrid(t, y)  # grille de points dans le plan (t,y)\n",
+    "U = np.ones(T.shape) / np.sqrt(\n",
+    "    1 + f2(T, Y) ** 2\n",
+    ")  # matrice avec les composantes horizontales des vecteurs (1), normalisées\n",
+    "V = f1(T, Y) / np.sqrt(\n",
+    "    1 + f2(T, Y) ** 2\n",
+    ")  # matrice avec les composantes verticales des vecteurs (f(t,y)), normalisées\n",
+    "plt.quiver(T, Y, U, V, angles=\"xy\", scale=20, color=\"cyan\")\n",
     "plt.axis([xmin, xmax, ymin, ymax])"
    ]
   },
@@ -339,33 +353,34 @@
    ],
    "source": [
     "# Euler explicite\n",
-    "def euler_exp(t0,T,y0,h,f):\n",
-    "    t = np.arange(t0, t0+T+h, h)\n",
+    "def euler_exp(t0, T, y0, h, f):\n",
+    "    t = np.arange(t0, t0 + T + h, h)\n",
     "    y = np.empty(t.size)\n",
     "    y[0] = y0\n",
-    "    N = len(t)-1\n",
+    "    N = len(t) - 1\n",
     "    for n in range(N):\n",
-    "        y[n+1] = y[n] + h * f(t[n], y[n])\n",
+    "        y[n + 1] = y[n] + h * f(t[n], y[n])\n",
     "    return t, y\n",
     "\n",
-    "t0=0\n",
-    "T=1\n",
-    "y0=1\n",
     "\n",
-    "for f, uex in zip([f1, f2], [uex1, uex2]):\n",
+    "t0 = 0\n",
+    "T = 1\n",
+    "y0 = 1\n",
+    "\n",
+    "for f, uex in zip([f1, f2], [uex1, uex2], strict=False):\n",
     "    plt.figure()\n",
     "    t = np.arange(0, 1, 1e-3)\n",
     "    y = uex(t, y0)\n",
-    "    plt.plot(t, y, label='Solution exacte')\n",
+    "    plt.plot(t, y, label=\"Solution exacte\")\n",
     "\n",
-    "    for h in [1/5, 1/10, 1/50]:\n",
+    "    for h in [1 / 5, 1 / 10, 1 / 50]:\n",
     "        tt, y = euler_exp(t0, T, y0, h, f)\n",
-    "        plt.plot(tt, y, label=f'Solution approchée pour h={h}')\n",
-    "    \n",
+    "        plt.plot(tt, y, label=f\"Solution approchée pour h={h}\")\n",
+    "\n",
     "    plt.title(f\"Solutions exacte et approchées de la fonction {f.__name__}\")\n",
     "    plt.legend()\n",
-    "    plt.xlabel('t')\n",
-    "    plt.ylabel('y')"
+    "    plt.xlabel(\"t\")\n",
+    "    plt.ylabel(\"y\")"
    ]
   },
   {
@@ -441,12 +456,14 @@
    ],
    "source": [
     "# Modèle de Verhulst\n",
-    "n=1\n",
-    "d=0.75\n",
-    "K=200\n",
+    "n = 1\n",
+    "d = 0.75\n",
+    "K = 200\n",
+    "\n",
+    "\n",
+    "def fV(t, P):\n",
+    "    return (n - d) * P * (1 - P / K)\n",
     "\n",
-    "def fV(t,P):\n",
-    "    return (n-d)*P*(1-P/K)\n",
     "\n",
     "plt.figure()\n",
     "\n",
@@ -455,20 +472,24 @@
     "t0, T = 0, 50\n",
     "\n",
     "\n",
-    "for P in range(1, K+100, 15):\n",
+    "for P in range(1, K + 100, 15):\n",
     "    tt, yy = euler_exp(t0, T, P, h, fV)\n",
-    "    plt.plot(tt, yy, label=f'Solution approchée pour h={h}')\n",
-    "    \n",
-    "plt.title(f\"Solution approchée du modèle de Verhulst pour la population d'individus\")\n",
-    "plt.xlabel('t')\n",
-    "plt.ylabel('y')\n",
+    "    plt.plot(tt, yy, label=f\"Solution approchée pour h={h}\")\n",
     "\n",
-    "t=np.linspace(t0, T, 35) # abcisse des points de la grille  \n",
-    "y=np.linspace(0, K+100, 23) # ordonnées des points de la grille  \n",
-    "T,P=np.meshgrid(t,y) # grille de points dans le plan (t,y)  \n",
-    "U=np.ones(T.shape)/np.sqrt(1+fV(T,P)**2) # matrice avec les composantes horizontales des vecteurs (1), normalisées  \n",
-    "V=fV(T,P)/np.sqrt(1+fV(T,P)**2) # matrice avec les composantes verticales des vecteurs (f(t,y)), normalisées  \n",
-    "plt.quiver(T,P,U,V,angles='xy',scale=20,color='cyan')\n",
+    "plt.title(\"Solution approchée du modèle de Verhulst pour la population d'individus\")\n",
+    "plt.xlabel(\"t\")\n",
+    "plt.ylabel(\"y\")\n",
+    "\n",
+    "t = np.linspace(t0, T, 35)  # abcisse des points de la grille\n",
+    "y = np.linspace(0, K + 100, 23)  # ordonnées des points de la grille\n",
+    "T, P = np.meshgrid(t, y)  # grille de points dans le plan (t,y)\n",
+    "U = np.ones(T.shape) / np.sqrt(\n",
+    "    1 + fV(T, P) ** 2\n",
+    ")  # matrice avec les composantes horizontales des vecteurs (1), normalisées\n",
+    "V = fV(T, P) / np.sqrt(\n",
+    "    1 + fV(T, P) ** 2\n",
+    ")  # matrice avec les composantes verticales des vecteurs (f(t,y)), normalisées\n",
+    "plt.quiver(T, P, U, V, angles=\"xy\", scale=20, color=\"cyan\")\n",
     "plt.legend(fontsize=4)"
    ]
   },
@@ -527,29 +548,34 @@
     }
    ],
    "source": [
-    "def fS(t,P):\n",
-    "    return (2-np.cos(t))*P-(P**2)/2-1\n",
+    "def fS(t, P):\n",
+    "    return (2 - np.cos(t)) * P - (P**2) / 2 - 1\n",
     "\n",
-    "P0=5\n",
-    "t0=0\n",
-    "T=10\n",
-    "h=0.1\n",
+    "\n",
+    "P0 = 5\n",
+    "t0 = 0\n",
+    "T = 10\n",
+    "h = 0.1\n",
     "\n",
     "plt.figure()\n",
     "tt, yy = euler_exp(t0, T, P0, h, fS)\n",
-    "plt.plot(tt, yy, label=f'Solution approchée pour h={h}')\n",
-    "    \n",
-    "plt.title(f\"Solutions approchée du modèle de Verhulst pour une population de saumons\")\n",
-    "plt.legend()\n",
-    "plt.xlabel('t')\n",
-    "plt.ylabel('y')\n",
+    "plt.plot(tt, yy, label=f\"Solution approchée pour h={h}\")\n",
     "\n",
-    "t=np.linspace(t0, T, 35) # abcisse des points de la grille  \n",
-    "y=np.linspace(0, 6, 23) # ordonnées des points de la grille  \n",
-    "T,P=np.meshgrid(t,y) # grille de points dans le plan (t,y)  \n",
-    "U=np.ones(T.shape)/np.sqrt(1+fS(T,P)**2) # matrice avec les composantes horizontales des vecteurs (1), normalisées  \n",
-    "V=fS(T,P)/np.sqrt(1+fS(T,P)**2) # matrice avec les composantes verticales des vecteurs (f(t,y)), normalisées  \n",
-    "plt.quiver(T,P,U,V,angles='xy',scale=20,color='cyan')\n"
+    "plt.title(\"Solutions approchée du modèle de Verhulst pour une population de saumons\")\n",
+    "plt.legend()\n",
+    "plt.xlabel(\"t\")\n",
+    "plt.ylabel(\"y\")\n",
+    "\n",
+    "t = np.linspace(t0, T, 35)  # abcisse des points de la grille\n",
+    "y = np.linspace(0, 6, 23)  # ordonnées des points de la grille\n",
+    "T, P = np.meshgrid(t, y)  # grille de points dans le plan (t,y)\n",
+    "U = np.ones(T.shape) / np.sqrt(\n",
+    "    1 + fS(T, P) ** 2\n",
+    ")  # matrice avec les composantes horizontales des vecteurs (1), normalisées\n",
+    "V = fS(T, P) / np.sqrt(\n",
+    "    1 + fS(T, P) ** 2\n",
+    ")  # matrice avec les composantes verticales des vecteurs (f(t,y)), normalisées\n",
+    "plt.quiver(T, P, U, V, angles=\"xy\", scale=20, color=\"cyan\")"
    ]
   },
   {

L3/Equations Différentielles/TP2_Lokta_Volterra.ipynb

@@ -92,56 +92,66 @@
    ],
    "source": [
     "%matplotlib inline\n",
-    "import numpy as np\n",
     "import matplotlib.pyplot as plt\n",
+    "import numpy as np\n",
+    "\n",
     "\n",
     "# Fonction F définissant l'EDO\n",
     "def F(Y):\n",
-    "    x=Y[0]\n",
-    "    y=Y[1]\n",
-    "    A=np.array([[0,1],[-2,-3]])\n",
-    "    return np.dot(A,Y)\n",
+    "    Y[0]\n",
+    "    Y[1]\n",
+    "    A = np.array([[0, 1], [-2, -3]])\n",
+    "    return np.dot(A, Y)\n",
     "\n",
-    "# ou \n",
-    "def F1(x,y):\n",
+    "\n",
+    "# ou\n",
+    "def F1(x, y):\n",
     "    return y\n",
     "\n",
-    "def F2(x,y):\n",
-    "    return -2*x-3*y\n",
+    "\n",
+    "def F2(x, y):\n",
+    "    return -2 * x - 3 * y\n",
+    "\n",
     "\n",
     "# Solution exacte de Y'=AY, Y(t_0)=Y_0\n",
-    "def uex(t,t0,Y0):\n",
-    "    U1=np.array([1,-1])\n",
-    "    U2=np.array([1,-2])\n",
-    "    P=np.ones((2,2))\n",
-    "    P[:,0]=U1\n",
-    "    P[:,1]=U2\n",
-    "    C=np.linalg.solve(P,Y0)\n",
-    "    return np.array([(C[0]*np.exp(-(t-t0))*U1[0]+C[1]*np.exp(-2*(t-t0))*U2[0]),(C[0]*np.exp(-(t-t0))*U1[1]+C[1]*np.exp(-2*(t-t0))*U2[1])])\n",
+    "def uex(t, t0, Y0):\n",
+    "    U1 = np.array([1, -1])\n",
+    "    U2 = np.array([1, -2])\n",
+    "    P = np.ones((2, 2))\n",
+    "    P[:, 0] = U1\n",
+    "    P[:, 1] = U2\n",
+    "    C = np.linalg.solve(P, Y0)\n",
+    "    return np.array(\n",
+    "        [\n",
+    "            (C[0] * np.exp(-(t - t0)) * U1[0] + C[1] * np.exp(-2 * (t - t0)) * U2[0]),\n",
+    "            (C[0] * np.exp(-(t - t0)) * U1[1] + C[1] * np.exp(-2 * (t - t0)) * U2[1]),\n",
+    "        ]\n",
+    "    )\n",
     "\n",
-    "## Représentation des solutions pour chaque valeur de la donnée initiale \n",
+    "\n",
+    "## Représentation des solutions pour chaque valeur de la donnée initiale\n",
     "tt = np.linspace(-10, 10, 100)\n",
     "t0 = tt[0]\n",
-    "for x, y in zip([1, -2, 0, 1, 3], [2, -2, -4, -2, 4]):\n",
+    "for x, y in zip([1, -2, 0, 1, 3], [2, -2, -4, -2, 4], strict=False):\n",
     "    sol = uex(tt, t0, [x, y])\n",
-    "    plt.plot(sol[0], sol[1], label=f'$((x0, y0) = ({x}, {y})$')\n",
+    "    plt.plot(sol[0], sol[1], label=f\"$((x0, y0) = ({x}, {y})$\")\n",
     "    plt.scatter(x, y)\n",
     "\n",
-    "#Tracé du champ de vecteurs\n",
-    "x=np.linspace(-5,5,26)\n",
-    "y=x\n",
-    "xx,yy=np.meshgrid(x,y)\n",
-    "U=F1(xx,yy)/np.sqrt(F1(xx,yy)**2+F2(xx,yy)**2)\n",
-    "V=F2(xx,yy)/np.sqrt(F1(xx,yy)**2+F2(xx,yy)**2)\n",
-    "plt.quiver(xx,yy,U,V,angles='xy', scale=20, color='gray')\n",
-    "plt.axis([-5.,5,-5,5])\n",
+    "# Tracé du champ de vecteurs\n",
+    "x = np.linspace(-5, 5, 26)\n",
+    "y = x\n",
+    "xx, yy = np.meshgrid(x, y)\n",
+    "U = F1(xx, yy) / np.sqrt(F1(xx, yy) ** 2 + F2(xx, yy) ** 2)\n",
+    "V = F2(xx, yy) / np.sqrt(F1(xx, yy) ** 2 + F2(xx, yy) ** 2)\n",
+    "plt.quiver(xx, yy, U, V, angles=\"xy\", scale=20, color=\"gray\")\n",
+    "plt.axis([-5.0, 5, -5, 5])\n",
     "\n",
-    "## Représentation des espaces propres \n",
-    "plt.plot(tt, -tt, label=f'SEP associé à -1', linewidth=3)\n",
-    "plt.plot(tt, -2*tt, label=f'SEP associé à -2', linewidth=3)\n",
+    "## Représentation des espaces propres\n",
+    "plt.plot(tt, -tt, label=\"SEP associé à -1\", linewidth=3)\n",
+    "plt.plot(tt, -2 * tt, label=\"SEP associé à -2\", linewidth=3)\n",
     "\n",
     "plt.legend(fontsize=7)\n",
-    "plt.title('Représentation des solutions et champs de vecteurs pour le système (S)')"
+    "plt.title(\"Représentation des solutions et champs de vecteurs pour le système (S)\")"
    ]
   },
   {
@@ -210,13 +220,15 @@
    "source": [
     "a, b, c, d = 0.1, 5e-5, 0.04, 5e-5\n",
     "H0, P0 = 2000, 1000\n",
-    "He, Pe = c/d, a/b\n",
+    "He, Pe = c / d, a / b\n",
+    "\n",
     "\n",
     "def F1(H, P):\n",
-    "    return H * (a - b*P)\n",
+    "    return H * (a - b * P)\n",
+    "\n",
     "\n",
     "def F2(H, P):\n",
-    "    return P * (-c + d*H)"
+    "    return P * (-c + d * H)"
    ]
   },
   {
@@ -256,17 +268,17 @@
     }
    ],
    "source": [
-    "xx, yy = np.linspace(0, 3000, 20), np.linspace (0, 4500, 30)\n",
-    "h,p = np.meshgrid(xx, yy)\n",
-    "n=np.sqrt(F1(h,p)**2+F2(h,p)**2)\n",
-    "plt.quiver(h, p, F1(h,p)/n, F2(h,p)/n, angles='xy', scale=20, color='gray')\n",
+    "xx, yy = np.linspace(0, 3000, 20), np.linspace(0, 4500, 30)\n",
+    "h, p = np.meshgrid(xx, yy)\n",
+    "n = np.sqrt(F1(h, p) ** 2 + F2(h, p) ** 2)\n",
+    "plt.quiver(h, p, F1(h, p) / n, F2(h, p) / n, angles=\"xy\", scale=20, color=\"gray\")\n",
     "\n",
-    "plt.vlines(He, 0, 4500, label=f'H=He={He}')\n",
-    "plt.hlines(Pe, 0, 3000, label=f'P=Pe={Pe}')\n",
-    "plt.scatter(He, Pe, label=f'(H0, P0) = (He, Pe)')\n",
-    "plt.scatter(H0, P0, label=f'(H, P)=(H0, P0)=({H0},{P0})', color='red')\n",
+    "plt.vlines(He, 0, 4500, label=f\"H=He={He}\")\n",
+    "plt.hlines(Pe, 0, 3000, label=f\"P=Pe={Pe}\")\n",
+    "plt.scatter(He, Pe, label=\"(H0, P0) = (He, Pe)\")\n",
+    "plt.scatter(H0, P0, label=f\"(H, P)=(H0, P0)=({H0},{P0})\", color=\"red\")\n",
     "\n",
-    "plt.title('Le modèle de Lotka-Volterra')\n",
+    "plt.title(\"Le modèle de Lotka-Volterra\")\n",
     "plt.legend(fontsize=7)"
    ]
   },
@@ -374,19 +386,20 @@
    "outputs": [],
    "source": [
     "a, b, c, d = 0.1, 5e-5, 0.04, 5e-5\n",
-    "T=200\n",
+    "T = 200\n",
     "H0, P0 = 2000, 1000\n",
-    "He, Pe = c/d, a/b\n",
-    "p=0.02\n",
+    "He, Pe = c / d, a / b\n",
+    "p = 0.02\n",
+    "\n",
     "\n",
     "def voltEE(T, X0, h):\n",
-    "    t = np.arange(0, T+h, h)\n",
+    "    t = np.arange(0, T + h, h)\n",
     "    H = 0 * t\n",
     "    P = 0 * t\n",
     "    H[0], P[0] = X0\n",
-    "    for n in range(len(t)-1):\n",
-    "        H[n+1] = H[n] + h * F1(H[n], P[n])\n",
-    "        P[n+1] = P[n] + h * F2(H[n], P[n])\n",
+    "    for n in range(len(t) - 1):\n",
+    "        H[n + 1] = H[n] + h * F1(H[n], P[n])\n",
+    "        P[n + 1] = P[n] + h * F2(H[n], P[n])\n",
     "    return np.array([t, H, P])"
    ]
   },
@@ -438,22 +451,22 @@
    ],
    "source": [
     "t, H, P = voltEE(T, [H0, P0], 0.001)\n",
-    "plt.plot(t, H, label='Population de sardines')\n",
-    "plt.plot(t, P, label='Population de requins')\n",
+    "plt.plot(t, H, label=\"Population de sardines\")\n",
+    "plt.plot(t, P, label=\"Population de requins\")\n",
     "plt.legend(fontsize=7)\n",
     "\n",
     "plt.figure()\n",
-    "xx, yy = np.linspace(0, 3000, 20), np.linspace (0, 4500, 30)\n",
-    "h,p = np.meshgrid(xx, yy)\n",
-    "n=np.sqrt(F1(h,p)**2 + F2(h,p)**2)\n",
-    "plt.quiver (h, p, F1(h,p)/n, F2(h,p)/n, angles='xy', scale=20, color='gray')\n",
+    "xx, yy = np.linspace(0, 3000, 20), np.linspace(0, 4500, 30)\n",
+    "h, p = np.meshgrid(xx, yy)\n",
+    "n = np.sqrt(F1(h, p) ** 2 + F2(h, p) ** 2)\n",
+    "plt.quiver(h, p, F1(h, p) / n, F2(h, p) / n, angles=\"xy\", scale=20, color=\"gray\")\n",
     "\n",
-    "plt.vlines(He, 0, 4500, label=f'H=He={He}')\n",
-    "plt.hlines(Pe, 0, 3000, label=f'P=Pe={Pe}')\n",
-    "plt.scatter(He, Pe, label=f'(H0, P0) = (He, Pe)')\n",
-    "plt.scatter(H0, P0, label=f'(H, P)=(H0, P0)=({H0},{P0})', color='red')\n",
+    "plt.vlines(He, 0, 4500, label=f\"H=He={He}\")\n",
+    "plt.hlines(Pe, 0, 3000, label=f\"P=Pe={Pe}\")\n",
+    "plt.scatter(He, Pe, label=\"(H0, P0) = (He, Pe)\")\n",
+    "plt.scatter(H0, P0, label=f\"(H, P)=(H0, P0)=({H0},{P0})\", color=\"red\")\n",
     "\n",
-    "plt.title('Le modèle de Lotka-Volterra')\n",
+    "plt.title(\"Le modèle de Lotka-Volterra\")\n",
     "plt.legend(fontsize=7)\n",
     "plt.plot(H, P)"
    ]
@@ -467,25 +480,28 @@
    "outputs": [],
    "source": [
     "a, b, c, d = 0.1, 5e-5, 0.04, 5e-5\n",
-    "T=200\n",
+    "T = 200\n",
     "H0, P0 = 2000, 1000\n",
-    "He, Pe = c/d, a/b\n",
-    "p=0.02\n",
+    "He, Pe = c / d, a / b\n",
+    "p = 0.02\n",
+    "\n",
     "\n",
     "def F1_p(H, P):\n",
     "    return (a - p) * H - b * H * P\n",
     "\n",
+    "\n",
     "def F2_p(H, P):\n",
-    "    return (-c-p) * P + d * H * P\n",
+    "    return (-c - p) * P + d * H * P\n",
+    "\n",
     "\n",
     "def voltEE_p(T, X0, h):\n",
-    "    t = np.arange(0, T+h, h)\n",
+    "    t = np.arange(0, T + h, h)\n",
     "    H = 0 * t\n",
     "    P = 0 * t\n",
     "    H[0], P[0] = X0\n",
-    "    for n in range(len(t)-1):\n",
-    "        H[n+1] = H[n] + h * F1_p(H[n], P[n])\n",
-    "        P[n+1] = P[n] + h * F2_p(H[n], P[n])\n",
+    "    for n in range(len(t) - 1):\n",
+    "        H[n + 1] = H[n] + h * F1_p(H[n], P[n])\n",
+    "        P[n + 1] = P[n] + h * F2_p(H[n], P[n])\n",
     "    return np.array([t, H, P])"
    ]
   },
@@ -535,22 +551,22 @@
    ],
    "source": [
     "t, H, P = voltEE_p(T, [H0, P0], 0.001)\n",
-    "plt.plot(t, H, label='Population de sardines')\n",
-    "plt.plot(t, P, label='Population de requins')\n",
+    "plt.plot(t, H, label=\"Population de sardines\")\n",
+    "plt.plot(t, P, label=\"Population de requins\")\n",
     "plt.legend(fontsize=7)\n",
     "\n",
     "plt.figure()\n",
-    "xx, yy = np.linspace(0, 3000, 20), np.linspace (0, 4500, 30)\n",
-    "h,p = np.meshgrid(xx, yy)\n",
-    "n=np.sqrt(F1(h,p)**2 + F2(h,p)**2)\n",
-    "plt.quiver (h, p, F1(h,p)/n, F2(h,p)/n, angles='xy', scale=20, color='gray')\n",
+    "xx, yy = np.linspace(0, 3000, 20), np.linspace(0, 4500, 30)\n",
+    "h, p = np.meshgrid(xx, yy)\n",
+    "n = np.sqrt(F1(h, p) ** 2 + F2(h, p) ** 2)\n",
+    "plt.quiver(h, p, F1(h, p) / n, F2(h, p) / n, angles=\"xy\", scale=20, color=\"gray\")\n",
     "\n",
-    "plt.vlines(He, 0, 4500, label=f'H=He={He}')\n",
-    "plt.hlines(Pe, 0, 3000, label=f'P=Pe={Pe}')\n",
-    "plt.scatter(He, Pe, label=f'(H0, P0) = (He, Pe)')\n",
-    "plt.scatter(H0, P0, label=f'(H, P)=(H0, P0)=({H0},{P0})', color='red')\n",
+    "plt.vlines(He, 0, 4500, label=f\"H=He={He}\")\n",
+    "plt.hlines(Pe, 0, 3000, label=f\"P=Pe={Pe}\")\n",
+    "plt.scatter(He, Pe, label=\"(H0, P0) = (He, Pe)\")\n",
+    "plt.scatter(H0, P0, label=f\"(H, P)=(H0, P0)=({H0},{P0})\", color=\"red\")\n",
     "\n",
-    "plt.title('Le modèle de Lotka-Volterra')\n",
+    "plt.title(\"Le modèle de Lotka-Volterra\")\n",
     "plt.legend(fontsize=7)\n",
     "plt.plot(H, P)"
    ]
@@ -697,46 +713,49 @@
     }
    ],
    "source": [
-    "gamma=0.5\n",
-    "a=0.004\n",
-    "lm=10\n",
+    "gamma = 0.5\n",
+    "a = 0.004\n",
+    "lm = 10\n",
+    "\n",
     "\n",
     "def fphi(d):\n",
-    "    return (gamma/d)*np.log(d/a)\n",
+    "    return (gamma / d) * np.log(d / a)\n",
+    "\n",
     "\n",
     "def F(X):\n",
-    "    (n,m)=np.shape(X)\n",
-    "    Y=np.zeros((n,m))\n",
-    "    Y[0,:]=X[1,:]\n",
-    "    Xaux=np.zeros(m+2)\n",
-    "    Xaux[-1]=1\n",
-    "    Xaux[1:-1]=X[0,:]\n",
-    "    Y[1,:]=fphi(Xaux[2:]-Xaux[1:-1])-fphi(Xaux[1:-1]-Xaux[0:-2])-lm*X[1,:]\n",
+    "    (n, m) = np.shape(X)\n",
+    "    Y = np.zeros((n, m))\n",
+    "    Y[0, :] = X[1, :]\n",
+    "    Xaux = np.zeros(m + 2)\n",
+    "    Xaux[-1] = 1\n",
+    "    Xaux[1:-1] = X[0, :]\n",
+    "    Y[1, :] = fphi(Xaux[2:] - Xaux[1:-1]) - fphi(Xaux[1:-1] - Xaux[0:-2]) - lm * X[1, :]\n",
     "    return Y\n",
     "\n",
-    "h=0.0002\n",
-    "T=15\n",
-    "N=100\n",
     "\n",
-    "t=np.arange(0,T+h,h)\n",
-    "Nt=np.size(t)\n",
-    "X=np.zeros((2,N,Nt))\n",
-    "R0=-1+2*np.random.rand(N)\n",
-    "X0=np.arange(1/(N+1),1,1/(N+1))+0.1*R0*(1/(N+1))\n",
+    "h = 0.0002\n",
+    "T = 15\n",
+    "N = 100\n",
     "\n",
-    "X[0,:,0]=X0\n",
-    "X[1,:,0]=X0\n",
+    "t = np.arange(0, T + h, h)\n",
+    "Nt = np.size(t)\n",
+    "X = np.zeros((2, N, Nt))\n",
+    "R0 = -1 + 2 * np.random.rand(N)\n",
+    "X0 = np.arange(1 / (N + 1), 1, 1 / (N + 1)) + 0.1 * R0 * (1 / (N + 1))\n",
+    "\n",
+    "X[0, :, 0] = X0\n",
+    "X[1, :, 0] = X0\n",
+    "\n",
+    "plt.figure(1, figsize=(24, 18))\n",
+    "for n in range(Nt - 1):\n",
+    "    Y = F(X[:, :, n])\n",
+    "    X[:, :, n + 1] = X[:, :, n] + (h / 2) * Y + (h / 2) * F(X[:, :, n] + h * Y)\n",
     "\n",
-    "plt.figure(1,figsize=(24,18))\n",
-    "for n in range(Nt-1):\n",
-    "    Y=F(X[:,:,n])\n",
-    "    X[:,:,n+1]=X[:,:,n]+(h/2)*Y+(h/2)*F(X[:,:,n]+h*Y)\n",
-    "    \n",
     "for i in range(N):\n",
-    "    plt.plot(t,X[0,i,:],'k')\n",
-    "plt.xlabel('t')\n",
-    "plt.ylabel('$x_i$')\n",
-    "plt.title('position x_i des globules rouges au cours du temps')\n"
+    "    plt.plot(t, X[0, i, :], \"k\")\n",
+    "plt.xlabel(\"t\")\n",
+    "plt.ylabel(\"$x_i$\")\n",
+    "plt.title(\"position x_i des globules rouges au cours du temps\")"
    ]
   },
   {

L3/Equations Différentielles/TP3_Convergence.ipynb

@@ -73,17 +73,18 @@
    "outputs": [],
    "source": [
     "%matplotlib inline\n",
-    "import numpy as np\n",
     "import matplotlib.pyplot as plt\n",
+    "import numpy as np\n",
+    "\n",
     "\n",
     "## Question 1\n",
     "def mon_schema(t0, T, y0, h, f):\n",
     "    t = np.arange(t0, t0 + T + h, h)\n",
     "    y = 0 * t\n",
     "    y[0] = y0\n",
-    "    for n in range(len(t)-1):\n",
-    "        yn1 = y[n] + h * f(t[n] + h / 2, y[n] + h/2 * f(t[n], y[n]))\n",
-    "        y[n+1] = y[n] + h / 2 * (f(t[n], y[n]) + f(t[n+1], yn1))\n",
+    "    for n in range(len(t) - 1):\n",
+    "        yn1 = y[n] + h * f(t[n] + h / 2, y[n] + h / 2 * f(t[n], y[n]))\n",
+    "        y[n + 1] = y[n] + h / 2 * (f(t[n], y[n]) + f(t[n + 1], yn1))\n",
     "    return t, y"
    ]
   },
@@ -140,25 +141,27 @@
     "## Question 2\n",
     "\n",
     "# f second membre de l'EDO\n",
-    "def f(t,y):\n",
+    "def f(t, y):\n",
     "    return y + np.sin(t) * np.power(y, 2)\n",
     "\n",
+    "\n",
     "# sol. exacte de (P)\n",
     "def yex(t):\n",
-    "    return 1 / (1/2 * np.exp(-t) + (np.cos(t)-np.sin(t)) / 2)\n",
+    "    return 1 / (1 / 2 * np.exp(-t) + (np.cos(t) - np.sin(t)) / 2)\n",
+    "\n",
     "\n",
     "t0, T = 0, 0.5\n",
     "N = 100\n",
     "y0 = 1\n",
-    "t, y_app = mon_schema(t0, T, y0, T/N, f)\n",
+    "t, y_app = mon_schema(t0, T, y0, T / N, f)\n",
     "y_ex = yex(t)\n",
     "\n",
     "plt.figure(1)\n",
-    "plt.plot(t, y_ex, label='Solution exacte', lw=3)\n",
-    "plt.plot(t, y_app, '+ ', label=f'Solution approchée pour N={N}')\n",
-    "plt.title('Solutions approchées pour mon_schema')\n",
-    "plt.xlabel(f'$t$')\n",
-    "plt.ylabel(f'$y$')\n",
+    "plt.plot(t, y_ex, label=\"Solution exacte\", lw=3)\n",
+    "plt.plot(t, y_app, \"+ \", label=f\"Solution approchée pour N={N}\")\n",
+    "plt.title(\"Solutions approchées pour mon_schema\")\n",
+    "plt.xlabel(\"$t$\")\n",
+    "plt.ylabel(\"$y$\")\n",
     "plt.legend(fontsize=7)"
    ]
   },
@@ -212,15 +215,17 @@
     "# Question 3\n",
     "plt.figure(2)\n",
     "\n",
-    "for s in range(2,11):\n",
-    "    h=(1/2)/(2**s)\n",
+    "for s in range(2, 11):\n",
+    "    h = (1 / 2) / (2**s)\n",
     "    t, y_app = mon_schema(t0, T, y0, h, f)\n",
-    "    plt.plot(t, y_app, label=f'h={h}')\n",
+    "    plt.plot(t, y_app, label=f\"h={h}\")\n",
     "\n",
     "plt.legend(fontsize=7)\n",
-    "plt.xlabel(f'$t$')\n",
-    "plt.ylabel('$y^n$')\n",
-    "plt.title('Solutions approchées de (P) obtenus avec mon_schema pour différentes valeurs du pas h')"
+    "plt.xlabel(\"$t$\")\n",
+    "plt.ylabel(\"$y^n$\")\n",
+    "plt.title(\n",
+    "    \"Solutions approchées de (P) obtenus avec mon_schema pour différentes valeurs du pas h\"\n",
+    ")"
    ]
   },
   {
@@ -252,23 +257,25 @@
     }
    ],
    "source": [
-    "E=[]\n",
-    "H=[]\n",
+    "E = []\n",
+    "H = []\n",
     "\n",
     "plt.figure(3)\n",
-    "for s in range(2,11):\n",
-    "    h=(1/2)/(2**s)\n",
+    "for s in range(2, 11):\n",
+    "    h = (1 / 2) / (2**s)\n",
     "    t, y_app = mon_schema(t0, T, y0, h, f)\n",
     "    y_ex = yex(t)\n",
     "    err = np.max(np.abs(y_app - y_ex))\n",
-    "    plt.plot(t, np.abs(y_app - y_ex), label=f'h={h}')\n",
+    "    plt.plot(t, np.abs(y_app - y_ex), label=f\"h={h}\")\n",
     "    E.append(err)\n",
     "    H.append(h)\n",
-    "    \n",
+    "\n",
     "plt.legend()\n",
-    "plt.xlabel(f'$t$')\n",
-    "plt.ylabel('$|y(t_n) - y^n|$')\n",
-    "plt.title('différence en valeur absolue entre sol. exacte et sol. approchée par mon_schema, pour différentes valeurs du pas h')"
+    "plt.xlabel(\"$t$\")\n",
+    "plt.ylabel(\"$|y(t_n) - y^n|$\")\n",
+    "plt.title(\n",
+    "    \"différence en valeur absolue entre sol. exacte et sol. approchée par mon_schema, pour différentes valeurs du pas h\"\n",
+    ")"
    ]
   },
   {
@@ -304,13 +311,13 @@
     "\n",
     "H, E = np.array(H), np.array(E)\n",
     "\n",
-    "plt.plot(T/H, E/H, label=f'$E_h / h$')\n",
-    "plt.plot(T/H, E/H**2, label=f'$E_h / h^2$')\n",
+    "plt.plot(T / H, E / H, label=\"$E_h / h$\")\n",
+    "plt.plot(T / H, E / H**2, label=\"$E_h / h^2$\")\n",
     "\n",
     "plt.legend()\n",
-    "plt.xlabel('N')\n",
-    "plt.ylabel('Erreur globale')\n",
-    "plt.title('Erreur globale en fonction de N')"
+    "plt.xlabel(\"N\")\n",
+    "plt.ylabel(\"Erreur globale\")\n",
+    "plt.title(\"Erreur globale en fonction de N\")"
    ]
   },
   {
@@ -344,14 +351,16 @@
    "source": [
     "plt.figure(5)\n",
     "\n",
-    "plt.plot(np.log(H), np.log(E), '+-', label='erreur')\n",
-    "plt.plot(np.log(H), np.log(H), '-', label='droite pente 1')\n",
-    "plt.plot(np.log(H), 2*np.log(H), '-', label='droite pente 2')\n",
+    "plt.plot(np.log(H), np.log(E), \"+-\", label=\"erreur\")\n",
+    "plt.plot(np.log(H), np.log(H), \"-\", label=\"droite pente 1\")\n",
+    "plt.plot(np.log(H), 2 * np.log(H), \"-\", label=\"droite pente 2\")\n",
     "\n",
     "plt.legend()\n",
-    "plt.title('Erreur pour la méthode mon_schema en echelle logarithmique : log(E) en fonction de log(h)')\n",
-    "plt.xlabel(f'$log(h)$')\n",
-    "plt.ylabel(f'$log(E)$')"
+    "plt.title(\n",
+    "    \"Erreur pour la méthode mon_schema en echelle logarithmique : log(E) en fonction de log(h)\"\n",
+    ")\n",
+    "plt.xlabel(\"$log(h)$\")\n",
+    "plt.ylabel(\"$log(E)$\")"
    ]
   },
   {
@@ -444,24 +453,26 @@
     "    t = np.arange(t0, t0 + T + h, h)\n",
     "    y = 0 * t\n",
     "    y[0] = y0\n",
-    "    for n in range(len(t)-1):\n",
-    "        y[n+1] = y[n] + h * f(t[n+1], y[n+1])\n",
+    "    for n in range(len(t) - 1):\n",
+    "        y[n + 1] = y[n] + h * f(t[n + 1], y[n + 1])\n",
     "    return t, y\n",
     "\n",
+    "\n",
     "def crank(t0, T, y0, h, f):\n",
     "    t = np.arange(t0, t0 + T + h, h)\n",
     "    y = 0 * t\n",
     "    y[0] = y0\n",
-    "    for n in range(len(t)-1):\n",
-    "        y[n+1] = y[n] + h/2 * (f(t[n], y[n]) + f(t[n+1], y[n+1]))\n",
+    "    for n in range(len(t) - 1):\n",
+    "        y[n + 1] = y[n] + h / 2 * (f(t[n], y[n]) + f(t[n + 1], y[n + 1]))\n",
     "    return t, y\n",
     "\n",
+    "\n",
     "def adams(t0, T, y0, h, f):\n",
     "    t = np.arange(t0, t0 + T + h, h)\n",
     "    y = 0 * t\n",
     "    y[0] = y0\n",
-    "    for n in range(1, len(t)-1):\n",
-    "        y[n+1] = y[n] + h/2 * (3* f(t[n], y[n]) - f(t[n-1], y[n-1]))\n",
+    "    for n in range(1, len(t) - 1):\n",
+    "        y[n + 1] = y[n] + h / 2 * (3 * f(t[n], y[n]) - f(t[n - 1], y[n - 1]))\n",
     "    return t, y"
    ]
   },
@@ -474,39 +485,41 @@
    "outputs": [],
    "source": [
     "def euler_explicite(t0, T, y0, h, f):\n",
-    "    N = int(T/h)\n",
+    "    N = int(T / h)\n",
     "    n = len(y0)\n",
-    "    t = np.linspace(t0, t0 + T, N+1)\n",
-    "    y = np.zeros((N+1, n))\n",
+    "    t = np.linspace(t0, t0 + T, N + 1)\n",
+    "    y = np.zeros((N + 1, n))\n",
     "    y[0,] = y0\n",
     "    for n in range(N):\n",
-    "        y[n+1] = y[n] + h * f(t[n], y[n])\n",
+    "        y[n + 1] = y[n] + h * f(t[n], y[n])\n",
     "    return t, y\n",
     "\n",
+    "\n",
     "def heun(t0, T, y0, h, f):\n",
-    "    N = int(T/h)\n",
+    "    N = int(T / h)\n",
     "    n = len(y0)\n",
-    "    t = np.linspace(t0, t0 + T, N+1)\n",
-    "    y = np.zeros((N+1, n))\n",
+    "    t = np.linspace(t0, t0 + T, N + 1)\n",
+    "    y = np.zeros((N + 1, n))\n",
     "    y[0,] = y0\n",
     "    for n in range(N):\n",
     "        p1 = f(t[n], y[n])\n",
     "        p2 = f(t[n] + h, y[n] + h * p1)\n",
-    "        y[n+1] = y[n] + h/2 * (p1 + p2)\n",
+    "        y[n + 1] = y[n] + h / 2 * (p1 + p2)\n",
     "    return t, y\n",
     "\n",
+    "\n",
     "def runge(t0, T, y0, h, f):\n",
-    "    N = int(T/h)\n",
+    "    N = int(T / h)\n",
     "    n = len(y0)\n",
-    "    t = np.linspace(t0, t0 + T, N+1)\n",
-    "    y = np.zeros((N+1, n))\n",
+    "    t = np.linspace(t0, t0 + T, N + 1)\n",
+    "    y = np.zeros((N + 1, n))\n",
     "    y[0,] = y0\n",
     "    for n in range(N):\n",
     "        p1 = f(t[n], y[n])\n",
-    "        p2 = f(t[n] + h/2, y[n] + h/2 * p1)\n",
-    "        p3 = f(t[n] + h/2, y[n] + h/2 * p2)\n",
-    "        p4 = f(t[n] + h, y[n] + h* p3)\n",
-    "        y[n+1] = y[n] + h/6 * (p1 + 2*p2 + 2*p3 + p4)\n",
+    "        p2 = f(t[n] + h / 2, y[n] + h / 2 * p1)\n",
+    "        p3 = f(t[n] + h / 2, y[n] + h / 2 * p2)\n",
+    "        p4 = f(t[n] + h, y[n] + h * p3)\n",
+    "        y[n + 1] = y[n] + h / 6 * (p1 + 2 * p2 + 2 * p3 + p4)\n",
     "    return t, y"
    ]
   },
@@ -624,13 +637,16 @@
     "# Question 1\n",
     "a, b, c = 0.1, 2, 1\n",
     "\n",
+    "\n",
     "# f second membre de l'EDO\n",
-    "def f1(t,y):\n",
-    "    return c * y * (1 - y/b)\n",
+    "def f1(t, y):\n",
+    "    return c * y * (1 - y / b)\n",
+    "\n",
     "\n",
     "# sol. exacte de (P1)\n",
     "def yex1(t):\n",
-    "    return b / (1 + (b-a)/a * np.exp(-c*t))\n",
+    "    return b / (1 + (b - a) / a * np.exp(-c * t))\n",
+    "\n",
     "\n",
     "t0, T = 0, 15\n",
     "h = 0.2\n",
@@ -639,25 +655,27 @@
     "plt.figure()\n",
     "for schema in [euler_explicite, heun, runge]:\n",
     "    t, y_app = schema(t0, T, y0, h, f1)\n",
-    "    plt.plot(t, y_app.ravel(), '+ ', label=f'Solution approchée par {schema.__name__}')\n",
+    "    plt.plot(t, y_app.ravel(), \"+ \", label=f\"Solution approchée par {schema.__name__}\")\n",
     "\n",
-    "t = np.arange(t0, t0+T+h, h)\n",
+    "t = np.arange(t0, t0 + T + h, h)\n",
     "y_ex = yex1(t)\n",
-    "plt.plot(t, y_ex, label='Solution exacte', lw=1)\n",
-    "plt.title(f'Solutions approchées pour le schema {schema.__name__}')\n",
-    "plt.xlabel(f'$t$')\n",
-    "plt.ylabel(f'$y$')\n",
+    "plt.plot(t, y_ex, label=\"Solution exacte\", lw=1)\n",
+    "plt.title(f\"Solutions approchées pour le schema {schema.__name__}\")\n",
+    "plt.xlabel(\"$t$\")\n",
+    "plt.ylabel(\"$y$\")\n",
     "plt.legend(fontsize=7)\n",
     "\n",
     "plt.figure()\n",
-    "for schema in [euler_explicite, heun, runge]:    \n",
+    "for schema in [euler_explicite, heun, runge]:\n",
     "    t, y_app = schema(t0, T, y0, h, f1)\n",
-    "    plt.plot(t, np.abs(y_app.ravel() - yex1(t)), label=f'Schema {schema.__name__}')\n",
-    "    \n",
+    "    plt.plot(t, np.abs(y_app.ravel() - yex1(t)), label=f\"Schema {schema.__name__}\")\n",
+    "\n",
     "plt.legend()\n",
-    "plt.xlabel(f'$t$')\n",
-    "plt.ylabel('$|y(t_n) - y^n|$')\n",
-    "plt.title(f'différence en valeur absolue entre sol. exacte et sol. approchée, pour différents schemas')"
+    "plt.xlabel(\"$t$\")\n",
+    "plt.ylabel(\"$|y(t_n) - y^n|$\")\n",
+    "plt.title(\n",
+    "    \"différence en valeur absolue entre sol. exacte et sol. approchée, pour différents schemas\"\n",
+    ")"
    ]
   },
   {
@@ -696,24 +714,26 @@
     "    Z[1] = -Y[0] + np.cos(t)\n",
     "    return Z\n",
     "\n",
+    "\n",
     "def yexF(t):\n",
-    "    return 1/2 * np.sin(t) * t + 5 * np.cos(t) + np.sin(t),\n",
+    "    return (1 / 2 * np.sin(t) * t + 5 * np.cos(t) + np.sin(t),)\n",
+    "\n",
     "\n",
     "t0, T = 0, 15\n",
     "h = 0.2\n",
-    "Y0 = np.array([5,1])\n",
+    "Y0 = np.array([5, 1])\n",
     "\n",
     "plt.figure()\n",
     "for schema in [euler_explicite, heun, runge]:\n",
     "    t, y_app = schema(t0, T, Y0, h, F)\n",
-    "    plt.plot(t, y_app[:,0], '+ ', label=f'Solution approchée par {schema.__name__}')\n",
+    "    plt.plot(t, y_app[:, 0], \"+ \", label=f\"Solution approchée par {schema.__name__}\")\n",
     "\n",
-    "t = np.arange(t0, t0+T+h, h)\n",
+    "t = np.arange(t0, t0 + T + h, h)\n",
     "y_ex = yexF(t)\n",
-    "plt.plot(t, y_ex[0], label='Solution exacte', lw=3)\n",
-    "plt.title('Solutions approchées par differents schemas')\n",
-    "plt.xlabel(f'$t$')\n",
-    "plt.ylabel(f'$y$')\n",
+    "plt.plot(t, y_ex[0], label=\"Solution exacte\", lw=3)\n",
+    "plt.title(\"Solutions approchées par differents schemas\")\n",
+    "plt.xlabel(\"$t$\")\n",
+    "plt.ylabel(\"$y$\")\n",
     "plt.legend(fontsize=7)"
    ]
   },
@@ -726,20 +746,24 @@
    "outputs": [],
    "source": [
     "%matplotlib inline\n",
-    "import numpy as np\n",
     "import matplotlib.pyplot as plt\n",
+    "import numpy as np\n",
+    "\n",
     "# Question 3\n",
     "\n",
+    "\n",
     "# f second membre de l'EDO\n",
-    "def f3(t,y):\n",
-    "    return (np.cos(t) - y) / (1+t)\n",
+    "def f3(t, y):\n",
+    "    return (np.cos(t) - y) / (1 + t)\n",
+    "\n",
     "\n",
     "# sol. exacte de (P1)\n",
     "def yex3(t):\n",
-    "    return (np.sin(t) - 1/4) / (1 + t)\n",
+    "    return (np.sin(t) - 1 / 4) / (1 + t)\n",
+    "\n",
     "\n",
     "t0, T = 0, 10\n",
-    "y0 = np.array([-1/4])"
+    "y0 = np.array([-1 / 4])"
    ]
   },
   {
@@ -793,15 +817,17 @@
     "plt.figure()\n",
     "for schema in [euler_explicite, heun, runge]:\n",
     "    plt.figure()\n",
-    "    for s in range(2,11):\n",
-    "        h=1/(2**s)\n",
+    "    for s in range(2, 11):\n",
+    "        h = 1 / (2**s)\n",
     "        t, y_app = schema(t0, T, y0, h, f3)\n",
-    "        plt.plot(t, y_app, label=f'h={h}')\n",
+    "        plt.plot(t, y_app, label=f\"h={h}\")\n",
     "\n",
     "    plt.legend(fontsize=7)\n",
-    "    plt.xlabel(f'$t$')\n",
-    "    plt.ylabel('$y^n$')\n",
-    "    plt.title(f'Solutions approchées de (P) obtenus avec {schema.__name__} pour différentes valeurs du pas h')"
+    "    plt.xlabel(\"$t$\")\n",
+    "    plt.ylabel(\"$y^n$\")\n",
+    "    plt.title(\n",
+    "        f\"Solutions approchées de (P) obtenus avec {schema.__name__} pour différentes valeurs du pas h\"\n",
+    "    )"
    ]
   },
   {
@@ -846,22 +872,24 @@
     "for schema in [euler_explicite, heun, runge]:\n",
     "    H, E = [], []\n",
     "    plt.figure()\n",
-    "    for s in range(2,11):\n",
-    "        h=1/(2**s)\n",
+    "    for s in range(2, 11):\n",
+    "        h = 1 / (2**s)\n",
     "        t, y_app = schema(t0, T, y0, h, f3)\n",
     "        E.append(np.max(np.abs(yex3(t) - y_app.ravel())))\n",
     "        H.append(h)\n",
-    "    \n",
+    "\n",
     "    H, E = np.array(H), np.array(E)\n",
-    "    plt.plot(np.log(H), np.log(E), '+-', label='erreur')\n",
-    "    plt.plot(np.log(H), np.log(H), '-', label='droite pente 1')\n",
-    "    plt.plot(np.log(H), 2*np.log(H), '-', label='droite pente 2')\n",
-    "    plt.plot(np.log(H), 3*np.log(H), '-', label='droite pente 3')\n",
-    "    \n",
+    "    plt.plot(np.log(H), np.log(E), \"+-\", label=\"erreur\")\n",
+    "    plt.plot(np.log(H), np.log(H), \"-\", label=\"droite pente 1\")\n",
+    "    plt.plot(np.log(H), 2 * np.log(H), \"-\", label=\"droite pente 2\")\n",
+    "    plt.plot(np.log(H), 3 * np.log(H), \"-\", label=\"droite pente 3\")\n",
+    "\n",
     "    plt.legend()\n",
-    "    plt.title(f'Erreur pour la méthode {schema.__name__} en echelle logarithmique : log(E) en fonction de log(h)')\n",
-    "    plt.xlabel(f'$log(h)$')\n",
-    "    plt.ylabel(f'$log(E)$')"
+    "    plt.title(\n",
+    "        f\"Erreur pour la méthode {schema.__name__} en echelle logarithmique : log(E) en fonction de log(h)\"\n",
+    "    )\n",
+    "    plt.xlabel(\"$log(h)$\")\n",
+    "    plt.ylabel(\"$log(E)$\")"
    ]
   },
   {
@@ -943,19 +971,20 @@
     "a = 5\n",
     "t0, T = 0, 20\n",
     "H = [0.1, 0.05, 0.025]\n",
-    "Y0 = np.array([1/10, 1])\n",
+    "Y0 = np.array([1 / 10, 1])\n",
+    "\n",
     "\n",
     "def P(t, Y):\n",
-    "    return np.array([Y[1], (a - Y[0]**2) * Y[1] - Y[0]])\n",
+    "    return np.array([Y[1], (a - Y[0] ** 2) * Y[1] - Y[0]])\n",
+    "\n",
     "\n",
     "for schema in [euler_explicite, heun, runge]:\n",
     "    plt.figure()\n",
     "    for h in H:\n",
     "        t, y_app = schema(t0, T, Y0, h, P)\n",
-    "        plt.plot(t, y_app[:,0], '+ ', label=f'Solution approchée pour h={h}')\n",
+    "        plt.plot(t, y_app[:, 0], \"+ \", label=f\"Solution approchée pour h={h}\")\n",
     "    plt.legend()\n",
-    "    plt.title(f'Solutions approchees pour differents pas h par {schema.__name__}')\n",
-    "    "
+    "    plt.title(f\"Solutions approchees pour differents pas h par {schema.__name__}\")"
    ]
   },
   {

L3/Méthodes Numériques/TP1_Equation_de_Poisson.ipynb

@@ -240,22 +240,25 @@
    "outputs": [],
    "source": [
     "import numpy as np\n",
+    "\n",
     "%matplotlib inline\n",
     "import matplotlib.pyplot as plt\n",
     "\n",
+    "\n",
     "def A(M):\n",
     "    return 2 * np.eye(M) - np.eye(M, k=-1) - np.eye(M, k=1)\n",
     "\n",
+    "\n",
     "def solution_approchée(f, M, a=0, b=1, ua=0, ub=0):\n",
-    "    X = np.linspace(a, b + 1 if b == 0 else b, M+2)\n",
-    "    U = np.zeros(M+2)\n",
+    "    X = np.linspace(a, b + 1 if b == 0 else b, M + 2)\n",
+    "    U = np.zeros(M + 2)\n",
     "    U[0], U[-1] = ua, ub\n",
-    "    \n",
-    "    h = (b-a)/(M+1)\n",
+    "\n",
+    "    h = (b - a) / (M + 1)\n",
     "\n",
     "    delta = np.zeros(M)\n",
-    "    delta[0], delta[-1] = ua/np.power(h, 2), ub/np.power(h, 2)\n",
-    "    \n",
+    "    delta[0], delta[-1] = ua / np.power(h, 2), ub / np.power(h, 2)\n",
+    "\n",
     "    U[1:-1] = np.linalg.solve(A(M), h**2 * (f(X)[1:-1] + delta))\n",
     "    return X, U"
    ]
@@ -290,22 +293,25 @@
    ],
    "source": [
     "M = 50\n",
-    "h = 1/(M+1)\n",
+    "h = 1 / (M + 1)\n",
+    "\n",
     "\n",
     "def f1(x):\n",
-    "    return (2 * np.pi)**2 * np.sin(2 * np.pi * x)\n",
+    "    return (2 * np.pi) ** 2 * np.sin(2 * np.pi * x)\n",
+    "\n",
     "\n",
     "def u1(x):\n",
     "    return np.sin(2 * np.pi * x)\n",
     "\n",
+    "\n",
     "x, U_app = solution_approchée(f1, M)\n",
     "plt.figure()\n",
-    "plt.scatter(x, U_app, label=f\"$A_M U_h = h² F$\")\n",
-    "plt.plot(x, u1(x), label='Solution exacte', color='red')\n",
+    "plt.scatter(x, U_app, label=\"$A_M U_h = h² F$\")\n",
+    "plt.plot(x, u1(x), label=\"Solution exacte\", color=\"red\")\n",
     "plt.legend()\n",
-    "plt.ylabel('f(x)')\n",
-    "plt.xlabel('x')\n",
-    "plt.title(f\"$-u''=f(x)$\")"
+    "plt.ylabel(\"f(x)\")\n",
+    "plt.xlabel(\"x\")\n",
+    "plt.title(\"$-u''=f(x)$\")"
    ]
   },
   {
@@ -340,21 +346,23 @@
     "H, E = [], []\n",
     "for k in range(2, 12):\n",
     "    M = 2**k\n",
-    "    h = 1/(M+1)\n",
-    "    \n",
+    "    h = 1 / (M + 1)\n",
+    "\n",
     "    x, U_app = solution_approchée(f1, M)\n",
-    "    \n",
+    "\n",
     "    e = np.abs(u1(x) - U_app)\n",
-    "    plt.plot(x, e, label=f'{h}')\n",
+    "    plt.plot(x, e, label=f\"{h}\")\n",
     "    E.append(np.max(e))\n",
     "    H.append(h)\n",
     "\n",
-    "H, E = np.array(H), np.array(E)    \n",
+    "H, E = np.array(H), np.array(E)\n",
     "\n",
-    "plt.xlabel('$h$')\n",
-    "plt.ylabel('$\\max_{j=0,\\dots,M+1}|u(x_j)-u_j|$')\n",
+    "plt.xlabel(\"$h$\")\n",
+    "plt.ylabel(r\"$\\max_{j=0,\\dots,M+1}|u(x_j)-u_j|$\")\n",
     "plt.legend(fontsize=7)\n",
-    "plt.title('Différence en valeur absolue entre la solution exacte et la solution approchée')"
+    "plt.title(\n",
+    "    \"Différence en valeur absolue entre la solution exacte et la solution approchée\"\n",
+    ")"
    ]
   },
   {
@@ -387,12 +395,12 @@
    ],
    "source": [
     "plt.figure()\n",
-    "plt.plot(H, E/H, label=f'$E_h / h$')\n",
-    "plt.plot(H, E/H**2, label=f'$E_h / h^2$')\n",
+    "plt.plot(H, E / H, label=\"$E_h / h$\")\n",
+    "plt.plot(H, E / H**2, label=\"$E_h / h^2$\")\n",
     "plt.legend()\n",
-    "plt.xlabel('$h$')\n",
-    "plt.ylabel('Erreur globale')\n",
-    "plt.title('Erreur globale en fonction de $h$')"
+    "plt.xlabel(\"$h$\")\n",
+    "plt.ylabel(\"Erreur globale\")\n",
+    "plt.title(\"Erreur globale en fonction de $h$\")"
    ]
   },
   {
@@ -425,13 +433,15 @@
    ],
    "source": [
     "plt.figure()\n",
-    "plt.plot(np.log(H), np.log(E), '+-', label='erreur')\n",
-    "plt.plot(np.log(H), np.log(H), '-', label='droite pente 1')\n",
-    "plt.plot(np.log(H), 2*np.log(H), '-', label='droite pente 2')\n",
+    "plt.plot(np.log(H), np.log(E), \"+-\", label=\"erreur\")\n",
+    "plt.plot(np.log(H), np.log(H), \"-\", label=\"droite pente 1\")\n",
+    "plt.plot(np.log(H), 2 * np.log(H), \"-\", label=\"droite pente 2\")\n",
     "plt.legend()\n",
-    "plt.xlabel(f'$log(h)$')\n",
-    "plt.ylabel(f'$log(E)$')\n",
-    "plt.title('Erreur pour la méthode mon_schema en echelle logarithmique : log(E) en fonction de log(h)')"
+    "plt.xlabel(\"$log(h)$\")\n",
+    "plt.ylabel(\"$log(E)$\")\n",
+    "plt.title(\n",
+    "    \"Erreur pour la méthode mon_schema en echelle logarithmique : log(E) en fonction de log(h)\"\n",
+    ")"
    ]
   },
   {
@@ -509,27 +519,31 @@
    ],
    "source": [
     "import numpy as np\n",
+    "\n",
     "%matplotlib inline\n",
     "import matplotlib.pyplot as plt\n",
     "\n",
-    "ua, ub = 1/2, 1/3\n",
+    "ua, ub = 1 / 2, 1 / 3\n",
     "a, b = 1, 2\n",
     "M = 49\n",
     "\n",
+    "\n",
     "def f2(x):\n",
-    "    return -2/np.power((x+1), 3)\n",
+    "    return -2 / np.power((x + 1), 3)\n",
+    "\n",
     "\n",
     "def u2(x):\n",
-    "    return 1/(x+1)\n",
+    "    return 1 / (x + 1)\n",
+    "\n",
     "\n",
     "x, U_app = solution_approchée(f2, M, a, b, ua, ub)\n",
     "plt.figure()\n",
-    "plt.scatter(x, U_app, label=f\"$A_M U_h = h² F$\")\n",
-    "plt.plot(x, u2(x), label='Solution exacte', color='red')\n",
+    "plt.scatter(x, U_app, label=\"$A_M U_h = h² F$\")\n",
+    "plt.plot(x, u2(x), label=\"Solution exacte\", color=\"red\")\n",
     "plt.legend()\n",
-    "plt.ylabel('f(x)')\n",
-    "plt.xlabel('x')\n",
-    "plt.title(f\"$-u''=f(x)$\")"
+    "plt.ylabel(\"f(x)\")\n",
+    "plt.xlabel(\"x\")\n",
+    "plt.title(\"$-u''=f(x)$\")"
    ]
   },
   {
@@ -565,19 +579,21 @@
     "H, E = [], []\n",
     "for k in range(2, 12):\n",
     "    M = 2**k\n",
-    "    h = (b-a)/(M+1)\n",
-    "    \n",
+    "    h = (b - a) / (M + 1)\n",
+    "\n",
     "    x, U_app = solution_approchée(f2, M, a, b, ua, ub)\n",
-    "    \n",
+    "\n",
     "    e = np.abs(u2(x) - U_app)\n",
-    "    plt.plot(x, e, label=f'{h}')\n",
+    "    plt.plot(x, e, label=f\"{h}\")\n",
     "    E.append(np.max(e))\n",
     "    H.append(h)\n",
-    " \n",
-    "plt.xlabel('$h$')\n",
-    "plt.ylabel('$\\max_{j=0,\\dots,M+1}|u(x_j)-u_j|$')\n",
+    "\n",
+    "plt.xlabel(\"$h$\")\n",
+    "plt.ylabel(r\"$\\max_{j=0,\\dots,M+1}|u(x_j)-u_j|$\")\n",
     "plt.legend(fontsize=7)\n",
-    "plt.title('Différence en valeur absolue entre la solution exacte et la solution approchée')"
+    "plt.title(\n",
+    "    \"Différence en valeur absolue entre la solution exacte et la solution approchée\"\n",
+    ")"
    ]
   },
   {
@@ -609,14 +625,14 @@
     }
    ],
    "source": [
-    "H, E = np.array(H), np.array(E)   \n",
+    "H, E = np.array(H), np.array(E)\n",
     "plt.figure()\n",
-    "plt.plot(H, E/H, label=f'$E_h / h$')\n",
-    "plt.plot(H, E/H**2, label=f'$E_h / h^2$')\n",
+    "plt.plot(H, E / H, label=\"$E_h / h$\")\n",
+    "plt.plot(H, E / H**2, label=\"$E_h / h^2$\")\n",
     "plt.legend()\n",
-    "plt.xlabel('$h$')\n",
-    "plt.ylabel('Erreur globale')\n",
-    "plt.title('Erreur globale en fonction de $h$')"
+    "plt.xlabel(\"$h$\")\n",
+    "plt.ylabel(\"Erreur globale\")\n",
+    "plt.title(\"Erreur globale en fonction de $h$\")"
    ]
   },
   {
@@ -649,13 +665,15 @@
    ],
    "source": [
     "plt.figure()\n",
-    "plt.plot(np.log(H), np.log(E), '+-', label='erreur')\n",
-    "plt.plot(np.log(H), np.log(H), '-', label='droite pente 1')\n",
-    "plt.plot(np.log(H), 2*np.log(H), '-', label='droite pente 2')\n",
+    "plt.plot(np.log(H), np.log(E), \"+-\", label=\"erreur\")\n",
+    "plt.plot(np.log(H), np.log(H), \"-\", label=\"droite pente 1\")\n",
+    "plt.plot(np.log(H), 2 * np.log(H), \"-\", label=\"droite pente 2\")\n",
     "plt.legend()\n",
-    "plt.xlabel(f'$log(h)$')\n",
-    "plt.ylabel(f'$log(E)$')\n",
-    "plt.title('Erreur pour la méthode mon_schema en echelle logarithmique : log(E) en fonction de log(h)')"
+    "plt.xlabel(\"$log(h)$\")\n",
+    "plt.ylabel(\"$log(E)$\")\n",
+    "plt.title(\n",
+    "    \"Erreur pour la méthode mon_schema en echelle logarithmique : log(E) en fonction de log(h)\"\n",
+    ")"
    ]
   },
   {
@@ -732,22 +750,25 @@
    ],
    "source": [
     "def An(M, h):\n",
-    "    mat = 2*np.eye(M) - np.eye(M, k=1) - np.eye(M, k=-1)\n",
-    "    mat[0,0] = 1\n",
+    "    mat = 2 * np.eye(M) - np.eye(M, k=1) - np.eye(M, k=-1)\n",
+    "    mat[0, 0] = 1\n",
     "    mat[-1, -1] = 1\n",
     "    return mat + h**2 * np.eye(M)\n",
     "\n",
+    "\n",
     "def f3(x):\n",
-    "    return (np.power(2 * np.pi, 2) + 1 ) * np.cos(2*np.pi * x)\n",
+    "    return (np.power(2 * np.pi, 2) + 1) * np.cos(2 * np.pi * x)\n",
+    "\n",
     "\n",
     "def u3(x):\n",
-    "    return np.cos(2*np.pi * x)\n",
+    "    return np.cos(2 * np.pi * x)\n",
+    "\n",
     "\n",
     "def solution_neumann(f, M, a, b):\n",
-    "    X = np.linspace(a, b, M+2)\n",
-    "    U = np.zeros(M+2)\n",
-    "    h = 1/(M+1)\n",
-    "    \n",
+    "    X = np.linspace(a, b, M + 2)\n",
+    "    U = np.zeros(M + 2)\n",
+    "    h = 1 / (M + 1)\n",
+    "\n",
     "    U[1:-1] = np.linalg.solve(An(M, h), h**2 * f3(X[1:-1]))\n",
     "    U[0], U[-1] = U[1], U[-2]\n",
     "    return X, U\n",
@@ -759,12 +780,14 @@
     "for M in [49, 99, 499]:\n",
     "    x, U_app = solution_neumann(f3, M, a, b)\n",
     "\n",
-    "    plt.scatter(x, U_app, marker='+', s=3, label=\"$h^2({A_N}_h + I_M)U = h^2F$ pour M={M}\")\n",
-    "plt.plot(x, u3(x), label='Solution exacte', color='red')\n",
+    "    plt.scatter(\n",
+    "        x, U_app, marker=\"+\", s=3, label=\"$h^2({A_N}_h + I_M)U = h^2F$ pour M={M}\"\n",
+    "    )\n",
+    "plt.plot(x, u3(x), label=\"Solution exacte\", color=\"red\")\n",
     "plt.legend(fontsize=8)\n",
-    "plt.ylabel('f(x)')\n",
-    "plt.xlabel('x')\n",
-    "plt.title(f\"$-u''(x) + u(x)=f(x)$\")"
+    "plt.ylabel(\"f(x)\")\n",
+    "plt.xlabel(\"x\")\n",
+    "plt.title(\"$-u''(x) + u(x)=f(x)$\")"
    ]
   },
   {
@@ -800,19 +823,21 @@
     "H, E = [], []\n",
     "for k in range(2, 12):\n",
     "    M = 2**k\n",
-    "    h = (b-a)/(M+1)\n",
-    "    \n",
+    "    h = (b - a) / (M + 1)\n",
+    "\n",
     "    x, U_app = solution_neumann(f3, M, a, b)\n",
-    "    \n",
+    "\n",
     "    e = np.abs(u3(x) - U_app)\n",
-    "    plt.plot(x, e, label=f'{h}')\n",
+    "    plt.plot(x, e, label=f\"{h}\")\n",
     "    E.append(np.max(e))\n",
     "    H.append(h)\n",
-    " \n",
-    "plt.xlabel('$h$')\n",
-    "plt.ylabel('$\\max_{j=0,\\dots,M+1}|u(x_j)-u_j|$')\n",
+    "\n",
+    "plt.xlabel(\"$h$\")\n",
+    "plt.ylabel(r\"$\\max_{j=0,\\dots,M+1}|u(x_j)-u_j|$\")\n",
     "plt.legend(fontsize=7)\n",
-    "plt.title('Différence en valeur absolue entre la solution exacte et la solution approchée')"
+    "plt.title(\n",
+    "    \"Différence en valeur absolue entre la solution exacte et la solution approchée\"\n",
+    ")"
    ]
   },
   {
@@ -845,13 +870,15 @@
    ],
    "source": [
     "plt.figure()\n",
-    "plt.plot(np.log(H), np.log(E), '+-', label='erreur')\n",
-    "plt.plot(np.log(H), np.log(H), '-', label='droite pente 1')\n",
-    "plt.plot(np.log(H), 2*np.log(H), '-', label='droite pente 2')\n",
+    "plt.plot(np.log(H), np.log(E), \"+-\", label=\"erreur\")\n",
+    "plt.plot(np.log(H), np.log(H), \"-\", label=\"droite pente 1\")\n",
+    "plt.plot(np.log(H), 2 * np.log(H), \"-\", label=\"droite pente 2\")\n",
     "plt.legend()\n",
-    "plt.xlabel(f'$log(h)$')\n",
-    "plt.ylabel(f'$log(E)$')\n",
-    "plt.title('Erreur pour la méthode mon_schema en echelle logarithmique : log(E) en fonction de log(h)')"
+    "plt.xlabel(\"$log(h)$\")\n",
+    "plt.ylabel(\"$log(E)$\")\n",
+    "plt.title(\n",
+    "    \"Erreur pour la méthode mon_schema en echelle logarithmique : log(E) en fonction de log(h)\"\n",
+    ")"
    ]
   },
   {
@@ -959,7 +986,11 @@
    "outputs": [],
    "source": [
     "def v(x):\n",
-    "    return 4*np.exp(-500*np.square(x-.8)) + np.exp(-50*np.square(x-.2))+.5*np.random.random(x.shape)"
+    "    return (\n",
+    "        4 * np.exp(-500 * np.square(x - 0.8))\n",
+    "        + np.exp(-50 * np.square(x - 0.2))\n",
+    "        + 0.5 * np.random.random(x.shape)\n",
+    "    )"
    ]
   }
  ],

L3/Statistiques/TP1.ipynb

@@ -9,8 +9,8 @@
    },
    "outputs": [],
    "source": [
-    "import numpy as np\n",
     "import matplotlib.pyplot as plt\n",
+    "import numpy as np\n",
     "import scipy.stats as stats"
    ]
   },
@@ -48,10 +48,10 @@
     "nb_repl = 100000\n",
     "sample = np.random.exponential(lam, nb_repl)\n",
     "intervalle = np.linspace(0, 5, 100)\n",
-    "plt.hist(sample, bins=intervalle, density=True, label='Echantillon')\n",
+    "plt.hist(sample, bins=intervalle, density=True, label=\"Echantillon\")\n",
     "\n",
     "densite = stats.expon().pdf\n",
-    "plt.plot(intervalle, densite(intervalle), label='Fonction densité')\n",
+    "plt.plot(intervalle, densite(intervalle), label=\"Fonction densité\")\n",
     "plt.legend()"
    ]
   },
@@ -86,15 +86,15 @@
    ],
    "source": [
     "np_repl = 10000\n",
-    "sampleX, sampleY = 2*np.random.rand(np_repl)-1, 2*np.random.rand(np_repl)-1\n",
+    "sampleX, sampleY = 2 * np.random.rand(np_repl) - 1, 2 * np.random.rand(np_repl) - 1\n",
     "\n",
     "intervalle = np.linspace(-2, 2, 100)\n",
-    "plt.hist(sampleX + sampleY, bins=intervalle, density=True, label='Echantillon')\n",
+    "plt.hist(sampleX + sampleY, bins=intervalle, density=True, label=\"Echantillon\")\n",
     "\n",
     "densite = stats.uniform(-1, 2).pdf\n",
-    "plt.plot(intervalle, densite(intervalle), label='Fonction densité')\n",
+    "plt.plot(intervalle, densite(intervalle), label=\"Fonction densité\")\n",
     "\n",
-    "plt.plot(intervalle, 1/4 * np.maximum(2 - np.abs(intervalle), 0), label='Fonction')\n",
+    "plt.plot(intervalle, 1 / 4 * np.maximum(2 - np.abs(intervalle), 0), label=\"Fonction\")\n",
     "plt.legend()"
    ]
   },
@@ -130,10 +130,22 @@
    "source": [
     "lam = 1\n",
     "nb_repl = 10000\n",
-    "sampleX, sampleY, sampleZ = np.random.exponential(lam, nb_repl), np.random.exponential(lam, nb_repl), np.random.exponential(lam, nb_repl)\n",
+    "sampleX, sampleY, sampleZ = (\n",
+    "    np.random.exponential(lam, nb_repl),\n",
+    "    np.random.exponential(lam, nb_repl),\n",
+    "    np.random.exponential(lam, nb_repl),\n",
+    ")\n",
     "intervalle = np.linspace(-5, 5, 100)\n",
-    "plt.hist(sampleX - sampleY/2, bins=intervalle, density=True, alpha=.7, label='Echantillon de X - Y/2')\n",
-    "plt.hist(sampleZ/2, bins=intervalle, density=True, alpha=.7, label='Echantillon de Z')\n",
+    "plt.hist(\n",
+    "    sampleX - sampleY / 2,\n",
+    "    bins=intervalle,\n",
+    "    density=True,\n",
+    "    alpha=0.7,\n",
+    "    label=\"Echantillon de X - Y/2\",\n",
+    ")\n",
+    "plt.hist(\n",
+    "    sampleZ / 2, bins=intervalle, density=True, alpha=0.7, label=\"Echantillon de Z\"\n",
+    ")\n",
     "plt.legend()"
    ]
   },
@@ -157,15 +169,17 @@
     }
    ],
    "source": [
-    "p = 1/2\n",
+    "p = 1 / 2\n",
     "nb_repl = 1000\n",
     "\n",
     "plt.figure(figsize=(18, 5))\n",
     "for i, k in enumerate([10, 100, 1000]):\n",
-    "    plt.subplot(1, 3, i+1)\n",
+    "    plt.subplot(1, 3, i + 1)\n",
     "    sample = np.random.binomial(k, p, nb_repl)\n",
     "    intervalle = np.linspace(np.min(sample), np.max(sample), 100)\n",
-    "    plt.hist(sample, bins=intervalle, density=True, label=f'Echantillon de X pour n={k}')\n",
+    "    plt.hist(\n",
+    "        sample, bins=intervalle, density=True, label=f\"Echantillon de X pour n={k}\"\n",
+    "    )\n",
     "    plt.legend()"
    ]
   },
@@ -179,7 +193,7 @@
    "outputs": [],
    "source": [
     "def sample_uniforme(N):\n",
-    "    return 2*np.random.rand(N) - 1"
+    "    return 2 * np.random.rand(N) - 1"
    ]
   },
   {
@@ -218,7 +232,7 @@
     "\n",
     "for _ in range(nb_lgn):\n",
     "    liste_Sn.append(np.mean(sample_uniforme(nb_repl)))\n",
-    "    \n",
+    "\n",
     "nb_bins = 100\n",
     "intervalles = np.linspace(np.min(liste_Sn), np.max(liste_Sn), nb_bins)\n",
     "plt.hist(liste_Sn, density=True, bins=intervalles)\n",
@@ -256,12 +270,14 @@
     "liste_Sn = []\n",
     "\n",
     "for _ in range(nb_lgn):\n",
-    "    liste_Sn.append(np.mean(np.sqrt(3*nb_repl) * np.tan(np.pi/2 * sample_uniforme(nb_repl))))\n",
+    "    liste_Sn.append(\n",
+    "        np.mean(np.sqrt(3 * nb_repl) * np.tan(np.pi / 2 * sample_uniforme(nb_repl)))\n",
+    "    )\n",
     "\n",
-    "#nb_bins = 100\n",
-    "#intervalles = np.linspace(np.min(liste_Sn), np.max(liste_Sn), nb_bins)\n",
-    "#plt.hist(liste_Sn, density=True, bins=intervalles)\n",
-    "#plt.show()\n",
+    "# nb_bins = 100\n",
+    "# intervalles = np.linspace(np.min(liste_Sn), np.max(liste_Sn), nb_bins)\n",
+    "# plt.hist(liste_Sn, density=True, bins=intervalles)\n",
+    "# plt.show()\n",
     "\n",
     "plt.figure()\n",
     "densite = stats.norm(scale=1).pdf\n",

L3/Statistiques/TP2.ipynb

@@ -9,11 +9,11 @@
    },
    "outputs": [],
    "source": [
-    "import numpy as np\n",
-    "import scipy.stats as stats\n",
-    "import scipy.special as sp\n",
     "import matplotlib.pyplot as plt\n",
-    "import scipy.optimize as opt"
+    "import numpy as np\n",
+    "import scipy.optimize as opt\n",
+    "import scipy.special as sp\n",
+    "import scipy.stats as stats"
    ]
   },
   {
@@ -27,7 +27,12 @@
    "source": [
     "def f(L, z):\n",
     "    x, y = L[0], L[1]\n",
-    "    return np.power(z*x, 2) + np.power(y/z, 2) - np.cos(2 * np.pi * x) - np.cos(2 * np.pi * y)"
+    "    return (\n",
+    "        np.power(z * x, 2)\n",
+    "        + np.power(y / z, 2)\n",
+    "        - np.cos(2 * np.pi * x)\n",
+    "        - np.cos(2 * np.pi * y)\n",
+    "    )"
    ]
   },
   {
@@ -123,17 +128,17 @@
    "source": [
     "plt.figure(figsize=(18, 5))\n",
     "for i, nb_repl in enumerate([100, 1000, 10000]):\n",
-    "    plt.subplot(1, 3, i+1)\n",
+    "    plt.subplot(1, 3, i + 1)\n",
     "    sample_X1 = np.random.normal(0, 1, nb_repl)\n",
     "    sample_X2 = np.random.normal(3, np.sqrt(5), nb_repl)\n",
-    "    sample_e = np.random.normal(0, np.sqrt(1/4), nb_repl)\n",
+    "    sample_e = np.random.normal(0, np.sqrt(1 / 4), nb_repl)\n",
     "    Y = 5 * sample_X1 - 4 * sample_X2 + 2 + sample_e\n",
     "\n",
     "    intervalle = np.linspace(np.min(Y), np.max(Y), 100)\n",
-    "    plt.hist(Y, bins=intervalle, density=True, label='Echantillon de Y')\n",
+    "    plt.hist(Y, bins=intervalle, density=True, label=\"Echantillon de Y\")\n",
     "\n",
     "    densite = stats.norm(-10, np.sqrt(105.25)).pdf\n",
-    "    plt.plot(intervalle, densite(intervalle), label='Fonction densité')\n",
+    "    plt.plot(intervalle, densite(intervalle), label=\"Fonction densité\")\n",
     "\n",
     "    plt.title(f\"Graphique de la somme de gaussiennes pour N={nb_repl}\")\n",
     "    plt.legend()"
@@ -151,8 +156,9 @@
     "def theta_hat(Y):\n",
     "    return np.mean(Y)\n",
     "\n",
+    "\n",
     "def sigma_hat(Y):\n",
-    "    return 1/nb_repl * np.sum(np.power(Y - theta_hat(Y), 2))"
+    "    return 1 / nb_repl * np.sum(np.power(Y - theta_hat(Y), 2))"
    ]
   },
   {
@@ -166,7 +172,11 @@
    "source": [
     "def log_likehood_gauss(X, Y):\n",
     "    theta, sigma_2 = X[0], X[1]\n",
-    "    return 1/2*np.log(2*np.pi) + 1/2*np.log(sigma_2) + 1/(2*nb_repl*sigma_2) * np.sum(np.power(Y - theta, 2))"
+    "    return (\n",
+    "        1 / 2 * np.log(2 * np.pi)\n",
+    "        + 1 / 2 * np.log(sigma_2)\n",
+    "        + 1 / (2 * nb_repl * sigma_2) * np.sum(np.power(Y - theta, 2))\n",
+    "    )"
    ]
   },
   {
@@ -191,9 +201,9 @@
     "nb_repl = 5000\n",
     "sample_X1 = np.random.normal(0, 1, nb_repl)\n",
     "sample_X2 = np.random.normal(3, np.sqrt(5), nb_repl)\n",
-    "sample_e = np.random.normal(0, np.sqrt(1/4), nb_repl)\n",
+    "sample_e = np.random.normal(0, np.sqrt(1 / 4), nb_repl)\n",
     "Y = 5 * sample_X1 - 4 * sample_X2 + 2 + sample_e\n",
-    "    \n",
+    "\n",
     "mk = {\"method\": \"BFGS\", \"args\": Y}\n",
     "res = opt.basinhopping(log_likehood_gauss, x0=(-1, 98.75), minimizer_kwargs=mk)\n",
     "print(res.x)\n",
@@ -211,12 +221,12 @@
    "outputs": [],
    "source": [
     "def simule(a, b, n):\n",
-    "    X = np.random.gamma(a, 1/b, n)\n",
+    "    X = np.random.gamma(a, 1 / b, n)\n",
     "    intervalle = np.linspace(0, np.max(X), 100)\n",
-    "    plt.hist(X, bins=intervalle, density=True, label='Echantillon de X')\n",
+    "    plt.hist(X, bins=intervalle, density=True, label=\"Echantillon de X\")\n",
     "\n",
-    "    densite = stats.gamma.pdf(intervalle, a, 0, 1/b)\n",
-    "    plt.plot(intervalle, densite, label='Fonction densité Gamma(2, 1)')\n",
+    "    densite = stats.gamma.pdf(intervalle, a, 0, 1 / b)\n",
+    "    plt.plot(intervalle, densite, label=\"Fonction densité Gamma(2, 1)\")\n",
     "    plt.legend()"
    ]
   },
@@ -254,8 +264,13 @@
    "source": [
     "def log_likehood_gamma(X, sample):\n",
     "    a, b = X[0], X[1]\n",
-    "    n = len(sample) \n",
-    "    return -n*a*np.log(b) + n * np.log(sp.gamma(a)) - (a-1) * np.sum(np.log(sample)) + b * np.sum(sample)"
+    "    n = len(sample)\n",
+    "    return (\n",
+    "        -n * a * np.log(b)\n",
+    "        + n * np.log(sp.gamma(a))\n",
+    "        - (a - 1) * np.sum(np.log(sample))\n",
+    "        + b * np.sum(sample)\n",
+    "    )"
    ]
   },
   {
@@ -296,7 +311,7 @@
     "nb_repl = 1000\n",
     "a, b = 2, 1\n",
     "\n",
-    "sample = np.random.gamma(a, 1/b, nb_repl)\n",
+    "sample = np.random.gamma(a, 1 / b, nb_repl)\n",
     "mk = {\"method\": \"BFGS\", \"args\": sample}\n",
     "res = opt.basinhopping(log_likehood_gamma, x0=(1, 1), minimizer_kwargs=mk)\n",
     "print(res.x)"

M1/Data Analysis/TP1/TP1.rmd

@@ -0,0 +1,120 @@
+```{r}
+setwd('/Users/arthurdanjou/Workspace/studies/M1/Data Analysis/TP1')
+```
+
+# Part 1 - Analysis of the data
+
+```{r}
+x <- c(1, 2, 3, 4)
+mean(x)
+
+y <- x - mean(x)
+mean(y)
+t(y)
+
+sum(y^2)
+```
+
+```{r}
+T <- read.table("Temperature Data.csv", header = TRUE, sep = ";", dec = ",", row.names = 1)
+n <- nrow(T)
+
+g <- colMeans(T)
+Y <- as.matrix(T - rep(1, n) %*% t(g))
+
+Dp <- diag(1 / n, n)
+
+V <- t(Y) %*% Dp %*% Y
+
+eigen_values <- eigen(V)$values
+vectors <- eigen(V)$vectors
+total_inertia <- sum(eigen_values)
+inertia_one <- max(eigen_values) / sum(eigen_values)
+inertia_plan <- (eigen_values[1] + eigen_values[2]) / sum(eigen_values)
+
+P <- Y %*% vectors[, 1:2]
+
+plot(P, pch = 19, xlab = "PC1", ylab = "PC2")
+text(P, rownames(T), cex = 0.7, pos = 3)
+axis(1, -10:10, pos = 0, labels = F)
+axis(2, -5:5, pos = 0, labels = F)
+```
+
+```{r}
+France <- P %*% matrix(c(0, -1, 1, 0), 2, 2)
+plot(France, pch = 19, xlab = "PC1", ylab = "PC2")
+text(France, rownames(T), cex = 0.7, pos = 3)
+axis(1, -10:10, pos = 0, labels = F)
+axis(2, -5:5, pos = 0, labels = F)
+```
+```{r}
+results <- matrix(NA, nrow = n, ncol = 2)
+colnames(results) <- c("Quality of Representation (%)", "Contribution to Inertia (%)")
+rownames(results) <- rownames(T)
+
+for (i in 1:n) {
+  yi <- Y[i,]
+  norm_yi <- sqrt(sum(yi^2))
+  qlt <- sum((yi %*% vectors[, 1:2])^2) / norm_yi^2 * 100
+  ctr <- (P[i, 1]^2 / eigen_values[1]) / n * 100
+  results[i,] <- c(qlt, ctr)
+}
+
+# Add the total row
+results <- rbind(results, colSums(results))
+rownames(results)[n + 1] <- "Total"
+
+results
+```
+
+# Part 2 - PCA with FactoMineR
+
+```{r}
+library(FactoMineR)
+T <- read.csv("Temperature Data.csv", header = TRUE, sep = ";", dec = ",", row.names = 1)
+summary(T)
+```
+
+```{r}
+T.pca <- PCA(T, graph = F)
+plot.PCA(T.pca, axes = c(1, 2), habillage = 1, choix = "ind")
+plot.PCA(T.pca, axes = c(1, 2), habillage = 1, choix = "var")
+
+print("Var coords")
+round(T.pca$var$coord[, 1:2], 2)
+
+print("Eigen values")
+round(T.pca$eig, 2)
+
+print("Ind dis")
+round(T.pca$ind$dist, 2)
+
+print("Ind contrib")
+round(T.pca$ind$contrib[, 1:2], 2)
+
+print("Var contrib")
+round(T.pca$var$contrib[, 1:2], 2)
+```
+
+## We add new values
+```{r}
+Amiens <- c(3.1, 3.8, 6.7, 9.5, 12.8, 15.8, 17.6, 17.6, 15.5, 11.1, 6.8, 4.2)
+T <- rbind(T, Amiens)
+row.names(T)[16] <- "Amiens"
+
+Moscow <- c(-9.2, -8, -2.5, 5.9, 12.8, 16.8, 18.4, 16.6, 11.2, 4.9, -1.5, -6.2)
+T <- rbind(T, Moscow)
+row.names(T)[17] <- "Moscow"
+
+Marrakech <- c(11.3, 12.8, 15.8, 18.1, 21.2, 24.7, 28.6, 28.6, 25, 20.9, 15.9, 12.1)
+T <- rbind(T, Marrakech)
+row.names(T)[18] <- "Marrakech"
+```
+
+## We redo the PCA
+
+```{r}
+T.pca <- PCA(T, ind.sup = 16:18, graph = F)
+plot.PCA(T.pca, axes = c(1, 2), habillage = 1, choix = "ind")
+plot.PCA(T.pca, axes = c(1, 2), habillage = 1, choix = "var")
+```

M1/Data Analysis/TP1/Temperature Data.csv

@@ -0,0 +1,16 @@
+Ville;janv;fev;mars;avril;mai;juin;juil;aout;sept;oct;nov;dec
+Bordeaux;5,6;6,6;10,3;12,8;15,8;19,3;20,9;21,0;18,6;13,8;9,1;6,2
+Brest;6,1;5,8;7,8;9,2;11,6;14,4;15,6;16,0;14,7;12,0;9,0;7,0
+Clermont-Ferrand;2,6;3,7;7,5;10,3;13,8;17,3;19,4;19,1;16,2;11,2;6,6;3,6
+Grenoble;1,5;3,2;7,7;10,6;14,5;17,8;20,1;19,5;16,7;11,4;6,5;2,3
+Lille;2,4;2,9;6,0;8,9;12,4;15,3;17,1;17,1;14,7;10,4;6,1;3,5
+Lyon;2,1;3,3;7,7;10,9;14,9;18,5;20,7;20,1;16,9;11,4;6,7;3,1
+Marseille;5,5;6,6;10,0;13,0;16,8;20,8;23,3;22,8;19,9;15,0;10,2;6,9
+Montpellier;5,6;6,7;9,9;12,8;16,2;20,1;22,7;22,3;19,3;14,6;10,0;6,5
+Nantes;5,0;5,3;8,4;10,8;13,9;17,2;18,8;18,6;16,4;12,2;8,2;5,5
+Nice;7,5;8,5;10,8;13,3;16,7;20,1;22,7;22,5;20,3;16,0;11,5;8,2
+Paris;3,4;4,1;7,6;10,7;14,3;17,5;19,1;18,7;16,0;11,4;7,1;4,3
+Rennes;4,8;5,3;7,9;10,1;13,1;16,2;17,9;17,8;15,7;11,6;7,8;5,4
+Strasbourg;0,4;1,5;5,6;9,8;14,0;17,2;19,0;18,3;15,1;9,5;4,9;1,3
+Toulouse;4,7;5,6;9,2;11,6;14,9;18,7;20,9;20,9;18,3;13,3;8,6;5,5
+Vichy;2,4;3,4;7,1;9,9;13,6;17,1;19,3;18,8;16,0;11,0;6,6;3,4

M1/General Linear Models/Projet/GLM Code - DANJOU & DUROUSSEAU.rmd

@@ -0,0 +1,512 @@
+---
+title: "Generalized Linear Models - Project by Arthur DANJOU"
+always_allow_html: true
+output:
+html_document:
+toc: true
+toc_depth: 4
+fig_caption: true
+---
+
+## Data Analysis
+
+```{r}
+setwd('/Users/arthurdanjou/Workspace/studies/M1/General Linear Models/Projet')
+```
+
+```{r}
+library(MASS)
+library(AER)
+library(rmarkdown)
+library(car)
+library(corrplot)
+library(carData)
+library(ggfortify)
+library(ggplot2)
+library(gridExtra)
+library(caret)
+```
+
+### Data Preprocessing
+```{r}
+data <- read.csv("./projet.csv", header = TRUE, sep = ",", dec = ".")
+
+# Factors
+data$saison <- as.factor(data$saison)
+data$mois <- as.factor(data$mois)
+data$jour_mois <- as.factor(data$jour_mois)
+data$jour_semaine <- as.factor(data$jour_semaine)
+data$horaire <- as.factor(data$horaire)
+data$jour_travail <- as.factor(data$jour_travail)
+data$vacances <- as.factor(data$vacances)
+data$meteo <- as.factor(data$meteo)
+
+# Quantitative variables
+data$humidite_sqrt <- sqrt(data$humidite)
+data$humidite_square <- data$humidite^2
+
+data$temperature1_square <- data$temperature1^2
+data$temperature2_square <- data$temperature2^2
+
+data$vent_square <- data$vent^2
+data$vent_sqrt <- sqrt(data$vent)
+
+# Remove obs column
+rownames(data) <- data$obs
+data <- data[, -1]
+paged_table(data)
+```
+
+```{r}
+colSums(is.na(data))
+sum(duplicated(data))
+```
+
+```{r}
+str(data)
+summary(data)
+```
+
+### Study of the Quantitative Variables
+
+#### Distribution of Variables
+
+```{r}
+plot_velos <- ggplot(data, aes(x = velos)) +
+  geom_histogram(bins = 25, fill = "blue") +
+  labs(title = "Distribution du nombre de vélos loués", x = "Nombre de locations de vélos")
+
+plot_temperature1 <- ggplot(data, aes(x = temperature1)) +
+  geom_histogram(bins = 30, fill = "green") +
+  labs(title = "Distribution de la température1", x = "Température moyenne mesuré (°C)")
+
+plot_temperature2 <- ggplot(data, aes(x = temperature2)) +
+  geom_histogram(bins = 30, fill = "green") +
+  labs(title = "Distribution de la température2", x = "Température moyenne ressentie (°C)")
+
+plot_humidite <- ggplot(data, aes(x = humidite)) +
+  geom_histogram(bins = 30, fill = "green") +
+  labs(title = "Distribution de la humidité", x = "Pourcentage d'humidité")
+
+plot_vent <- ggplot(data, aes(x = vent)) +
+  geom_histogram(bins = 30, fill = "green") +
+  labs(title = "Distribution de la vent", x = "Vitesse du vent (Km/h)")
+
+grid.arrange(plot_velos, plot_temperature1, plot_temperature2, plot_humidite, plot_vent, ncol = 3)
+```
+
+#### Correlation between Quantitatives Variables
+
+```{r}
+#detach(package:arm) # If error, uncomment this line due to duplicate function 'corrplot'
+corr_matrix <- cor(data[, sapply(data, is.numeric)])
+corrplot(corr_matrix, type = "lower", tl.col = "black", tl.srt = 45)
+pairs(data[, sapply(data, is.numeric)])
+cor.test(data$temperature1, data$temperature2)
+```
+
+### Study of the Qualitative Variables
+
+```{r}
+plot_saison <- ggplot(data, aes(x = saison, y = velos)) +
+  geom_boxplot(fill = "lightblue") +
+  labs(title = "Nombre de vélos par saison", x = "Saison", y = "Nombre de vélos loués")
+
+plot_jour_semaine <- ggplot(data, aes(x = jour_semaine, y = velos)) +
+  geom_boxplot(fill = "lightblue") +
+  labs(title = "Nombre de vélos par jour de la semaine", x = "Jour de la semaine", y = "Nombre de vélos loués")
+
+plot_mois <- ggplot(data, aes(x = mois, y = velos)) +
+  geom_boxplot(fill = "lightblue") +
+  labs(title = "Nombre de vélos par mois de l'année", x = "Mois de l'année", y = "Nombre de vélos loués")
+
+plot_jour_mois <- ggplot(data, aes(x = jour_mois, y = velos)) +
+  geom_boxplot(fill = "lightblue") +
+  labs(title = "Nombre de vélos par jour du mois", x = "Jour du mois", y = "Nombre de vélos loués")
+
+plot_horaire <- ggplot(data, aes(x = horaire, y = velos)) +
+  geom_boxplot(fill = "lightblue") +
+  labs(title = "Nombre de vélos par horaire de la journée", x = "Horaire de la journée", y = "Nombre de vélos loués")
+
+plot_jour_travail <- ggplot(data, aes(x = jour_travail, y = velos)) +
+  geom_boxplot(fill = "lightblue") +
+  labs(title = "Nombre de vélos par jour travaillé", x = "Jour travaillé", y = "Nombre de vélos loués")
+
+plot_vacances <- ggplot(data, aes(x = vacances, y = velos)) +
+  geom_boxplot(fill = "lightblue") +
+  labs(title = "Nombre de vélos par vacances", x = "Vacances", y = "Nombre de vélos loués")
+
+plot_meteo <- ggplot(data, aes(x = meteo, y = velos)) +
+  geom_boxplot(fill = "lightblue") +
+  labs(title = "Nombre de vélos par météo", x = "Météo", y = "Nombre de vélos loués")
+
+grid.arrange(plot_horaire, plot_jour_semaine, plot_jour_mois, plot_mois, plot_saison, plot_jour_travail, plot_vacances, plot_meteo, ncol = 3)
+```
+
+```{r}
+chisq.test(data$mois, data$saison)
+chisq.test(data$meteo, data$saison)
+chisq.test(data$meteo, data$mois)
+```
+
+### Outliers Detection
+
+```{r}
+boxplot_velos <- ggplot(data, aes(x = "", y = velos)) +
+  geom_boxplot(fill = "lightblue") +
+  labs(title = "Boxplot de vélos", y = "Nombre de vélos")
+
+boxplot_temperature1 <- ggplot(data, aes(x = "", y = temperature1)) +
+  geom_boxplot(fill = "lightblue") +
+  labs(title = "Boxplot de température1", y = "Température moyenne mesuré (°C)")
+
+boxplot_temperature1_sq <- ggplot(data, aes(x = "", y = temperature1_square)) +
+  geom_boxplot(fill = "lightblue") +
+  labs(title = "Boxplot de température1^2", y = "Température moyenne mesuré (°C^2)")
+
+boxplot_temperature2 <- ggplot(data, aes(x = "", y = temperature2)) +
+  geom_boxplot(fill = "lightblue") +
+  labs(title = "Boxplot de température2", y = "Température moyenne ressentie (°C)")
+
+boxplot_temperature2_sq <- ggplot(data, aes(x = "", y = temperature2_square)) +
+  geom_boxplot(fill = "lightblue") +
+  labs(title = "Boxplot de température2^2", y = "Température moyenne ressentie (°C^2)")
+
+boxplot_humidite <- ggplot(data, aes(x = "", y = humidite)) +
+  geom_boxplot(fill = "lightblue") +
+  labs(title = "Boxplot de humidité", y = "Pourcentage d'humidité")
+
+boxplot_humidite_sqrt <- ggplot(data, aes(x = "", y = humidite_sqrt)) +
+  geom_boxplot(fill = "lightblue") +
+  labs(title = "Boxplot de sqrt(humidité)", y = "Pourcentage d'humidité (sqrt(%))")
+
+boxplot_humidite_square <- ggplot(data, aes(x = "", y = humidite_square)) +
+  geom_boxplot(fill = "lightblue") +
+  labs(title = "Boxplot de humidité^2", y = "Pourcentage d'humidité (%^2)")
+
+boxplot_vent <- ggplot(data, aes(x = "", y = vent)) +
+  geom_boxplot(fill = "lightblue") +
+  labs(title = "Boxplot de vent", y = "Vitesse du vent (Km/h)")
+
+boxplot_vent_sqrt <- ggplot(data, aes(x = "", y = vent_sqrt)) +
+  geom_boxplot(fill = "lightblue") +
+  labs(title = "Boxplot de sqrt(vent)", y = "Vitesse du vent sqrt(Km/h)")
+
+boxplot_vent_square <- ggplot(data, aes(x = "", y = vent_square)) +
+  geom_boxplot(fill = "lightblue") +
+  labs(title = "Boxplot de vent^2", y = "Vitesse du vent (Km/h)^2")
+
+grid.arrange(boxplot_velos, boxplot_temperature1, boxplot_temperature1_sq, boxplot_temperature2, boxplot_temperature2_sq, boxplot_humidite, boxplot_humidite_sqrt, boxplot_humidite_square, boxplot_vent, boxplot_vent_sqrt, boxplot_vent_square, ncol = 4)
+```
+
+```{r}
+length_data <- nrow(data)
+numeric_vars <- sapply(data, is.numeric)
+total_outliers <- 0
+
+for (var in names(data)[numeric_vars]) {
+  data_outlier <- data[[var]]
+  Q1 <- quantile(data_outlier, 0.25)
+  Q3 <- quantile(data_outlier, 0.75)
+  IQR <- Q3 - Q1
+
+  lower_limit <- Q1 - 1.5 * IQR
+  upper_limit <- Q3 + 1.5 * IQR
+
+  outliers <- data[data_outlier < lower_limit | data_outlier > upper_limit,]
+  cat("Number of outliers for the variable", var, ":", nrow(outliers), "\n")
+  data <- data[data_outlier >= lower_limit & data_outlier <= upper_limit,]
+}
+
+cat("Number of outliers removed :", length_data - nrow(data), "\n")
+cat("Data length after removing outliers :", nrow(data), "\n")
+```
+
+## Model Creation and Comparison
+
+### Data Split
+
+```{r}
+set.seed(123)
+data_split <- rsample::initial_split(data, prop = 0.8)
+data_train <- rsample::training(data_split)
+data_test <- rsample::testing(data_split)
+```
+
+### Choice of the Distribution *vélos*
+
+```{r}
+model_poisson <- glm(velos ~ ., family = poisson, data = data_train)
+model_nb <- glm.nb(velos ~ ., data = data_train)
+model_gaussian <- glm(velos ~ ., family = gaussian, data = data_train)
+t(AIC(model_poisson, model_nb, model_gaussian)[2])
+
+dispersiontest(model_poisson)
+
+mean_velos <- mean(data_train$velos)
+var_velos <- var(data_train$velos)
+cat("Mean :", mean_velos, "Variance :", var_velos, "\n")
+```
+
+### Model Selection
+
+```{r}
+model_full_quantitative <- glm.nb(
+  velos ~ vent +
+    vent_square +
+    vent_sqrt +
+
+    humidite +
+    humidite_square +
+    humidite_sqrt +
+
+    temperature1_square +
+    temperature1 +
+
+    temperature2 +
+    temperature2_square
+  , data = data_train)
+summary(model_full_quantitative)
+```
+
+```{r}
+anova(model_full_quantitative)
+```
+
+```{r}
+model_quantitative_quali <- glm.nb(
+  velos ~
+    vent +
+      vent_square +
+      vent_sqrt +
+      humidite +
+      humidite_square +
+      humidite_sqrt +
+      temperature1 +
+      temperature1_square +
+
+      horaire +
+      saison +
+      meteo +
+      mois +
+      vacances +
+      jour_travail +
+      jour_semaine +
+      jour_mois
+  , data = data_train)
+summary(model_quantitative_quali)
+```
+
+```{r}
+anova(model_quantitative_quali)
+```
+
+```{r}
+model_quanti_quali_final <- glm.nb(
+  velos ~
+    vent +
+      vent_square + #
+      humidite +
+      humidite_square +
+      humidite_sqrt + #
+      temperature1 +
+      temperature1_square +
+
+      horaire +
+      saison +
+      meteo +
+      mois +
+      vacances
+  , data = data_train)
+summary(model_quanti_quali_final)
+```
+
+```{r}
+model_0 <- glm.nb(velos ~ 1, data = data_train)
+model_forward <- stepAIC(
+  model_0,
+  vélos ~ vent +
+    humidite +
+    humidite_square +
+    temperature1 +
+    temperature1_square +
+
+    horaire +
+    saison +
+    meteo +
+    mois +
+    vacances,
+  data = data_train,
+  trace = FALSE,
+  direction = "forward"
+)
+model_backward <- stepAIC(
+  model_quanti_quali_final,
+  ~1,
+  trace = FALSE,
+  direction = "backward"
+)
+model_both <- stepAIC(
+  model_0,
+  vélos ~ vent +
+    humidite +
+    humidite_square +
+    temperature1 +
+    temperature1_square +
+
+    horaire +
+    saison +
+    meteo +
+    mois +
+    vacances,
+  data = data_train,
+  trace = FALSE,
+  direction = "both"
+)
+AIC(model_forward, model_both, model_backward)
+summary(model_forward)
+```
+
+```{r}
+model_final_without_interaction <- glm.nb(
+  velos ~ horaire +
+    mois +
+    meteo +
+    temperature1 +
+    saison +
+    temperature1_square +
+    humidite_square +
+    vacances +
+    humidite +
+    vent
+  , data = data_train)
+summary(model_final_without_interaction)
+```
+
+### Final Model
+
+#### Choice and Validation of the Model
+
+```{r}
+model_final <- glm.nb(
+  velos ~ horaire +
+    mois +
+    meteo +
+    temperature1 +
+    saison +
+    temperature1_square +
+    humidite_square +
+    vacances +
+    humidite +
+    vent +
+
+    horaire:temperature1 +
+    temperature1_square:mois
+  , data = data_train
+)
+summary(model_final)
+```
+
+```{r}
+anova(model_final, test = "Chisq")
+```
+
+```{r}
+lrtest(model_final, model_final_without_interaction)
+```
+
+```{r}
+dispersion_ratio <- sum(residuals(model_final, type = "pearson")^2) / df.residual(model_final)
+print(paste("Dispersion Ratio:", round(dispersion_ratio, 2)))
+
+hist(residuals(model_final, type = "deviance"), breaks = 30, freq = FALSE, col = "lightblue", main = "Histogram of Deviance Residuals")
+x <- seq(-5, 5, length = 100)
+curve(dnorm(x), col = "darkblue", lwd = 2, add = TRUE)
+
+autoplot(model_final, 1:4)
+```
+
+```{r}
+library(arm)
+binnedplot(fitted(model_final), residuals(model_final, type = "deviance"), col.int = "blue", col.pts = 2)
+```
+
+## Performance and Limitations of the Final Model
+
+### Predictions and *Mean Square Error*
+
+```{r}
+data_test$predictions <- predict(model_final, newdata = data_test, type = "response")
+data_train$predictions <- predict(model_final, newdata = data_train, type = "response")
+
+predictions_ci <- predict(
+  model_final,
+  newdata = data_test,
+  type = "link",
+  se.fit = TRUE
+)
+
+data_test$lwr <- exp(predictions_ci$fit - 1.96 * predictions_ci$se.fit)
+data_test$upr <- exp(predictions_ci$fit + 1.96 * predictions_ci$se.fit)
+
+MSE <- mean((data_test$velos - data_test$predictions)^2)
+cat("MSE :", MSE, "\n")
+cat("RMSE train :", sqrt(mean((data_train$velos - data_train$predictions)^2)), "\n")
+cat('RMSE :', sqrt(MSE), '\n')
+```
+
+### Evaluation of Model Performance
+
+```{r}
+bounds <- c(200, 650)
+
+cat("Observations vs Prédictions\n")
+cat(nrow(data_test[data_test$velos < bounds[1],]), "vs", sum(data_test$predictions < bounds[1]), "\n")
+cat(nrow(data_test[data_test$velos > bounds[1] & data_test$velos < bounds[2],]), "vs", sum(data_test$predictions > bounds[1] & data_test$predictions < bounds[2]), "\n")
+cat(nrow(data_test[data_test$velos > bounds[2],]), "vs", sum(data_test$predictions > bounds[2]), "\n")
+cat('\n')
+
+categories <- c(0, bounds, Inf)
+categories_label <- c("Low", "Mid", "High")
+
+data_test$velos_cat <- cut(data_test$velos,
+                           breaks = categories,
+                           labels = categories_label,
+                           include.lowest = TRUE)
+data_test$predictions_cat <- cut(data_test$predictions,
+                                 breaks = categories,
+                                 labels = categories_label,
+                                 include.lowest = TRUE)
+conf_matrix <- confusionMatrix(data_test$velos_cat, data_test$predictions_cat)
+conf_matrix
+```
+
+```{r}
+ggplot(data_test, aes(x = velos, y = predictions)) +
+  geom_point(color = "blue", alpha = 0.6, size = 2) +
+  geom_abline(slope = 1, intercept = 0, color = "red", linetype = "dashed") +
+  geom_ribbon(aes(ymin = lwr, ymax = upr), alpha = 0.2, fill = "grey") +
+  labs(
+    title = "Comparison of Observed and Predicted Bikes",
+    x = "Number of Observed Bikes",
+    y = "Number of Predicted Bikes"
+  ) +
+  theme_minimal()
+
+ggplot(data_test, aes(x = velos_cat, fill = predictions_cat)) +
+  geom_bar(position = "dodge") +
+  labs(title = "Predictions vs Observations (by categories)",
+       x = "Observed categories", y = "Number of predictions")
+
+df_plot <- data.frame(observed = data_test$velos, predicted = data_test$predictions)
+
+# Créer l'histogramme avec la courbe de densité
+ggplot(df_plot, aes(x = observed)) +
+  geom_histogram(aes(y = ..density..), binwidth = 50, fill = "lightblue", color = "black", alpha = 0.7) + # Histogramme des données observées
+  geom_density(aes(x = predicted), color = "red", size = 1) + # Courbe de densité des valeurs prédites
+  labs(title = "Observed distribution vs. Predicted distribution",
+       x = "Number of vélos",
+       y = "Density") +
+  theme_bw()
+
+```

M1/General Linear Models/TP1-bis/TP1.Rmd

@@ -0,0 +1,139 @@
+```{r}
+setwd('/Users/arthurdanjou/Workspace/studies/M1/General Linear Models/TP1-bis')
+
+library(tidyverse)
+options(scipen = 999, digits = 5)
+```
+```{r}
+data <- read.csv("data01.csv", header = TRUE, sep = ",", dec = ".")
+head(data, 20)
+```
+
+```{r}
+ggplot(data, aes(x = cholesterol)) +
+  geom_histogram(binwidth = 5, color = "black", fill = "gray80") +
+  labs(x = "Cholesterol", y = "Frequency", title = "Histogram of cholesterol") +
+  theme_bw(14)
+
+ggplot(data, aes(x = poids)) +
+  geom_histogram(binwidth = 2.5, color = "black", fill = "gray80") +
+  labs(x = "Poids", y = "Frequency", title = "Histogram of Poids") +
+  theme_bw(14)
+
+ggplot(aes(y = cholesterol, x = poids), data = data) +
+  geom_point() +
+  labs(y = "Cholesterol (y)", x = "Poids, kg (x)", title = "Scatter plot of cholesterol and poids") +
+  theme_bw(14)
+```
+
+# OLSE
+```{r}
+x <- data[, "poids"]
+y <- data[, "cholesterol"]
+Sxy <- sum((x - mean(x)) * y)
+Sxx <- sum((x - mean(x))^2)
+
+beta1 <- Sxy / Sxx
+beta0 <- mean(y) - beta1 * mean(x)
+
+c(beta0, beta1)
+```
+
+Final Equation: y = 18.4470 + 2.0523 * x
+
+```{r}
+X <- cbind(1, x)
+
+colnames(X) <- NULL
+X_t_X <- t(X) %*% X
+inv_X_t_x <- solve(X_t_X)
+betas <- inv_X_t_x %*% t(X) %*% y
+betas
+```
+```{r}
+model <- lm(data, formula = cholesterol ~ poids)
+summary(model)
+coef(model)
+```
+```{r}
+data <- data %>%
+  mutate(yhat = beta0 + beta1 * poids) %>%
+  mutate(residuals = cholesterol - yhat)
+
+data
+
+ggplot(data, aes(x = poids, y = cholesterol)) +
+  geom_point(size = 2, shape = 21, fill = "blue", color = "cyan") +
+  geom_line(aes(y = yhat), color = "blue") +
+  labs(x = "Poids", y = "Cholesterol", title = "OLS Regression Line") +
+  theme_bw(14)
+```
+```{r}
+mean(data[, "cholesterol"])
+mean(data[, "yhat"])
+mean(data[, "residuals"]) %>% round(10)
+cov(data[, "residuals"], data[, "poids"]) %>% round(10)
+(RSS <- sum((data[, "residuals"])^2))
+(TSS <- sum((y - mean(y))^2))
+TSS - beta1 * Sxy
+```
+
+```{r}
+dof <- nrow(data) - 2
+
+sigma_hat_2 <- RSS / dof
+
+cov_beta <- sigma_hat_2 * inv_X_t_x
+var_beta <- diag(cov_beta)
+std_beta <- sqrt(var_beta)
+
+sigma(model)^2
+vcov(model)
+```
+
+
+# Hypothesis Testing
+
+```{r}
+(t_beta <- beta1 / std_beta[2])
+qt(0.975, dof)
+2 * pt(abs(t_beta), dof, lower.tail = FALSE)
+summary(model)
+```
+```{r}
+MSS <- (TSS - RSS)
+(F <- MSS / (RSS / dof))
+qf(0.95, 1, dof)
+pf(F, 1, dof, lower.tail = FALSE)
+anova(model)
+```
+
+# Confidence Interval
+```{r}
+(CI_beta1 <- c(beta1 - qt(0.97, dof) * std_beta[2], beta1 + qt(0.97, dof) * std_beta[2]))
+confint(model, 0.95)
+
+t <- qt(0.975, dof)
+sigma_hat <- sigma(model)
+n <- nrow(data)
+
+data <- data %>%
+  mutate(error = t *
+    sigma_hat *
+    sqrt(1 / n + (poids - mean(poids))^2 / RSS)) %>%
+  mutate(conf.low = yhat - error, conf.high = yhat + error, error = NULL)
+
+ggplot(data, aes(x = poids, y = cholesterol)) +
+  geom_ribbon(aes(ymin = conf.low, ymax = conf.high), alpha = 0.3, fill = "blue") +
+  geom_point(size = 2, shape = 21, fill = "blue", color = "cyan") +
+  geom_line(aes(y = yhat), color = "blue") +
+  labs(x = "Poids", y = "Cholesterol", title = "OLS Regression Line") +
+  theme_bw(14)
+```
+
+# R^2
+```{r}
+(R2 <- MSS / TSS)
+summary(model)$r.squared
+cor(data[, "cholesterol"], data[, "poids"])^2
+```

M1/General Linear Models/TP1-bis/data01.csv

@@ -0,0 +1,51 @@
+id,cholesterol,poids
+1,144.47452579195235,61.2
+2,145.88924868817446,62.6
+3,161.1126037995184,69.9
+4,155.4458581667524,63.8
+5,147.97655520732974,64
+6,170.24615865999974,70.5
+7,144.19706954005656,65.4
+8,140.1067951922945,58.3
+9,142.7466793355334,60.7
+10,145.2692979993652,61.7
+11,160.3640967819068,68.5
+12,148.56479095579394,65
+13,149.76055898423206,65.1
+14,143.85346030579532,63.9
+15,137.88860216547474,61.2
+16,164.79575052668758,70.8
+17,154.49767048200715,65.5
+18,131.4504444444691,55.5
+19,158.60793029776818,66.4
+20,154.20805689206188,61.6
+21,136.4149514835298,59.1
+22,134.5904701014675,62.6
+23,144.2563545892844,59.3
+24,138.22197617664875,60.5
+25,139.21587117755206,60.9
+26,138.70662904163586,56.6
+27,153.73921419517316,66.9
+28,143.2077515962295,64.1
+29,139.1754465872936,58.8
+30,158.02566076295264,68.6
+31,151.67509002312616,65.2
+32,147.4035408260477,62.3
+33,153.80002424297288,67.1
+34,158.72992406100167,67.1
+35,153.92208543890675,66.8
+36,155.54678399213427,66.3
+37,158.2201910034931,65.8
+38,149.64656232873804,63.2
+39,143.75436129736758,62.2
+40,150.4910110335996,61.9
+41,147.0277746100402,60.7
+42,148.96429207047277,62.6
+43,138.37451986964854,58.3
+44,163.40504312344743,72.3
+45,165.13133732815768,68.4
+46,135.39612367787572,58.9
+47,155.49199962327577,61.8
+48,151.67314985744744,61.6
+49,153.49019996627314,66.7
+50,142.15508998013192,63.1

M1/General Linear Models/TP1/TP1.Rmd

@@ -0,0 +1,77 @@
+```{r}
+setwd('/Users/arthurdanjou/Workspace/studies/M1/General Linear Models/TP1')
+```
+
+```{r}
+library(rmarkdown)
+health <- read.table("./health.txt", header = TRUE, sep = " ", dec = ".")
+paged_table(health)
+```
+
+```{r}
+Health <- health[2:5]
+
+library(dplyr)
+library(corrplot)
+correlation_matrix <- cor(Health)
+corrplot(correlation_matrix, order = 'hclust', addrect = 3)
+```
+
+```{r}
+model <- lm(y ~ ., data = Health)
+
+coefficients(model)
+summary(model)
+```
+
+```{r}
+library(ggfortify)
+library(car)
+autoplot(model, 1:3)
+```
+
+The points are not well distributed around 0 -> [P1] is not verified
+The points are not well distributed around 1 -> [P2] is not verified
+The QQPlot is aligned with the line y = x, so it is globally gaussian -> [P4] is verified
+
+```{r}
+set.seed(0)
+durbinWatsonTest(model)
+```
+
+The p-value is 0.58 > 0.05 -> We do not reject H0 so the residuals are not auto-correlated -> [P3] is verified
+
+```{r}
+library(GGally)
+ggpairs(Health, progress = F)
+```
+
+We observe that the variable age is correlated with the variable y. There is a quadratic relation between both variables.
+
+```{r}
+Health2 <- Health
+Health2$age_sq <- Health2$age^2
+Health2 <- Health2[1:24,]
+
+model2 <- lm(y ~ ., data = Health2)
+
+summary(model2)
+coefficients(model2)
+```
+
+```{r}
+library(ggfortify)
+library(car)
+autoplot(model2, 1:4)
+```
+
+The points are well distributed around 0 -> [P1] is verified
+The points are not well distributed around 1 -> [P2] is verified
+The QQPlot is aligned with the line y = x, so it is gaussian -> [P4] is verified
+
+```{r}
+set.seed(0)
+durbinWatsonTest(model2)
+```
+
+The p-value is 0.294 > 0.05 -> We do not reject H0 so the residuals are not auto-correlated -> [P3] is verified

M1/General Linear Models/TP1/health.txt

@@ -0,0 +1,26 @@
+"Id" "y" "age" "tri" "chol"
+"1" 0.344165525138049 61.3710178481415 255.998603752814 174.725536967162
+"2" 0.468648478326459 70.0093143060803 303.203193042427 191.830689532217
+"3" 0.0114155523307995 20.0903518591076 469.998112767935 126.269967628177
+"4" 0.472875443347101 71.2420938722789 146.105958395638 211.434927976225
+"5" 0 20.0899018836208 221.786231906153 240.876589370891
+"6" 0.143997241336945 43.2352053862996 266.090678572655 137.168468555901
+"7" 0.0414102111478797 25.8429238037206 372.907817093655 227.054411582649
+"8" 0.113811893132696 41.4695196016692 131.169532104395 131.447072112933
+"9" 0.109292366261165 35.7887735008262 430.398655338213 213.031274722889
+"10" 0.137468875629733 41.5359775861725 213.798411563039 248.683155018371
+"11" 0.0532629899999104 32.2978379554115 121.814481257461 216.917818398215
+"12" 0.353328774446386 61.3454213505611 407.593103558756 125.090295937844
+"13" 0.32693962726726 58.9427325245924 310.99092704244 234.297853410244
+"14" 0.160669457776164 45.8133233059198 146.624271371402 179.472973288503
+"15" 0.513130027249664 72.5317458156496 388.182279183529 179.566718712449
+"16" 0.617920854597292 80.2682227501646 227.86060355138 171.406586996745
+"17" 0.205049999385919 48.5804966441356 270.10274540633 216.100836060941
+"18" 0.0125951861990601 23.7895587598905 173.06959128473 246.627336950041
+"19" 0.321090735035653 58.1796469353139 451.47649507504 144.35365190031
+"20" 0.375862066828795 65.0117327272892 158.536369032227 127.305114357732
+"21" 0.0722375355431054 35.3545167273842 126.951391426846 193.100387256127
+"22" 0.0772129996198421 31.5452552819625 379.832963193767 235.720843761228
+"23" 0.0605716685358678 30.9160601114854 311.444346229546 191.08392035123
+"24" 0.157789955300155 44.7116475505754 164.532195450738 224.480235648807
+"25" 1 99 457.110102558509 239.30889045354

M1/General Linear Models/TP2-bis/TP2.Rmd

@@ -0,0 +1,117 @@
+```{r}
+setwd('/Users/arthurdanjou/Workspace/studies/M1/General Linear Models/TP2-bis')
+
+library(tidyverse)
+library(GGally)
+library(broom)
+library(scales)
+library(car)
+library(qqplotr)
+options(scipen = 999, digits = 5)
+```
+```{r}
+data <- read.csv('data02.csv', sep = ',', header = TRUE, dec = ".")
+data %>%
+  mutate(type = factor(type, levels = c("maths", "english", "final"), labels = c("maths", "english", "final"))) %>%
+  ggplot(aes(x = note)) +
+  facet_wrap(vars(type), scales = "free_x") +
+  geom_histogram(binwidth = 4, color = "black", fill = "grey80") +
+  labs(title = "Histogram of notes", x = "Note") +
+  theme_bw(14)
+```
+```{r}
+data_wide <- pivot_wider(data, names_from = type, values_from = note)
+data_wide %>%
+  select(-id) %>%
+  ggpairs() + theme_bw(14)
+```
+```{r}
+model <- lm(data_wide, formula = final ~ maths + english)
+summary(model)
+```
+
+```{r}
+tidy(model, conf.int = TRUE, conf.level = 0.95)
+glance(model)
+
+(R2 <- summary(model)$r.squared)
+(R2 / 2) * 57 / (1 - R2)
+vcov(model)
+```
+
+# Hypothesis testing
+
+```{r}
+C <- c(0, 1, -1)
+beta <- cbind(coef(model))
+(C_beta <- C %*% beta)
+
+X <- model.matrix(model)
+(inv_XtX <- solve(t(X) %*% X))
+
+q <- 1
+numerator <- t(C_beta) %*%
+  solve(t(C) %*% inv_XtX %*% C) %*%
+  C_beta
+denominator <- sigma(model)^2
+F <- (numerator / q) / denominator
+F
+
+dof <- nrow(data_wide) - 3
+
+qf(0.95, q, dof)
+pf(F, q, dof, lower.tail = FALSE)
+
+linearHypothesis(model, "maths - english = 0")
+```
+
+# Submodel testing
+```{r}
+data_predict <- predict(model, newdata = expand.grid(maths = seq(70, 90, 2), english = c(75, 85)), interval = "confidence") %>%
+  as_tibble() %>%
+  bind_cols(expand.grid(maths = seq(70, 90, 2), english = c(75, 85)))
+
+data_predict %>%
+  mutate(english = as.factor(english)) %>%
+  ggplot(aes(x = maths, y = fit, color = english, fill = english, label = round(fit, 1))) +
+  geom_ribbon(aes(ymin = lwr, ymax = upr), alpha = 0.2, show.legend = FALSE) +
+  geom_point(size = 2) +
+  geom_line(aes(y = fit)) +
+  geom_text(vjust = -1, show.legend = FALSE) +
+  labs(title = "Prediction of final note", x = "Maths note", y = "Final note", color = "English", fill = "English") +
+  theme_bw(14)
+```
+```{r}
+diag_data <- augment(model)
+
+ggplot(diag_data, aes(x = .fitted, y = .resid)) +
+  geom_point() +
+  geom_hline(yintercept = 0) +
+  labs(title = "Residuals vs Fitted", x = "Fitted values", y = "Residuals") +
+  theme_bw(14)
+```
+```{r}
+ggplot(diag_data, aes(sample = .resid)) +
+  stat_qq_band(alpha = 0.2, fill = "blue") +
+  stat_qq_line(color = "red") +
+  stat_qq_point(size = 1) +
+  labs(y = "Sample quantile", x = "Theoritical quantile") +
+  theme_minimal(base_size = 14)
+
+ggplot(diag_data, aes(x = .resid)) +
+  geom_histogram(fill = "dodgerblue", color = "black", bins = 7) +
+  labs(y = "Count", x = "Résiduals") +
+  scale_y_continuous(expand = expansion(c(0, 0.05))) +
+  scale_x_continuous(breaks = pretty_breaks(n = 10)) +
+  theme_minimal(base_size = 14)
+
+mutate(diag_data, obs = row_number()) |>
+  ggplot(aes(x = obs, y = .cooksd)) +
+  geom_segment(aes(x = obs, y = 0, xend = obs, yend = .cooksd)) +
+  geom_point(color = "blue", size = 1) +
+  scale_x_continuous(breaks = seq(0, 60, 10)) +
+  labs(y = "Cook's distance", x = "Index") +
+  theme_minimal(base_size = 14)
+
+influenceIndexPlot(model, vars = "cook", id = list(n = 5), main = NULL)
+```

M1/General Linear Models/TP2-bis/data02.csv

@@ -0,0 +1,181 @@
+id,type,note
+1,final,59.29
+1,maths,75.34
+1,english,81.17
+2,final,60.75
+2,maths,78.96
+2,english,81.99
+3,final,65.88
+3,maths,78.06
+3,english,80.16
+4,final,64.5
+4,maths,77.83
+4,english,76.74
+5,final,59.99
+5,maths,83.26
+5,english,80.93
+6,final,63.6
+6,maths,83.26
+6,english,77.98
+7,final,69.01
+7,maths,81.9
+7,english,80.24
+8,final,67.21
+8,maths,86.83
+8,english,80.75
+9,final,69.93
+9,maths,84.28
+9,english,79.05
+10,final,60.1
+10,maths,77.89
+10,english,72.77
+11,final,59.19
+11,maths,77.91
+11,english,74.23
+12,final,64.19
+12,maths,75.72
+12,english,74.48
+13,final,68.89
+13,maths,88.06
+13,english,82.16
+14,final,75.48
+14,maths,84
+14,english,83.16
+15,final,70.95
+15,maths,85.58
+15,english,83.15
+16,final,64.24
+16,maths,83.5
+16,english,81.94
+17,final,63.32
+17,maths,84.36
+17,english,78.67
+18,final,65.31
+18,maths,79.1
+18,english,82.73
+19,final,60.88
+19,maths,78.9
+19,english,80.34
+20,final,62.38
+20,maths,76.31
+20,english,81.53
+21,final,60.83
+21,maths,80.42
+21,english,79.98
+22,final,67.62
+22,maths,81.1
+22,english,83.96
+23,final,70.03
+23,maths,84.25
+23,english,79.44
+24,final,67.72
+24,maths,79.44
+24,english,82.07
+25,final,72.76
+25,maths,86.04
+25,english,82.4
+26,final,74.76
+26,maths,87.03
+26,english,87
+27,final,74.33
+27,maths,84.65
+27,english,87.8
+28,final,64.87
+28,maths,77.41
+28,english,78.92
+29,final,66.04
+29,maths,81.65
+29,english,81.78
+30,final,64.73
+30,maths,75.84
+30,english,79.03
+31,final,60.86
+31,maths,70.64
+31,english,80.88
+32,final,62.11
+32,maths,71.72
+32,english,76.82
+33,final,65.91
+33,maths,76.24
+33,english,76.7
+34,final,68.93
+34,maths,86.21
+34,english,83.18
+35,final,71.63
+35,maths,83.73
+35,english,82.51
+36,final,68.16
+36,maths,84.52
+36,english,80.64
+37,final,67.39
+37,maths,80.82
+37,english,80.51
+38,final,62.62
+38,maths,76.91
+38,english,78.17
+39,final,61.97
+39,maths,79.58
+39,english,78.33
+40,final,58.88
+40,maths,72.49
+40,english,76.25
+41,final,62.72
+41,maths,78.31
+41,english,74.58
+42,final,63.45
+42,maths,73.51
+42,english,76.17
+43,final,62.28
+43,maths,77.46
+43,english,80.04
+44,final,67.27
+44,maths,77.79
+44,english,78.98
+45,final,64.04
+45,maths,83.26
+45,english,75.18
+46,final,65.24
+46,maths,80.48
+46,english,79.08
+47,final,61.27
+47,maths,81.74
+47,english,81.21
+48,final,67.51
+48,maths,77.36
+48,english,78.09
+49,final,56.02
+49,maths,74.08
+49,english,73.34
+50,final,59.69
+50,maths,76.24
+50,english,73.21
+51,final,62.68
+51,maths,70.61
+51,english,72.48
+52,final,54.8
+52,maths,72.41
+52,english,78.33
+53,final,55.89
+53,maths,77.09
+53,english,75.79
+54,final,60.36
+54,maths,78.81
+54,english,77.19
+55,final,60.47
+55,maths,76.84
+55,english,76.34
+56,final,63.31
+56,maths,80.6
+56,english,76.26
+57,final,60.2
+57,maths,80.41
+57,english,76.67
+58,final,64.03
+58,maths,86.18
+58,english,76.56
+59,final,67.61
+59,maths,83.56
+59,english,82.45
+60,final,66.87
+60,maths,84.23
+60,english,79.77

M1/General Linear Models/TP2/Cepages B TP2.csv

@@ -0,0 +1,37 @@
+Origine;Couleur;Alcool;pH;AcTot;Tartrique;Malique;Citrique;Acetique;Lactique
+Bordeaux;Blanc;12;2,84;89;21,1;21;4,3;16,9;9,3
+Bordeaux;Blanc;11,5;3,1;97;26,4;34,2;3,9;9,9;16
+Bordeaux;Blanc;14,6;2,96;99;20,7;21,8;8,1;19,7;11,2
+Bordeaux;Blanc;10,5;3,1;72;29,7;4,2;3,6;11,9;14,4
+Bordeaux;Blanc;14;3,29;76;22,3;9,3;4,7;20,1;21,6
+Bordeaux;Blanc;13,2;2,94;83;24,6;9,4;4,1;19,7;16,8
+Bordeaux;Blanc;11,2;2,91;95;39,4;14,5;4,2;19,4;10,5
+Bordeaux;Blanc;15,4;3,43;86;14,1;28,8;8,5;15;12,6
+Bordeaux;Blanc;13,4;3,35;76;18,9;23;6,4;14,4;10,5
+Bourgogne;Blanc;11,4;2,9;103;50;18;2,8;14,4;8,5
+Bourgogne;Blanc;10,5;2,95;118;31,6;38,8;4,2;13,1;15,7
+Bourgogne;Blanc;10,3;2,9;106;37,5;27,6;3,2;14,7;11,5
+Bourgogne;Blanc;13;2,89;97;42,1;19;3,6;11,2;15,7
+Bourgogne;Blanc;13,4;2,83;107;50,5;22,1;5;11,9;9,4
+Bourgogne;Blanc;12,7;3,11;101;33,2;17,5;5,3;9,4;36,7
+Bourgogne;Blanc;10,8;2,83;121;42,5;44,8;4,6;9,4;8,7
+Bourgogne;Blanc;12;3,25;76;44,2;1;3;17,5;17,6
+Bourgogne;Blanc;13,8;3,15;87;29,2;24,4;6,4;10,6;8,6
+Bordeaux;Rouge;11,7;3,49;74;22,5;3,6;1,4;21,8;24,3
+Bordeaux;Rouge;10,8;3,5;76;24,8;1,8;1,3;21,2;27
+Bordeaux;Rouge;10,1;3,66;72;25,7;5;0,8;20;29,7
+Bordeaux;Rouge;11,7;3,22;77;30,1;1,4;1,1;17,5;20,2
+Bordeaux;Rouge;10,2;3,45;74;23,5;2;1;20,6;23,5
+Bordeaux;Rouge;11,5;3,28;86;26,4;3,4;1,1;21,2;30,4
+Bordeaux;Rouge;11,2;3,35;73;30,8;1,8;3,6;10,3;22,2
+Bordeaux;Rouge;12,2;3,43;77;26,1;1,8;1,4;14,7;17,9
+Bordeaux;Rouge;11,2;3,41;75;27,2;3;1,5;15,9;23,1
+Bourgogne;Rouge;12,7;3,36;78;36,2;2;0,8;17,2;20,1
+Bourgogne;Rouge;13,1;3,48;87;30;2;1;22,1;37,4
+Bourgogne;Rouge;13,4;3,5;75;27,8;0;1,3;14,7;33,1
+Bourgogne;Rouge;13,2;3,59;76;30;3,6;2,2;13,4;40,9
+Bourgogne;Rouge;13,4;3,34;79;34,6;0;1,6;16,2;23,2
+Bourgogne;Rouge;13,8;3,46;76;27,7;1,2;3;16,2;30,4
+Bourgogne;Rouge;13,6;3,17;97;39,7;18,4;5,4;12,2;14,3
+Bourgogne;Rouge;14;3,42;76;32,6;0,4;2,1;14,7;20,4
+Bourgogne;Rouge;13,1;3,35;81;36;1,6;1,9;15;23,1

M1/General Linear Models/TP2/TP2.rmd

@@ -0,0 +1,85 @@
+```{r}
+setwd('/Users/arthurdanjou/Workspace/studies/M1/General Linear Models/TP2')
+```
+
+# Question 1 : Import dataset and check variables
+
+```{r}
+library(dplyr)
+cepages <- read.csv("Cepages B TP2.csv", header = TRUE, sep = ";", dec = ",")
+cepages$Couleur <- as.factor(cepages$Couleur)
+cepages$Origine <- as.factor(cepages$Origine)
+cepages <- cepages %>% mutate(across(where(is.character), as.numeric))
+cepages <- cepages %>% mutate(across(where(is.integer), as.numeric))
+paged_table(cepages)
+```
+
+# Question 2 : Table of counts
+
+```{r}
+table(cepages$Origine, cepages$Couleur)
+```
+
+# Question 3
+
+## Display the table of average Ph according to couleur and average ph
+
+```{r}
+tapply(cepages$pH, list(cepages$Couleur), mean)
+```
+
+## Display the table of average pH according to couleur and origine
+
+```{r}
+tapply(cepages$pH, list(cepages$Couleur, cepages$Origine), mean)
+```
+
+# Question 4 : Regression lines of ph over AcTol for different Color
+```{r}
+library(ggplot2)
+
+ggplot(cepages, aes(x = AcTot, y = pH, color = Couleur)) +
+  geom_point(col = 'red', size = 0.5) +
+  geom_smooth(method = "lm", se = F)
+
+ggplot(cepages, aes(y = pH, x = AcTot, colour = Couleur, fill = Couleur)) +
+  geom_boxplot(alpha = 0.5, outlier.alpha = 0)
+```
+
+# Question 5 : Regression Ligne of pH over AcTot for different Origine
+
+```{r}
+ggplot(cepages, aes(x = AcTot, y = pH, color = Origine)) +
+  geom_smooth(method = 'lm', se = F) +
+  geom_point(col = 'red', size = 0.5)
+
+ggplot(cepages, aes(y = pH, x = AcTot, colour = Origine, fill = Origine)) +
+  geom_boxplot(alpha = 0.5, outlier.alpha = 0)
+```
+
+# Question 6 : ANOVA
+```{r}
+model_full <- lm(pH ~ Couleur, data = cepages)
+summary(model_full)
+```
+
+```{r}
+autoplot(model_full, 1:4)
+```
+
+[P1] is verified as the 'Residuals vs Fitted' plot shows that the points are well distributed around 0
+[P2] is verified as the 'Scale-Location' plot shows that the points are well distributed around 1
+[P4] is verified as the 'QQPlot' is aligned with the 'y=x' line
+
+```{r}
+set.seed(12)
+durbinWatsonTest(model_full)
+```
+[P3] is verified as the p-value is 0.7 > 0.05, so we do not reject H0 so the residuals are not auto-correlated
+
+# Bonus : Type II Test
+
+```{r}
+library(car)
+Anova(model_full)
+```

M1/General Linear Models/TP3-bis/TP3.Rmd

@@ -0,0 +1,206 @@
+```{r}
+setwd('/Users/arthurdanjou/Workspace/studies/M1/General Linear Models/TP3-bis')
+
+library(GGally)
+library(broom)
+library(scales)
+library(car)
+library(glue)
+library(janitor)
+library(marginaleffects)
+library(tidyverse)
+library(qqplotr)
+options(scipen = 999, digits = 5)
+```
+```{r}
+data03 <- read.csv('data03.csv', header = TRUE, sep = ',', dec = '.')
+data03$sexe <- as.factor(data03$sexe)
+data03$travail <- as.factor(data03$travail)
+head(data03, 15)
+```
+```{r}
+tab_sexe <- data03 |>
+  count(sexe) |>
+  mutate(freq1 = n / sum(n)) |>
+  mutate(freq2 = glue("{n} ({label_percent()(freq1)})")) |>
+  rename(Sexe = 1, Effectif = n, Proportion = freq1, "n (%)" = freq2)
+tab_sexe
+```
+
+```{r}
+tab_travail <- data03 |>
+  count(travail) |>
+  mutate(freq1 = n / sum(n)) |>
+  mutate(freq2 = glue("{n} ({label_percent()(freq1)})")) |>
+  rename(Travail = 1, Effectif = n, Proportion = freq1, "n (%)" = freq2)
+tab_travail
+```
+
+```{r}
+cross_sexe_travail <- data03 |>
+  count(sexe, Travail = travail) |>
+  group_by(sexe) |>
+  mutate(freq1 = n / sum(n)) |>
+  mutate(freq2 = glue("{n} ({label_percent(0.1)(freq1)})"), n = NULL, freq1 = NULL) |>
+  pivot_wider(names_from = sexe, values_from = freq2)
+cross_sexe_travail
+```
+
+```{r}
+data03 <- mutate(data03, logy = log(y))
+
+data03 |>
+  pivot_longer(c(y, logy), names_to = "variable", values_to = "value") |>
+  mutate(variable = factor(
+    variable,
+    levels = c("y", "logy"),
+    labels = c("Salaire", "Log-Salaire"))
+  ) |>
+  ggplot(aes(x = value)) +
+  facet_wrap(vars(variable), scales = "free") +
+  geom_histogram(
+    fill = "dodgerblue",
+    color = "black",
+    bins = 15) +
+  scale_y_continuous(expand = expansion(c(0, 0.05))) +
+  scale_x_continuous(breaks = pretty_breaks()) +
+  labs(x = "Valeur", y = "Effectif") +
+  theme_bw(base_size = 14) +
+  theme(strip.text = element_text(size = 11, face = "bold"))
+```
+```{r}
+data03 |>
+  pivot_longer(c(y, logy), names_to = "variable", values_to = "value") |>
+  mutate(variable = factor(
+    variable,
+    levels = c("y", "logy"), labels = c("Salaire", "Log-Salaire")
+  )) |>
+  ggplot(aes(x = sexe, y = value)) +
+  facet_wrap(vars(variable), scales = "free") +
+  geom_boxplot(
+    width = 0.5, fill = "cyan", linewidth = 0.5, outlier.size = 2, outlier.alpha = 0.3
+  ) +
+  scale_y_continuous(breaks = pretty_breaks()) +
+  labs(x = NULL, y = "Valeur") +
+  theme_bw(base_size = 14) +
+  theme(
+    strip.text = element_text(size = 11, face = "bold"),
+    panel.border = element_rect(linewidth = 0.5)
+  )
+```
+```{r}
+data03 |>
+  pivot_longer(c(y, logy), names_to = "variable", values_to = "value") |>
+  mutate(variable = factor(
+    variable,
+    levels = c("y", "logy"), labels = c("Salaire", "Log-Salaire")
+  )) |>
+  ggplot(aes(x = travail, y = value)) +
+  facet_wrap(vars(variable), scales = "free") +
+  stat_boxplot(width = 0.25, geom = "errorbar", linewidth = 0.5) +
+  geom_boxplot(
+    width = 0.5, fatten = 0.25, fill = "cyan", linewidth = 0.5,
+    outlier.size = 2, outlier.alpha = 0.3
+  ) +
+  scale_y_continuous(breaks = pretty_breaks()) +
+  labs(x = NULL, y = "Valeur") +
+  theme_bw(base_size = 14) +
+  theme(
+    strip.text = element_text(size = 11, face = "bold"),
+    panel.border = element_rect(linewidth = 0.5)
+  )
+```
+
+```{r}
+data03 |>
+  group_by(sexe) |>
+  summarise(n = n(), "Mean (Salaire)" = mean(y), "SD (Salaire)" = sd(y))
+```
+
+```{r}
+data03 |>
+  group_by(travail) |>
+  summarise(n = n(), "Mean (Salaire)" = mean(y), "SD (Salaire)" = sd(y))
+```
+
+```{r}
+data03 |>
+  group_by(sexe, travail) |>
+  summarise(n = n(), "Mean (Salaire)" = mean(y), "SD (Salaire)" = sd(y))
+```
+```{r}
+data03 |>
+  group_by(sexe) |>
+  summarise(n = n(), "Mean (Salaire)" = mean(logy), "SD (Salaire)" = sd(logy))
+```
+
+```{r}
+data03 |>
+  group_by(travail) |>
+  summarise(n = n(), "Mean (Salaire)" = mean(logy), "SD (Salaire)" = sd(logy))
+```
+
+```{r}
+data03 |>
+  group_by(sexe, travail) |>
+  summarise(n = n(), "Mean (Salaire)" = mean(logy), "SD (Salaire)" = sd(logy))
+```
+```{r}
+data03 <- data03 |>
+  mutate(sexef = ifelse(sexe == "Femme", 1, 0), sexeh = 1 - sexef) |>
+  mutate(job1 = (travail == "Type 1") * 1) |>
+  mutate(job2 = (travail == "Type 2") * 1) |>
+  mutate(job3 = (travail == "Type 3") * 1)
+head(data03, 15)
+```
+```{r}
+mod1 <- lm(y ~ sexeh, data = data03)
+mod2 <- lm(y ~ job2 + job3, data = data03)
+mod3 <- lm(y ~ sexeh + job2 + job3, data = data03)
+tidy(mod1)
+tidy(mod2)
+tidy(mod3)
+```
+
+Interprétations des coefficients du modèle 1
+$𝑦_i = β_0 + β_1 sexeh_i + ϵ_i$
+• (Intercept): $\hat{β_0} = 7.88$ : Salaire moyen chez les femmes
+• sexeh: $\hat{𝛽1} = 2.12$ : Les hommes gagnent en moyenne 2.12 dollars par heure de plus que les femmes
+(significatif).
+
+Interprétations des coefficients du modèle 2
+$𝑦_i = β_0 + β_1 job2_i + β_2 job3_i + ϵ_i$
+• (Intercept): $\hat{β_0} = 12.21$ : Salaire moyen pour le travail de type 1.
+• job2: $\hat{β_1} = −5.09$ : la différence de salaire entre le travail de type 2 et celui de type 1 est de −5.09 dollars par heure en moyenne (significatif)
+• job3: $\hat{β_2} = −3.78$ : la différence de salaire entre le travail de type 3 et celui de type 1 est de −3.78 dollarspar heure en moyenne (significatif).
+
+Interprétations des coefficients du modèle 3
+$𝑦_i = β_0 + β_1 sexeh_i + β_2 job2_i + β_3 job3_i + ϵ_i$
+• (Intercept): $\hat{β_0} = 11.13$ : Salaire moyen chez les femmes avec un travail de type 1
+• sexeh: $\hat{β_1 = 1.97$ : Les hommes gagnent en moyenne 1.97 dollars par heure de plus que les femmes
+(significatif), quelque soit le type de travail.
+• job2: $\hat{β_2} = −4.71$ : la différence de salaire entre le travail de type 2 et celui de type 1 est de −4.71 dollars par heure en moyenne (significatif), quelque soit le sexe.
+• job3: $\hat{β_3} = −4.3$ : la différence de salaire entre le travail de type 3 et celui de type 1 est de −4.3 dollars par heure en moyenne (significatif), quelque soit le sexe.
+
+```{r}
+anova(mod1, mod3)
+```
+La p-value du test est inférieur à 0.05, on rejette donc $𝐻0$ et on conclue qu’au moins un des coefficients (𝛽1, 𝛽2) est significativement non nulle.
+• On vient de tester si le type de travail est associé au salaire horaire. C’est donc le cas pour ces données.
+```{r}
+linearHypothesis(mod3, c("job2", "job3"))
+linearHypothesis(mod3, "job2 = job3")
+```
+Le test est non significatif (𝑝 = 0.44). On ne rejette pas $𝐻0$ et on conclue qu’il n’y pas de différence de salaire horaire entre le travail de type 2 et le travail de type 3, quelque soit le sexe.
+```{r}
+mod3bis <- lm(y ~ sexe + travail, data = data03)
+summary(mod3bis)
+```
+Les modèles mod3bis1 et mod3 sont identiques
+• Pas besoins de créer toutes ces variables indicatrices si nos variables catégorielles sont de type factor !
+• La référence sera toujours la première modalité du factor.
+• On peut changer la référence avec `relevel()` ou avec `C()`. Par exemple, si on veut la modalité 2 en référence pour le travail
+```{r}
+lm(y ~ sexe + relevel(travail, ref = 2), data = data03) |>
+  tidy()
+```

M1/General Linear Models/TP3-bis/data03.csv

@@ -0,0 +1,535 @@
+id,y,education,experience,sexe,travail
+1,3.75,12,6,Femme,Type 3
+2,12,16,14,Femme,Type 1
+3,15.73,16,4,Homme,Type 1
+4,5,12,0,Femme,Type 2
+5,9,12,20,Homme,Type 2
+6,6.88,17,15,Femme,Type 1
+7,9.1,13,16,Homme,Type 2
+8,3.35,16,3,Homme,Type 2
+9,10,16,10,Femme,Type 1
+10,4.59,12,36,Femme,Type 2
+11,7.61,12,20,Homme,Type 3
+12,18.5,14,13,Femme,Type 3
+13,20.4,17,3,Homme,Type 1
+14,8.49,12,24,Femme,Type 2
+15,12.5,15,6,Femme,Type 2
+16,5.75,9,34,Femme,Type 1
+17,4,12,12,Homme,Type 2
+18,12.47,13,10,Homme,Type 3
+19,5.55,11,45,Femme,Type 2
+20,6.67,16,10,Femme,Type 1
+21,4.75,12,2,Femme,Type 2
+22,7,12,7,Homme,Type 3
+23,12.2,14,10,Homme,Type 3
+24,15,12,42,Homme,Type 1
+25,9.56,12,23,Homme,Type 3
+26,7.65,12,20,Homme,Type 2
+27,5.8,13,5,Homme,Type 2
+28,5.8,16,14,Homme,Type 1
+29,3.6,12,6,Femme,Type 2
+30,7.5,12,3,Homme,Type 3
+31,8.75,12,30,Homme,Type 1
+32,10.43,14,15,Femme,Type 2
+33,3.75,12,41,Femme,Type 2
+34,8.43,12,12,Homme,Type 2
+35,4.55,12,4,Femme,Type 1
+36,6.25,9,30,Homme,Type 3
+37,4.5,12,16,Homme,Type 3
+38,4.3,13,8,Homme,Type 3
+39,8,12,15,Femme,Type 2
+40,7,7,42,Homme,Type 3
+41,4.5,12,3,Femme,Type 1
+42,4.75,12,10,Femme,Type 2
+43,4.5,12,7,Femme,Type 1
+44,3.4,8,49,Femme,Type 2
+45,9.83,12,23,Homme,Type 3
+46,6.25,16,7,Femme,Type 1
+47,23.25,17,25,Femme,Type 1
+48,9,16,27,Femme,Type 2
+49,19.38,16,11,Femme,Type 1
+50,14,16,16,Femme,Type 1
+51,6.5,12,8,Homme,Type 3
+52,6,12,19,Femme,Type 2
+53,6.25,16,7,Femme,Type 1
+54,6.5,8,27,Homme,Type 3
+55,9.5,12,25,Femme,Type 2
+56,4.25,12,29,Femme,Type 2
+57,14.53,16,18,Homme,Type 1
+58,8.85,14,19,Femme,Type 2
+59,9.17,12,44,Femme,Type 2
+60,11,8,42,Homme,Type 3
+61,3.75,16,13,Femme,Type 3
+62,3.35,14,0,Homme,Type 2
+63,3.35,12,8,Femme,Type 3
+64,6.75,12,12,Homme,Type 3
+65,10,16,7,Femme,Type 2
+66,8.93,8,47,Homme,Type 2
+67,11.11,12,28,Homme,Type 2
+68,6.5,11,39,Homme,Type 2
+69,14,5,44,Homme,Type 3
+70,6.25,13,30,Femme,Type 2
+71,4.7,8,19,Homme,Type 3
+72,22.83,18,37,Femme,Type 1
+73,13.45,12,16,Homme,Type 3
+74,5,12,39,Femme,Type 2
+75,10,10,12,Homme,Type 3
+76,8.9,10,27,Homme,Type 3
+77,7,11,12,Femme,Type 2
+78,15,12,39,Homme,Type 1
+79,3.5,12,35,Homme,Type 2
+80,12.57,12,12,Homme,Type 3
+81,8,12,14,Femme,Type 2
+82,7,18,33,Homme,Type 1
+83,26,14,21,Homme,Type 3
+84,11.43,12,3,Homme,Type 3
+85,5.56,14,5,Homme,Type 2
+86,12,18,18,Femme,Type 1
+87,5,12,4,Homme,Type 2
+88,9.15,12,7,Homme,Type 3
+89,8.5,12,16,Femme,Type 1
+90,6.25,16,4,Homme,Type 2
+91,3.35,7,43,Homme,Type 3
+92,15.38,16,33,Homme,Type 1
+93,6.1,12,33,Femme,Type 1
+94,4.13,12,4,Femme,Type 2
+95,14.21,11,15,Homme,Type 3
+96,7.53,14,1,Homme,Type 2
+97,3.5,10,33,Femme,Type 2
+98,6.58,12,24,Femme,Type 1
+99,4.85,10,13,Homme,Type 3
+100,7.81,12,1,Femme,Type 1
+101,6,13,31,Homme,Type 2
+102,4.5,11,14,Homme,Type 3
+103,24.98,18,29,Homme,Type 1
+104,13.33,18,10,Homme,Type 2
+105,20.5,16,14,Homme,Type 1
+106,10,12,20,Homme,Type 2
+107,11.22,18,19,Homme,Type 1
+108,10.58,16,9,Homme,Type 1
+109,12.65,17,13,Femme,Type 1
+110,12,12,14,Homme,Type 3
+111,5.1,8,21,Femme,Type 3
+112,9.86,15,13,Homme,Type 1
+113,10,12,11,Homme,Type 3
+114,8,18,33,Homme,Type 1
+115,22.2,18,40,Femme,Type 1
+116,4.25,13,0,Femme,Type 2
+117,5,16,3,Homme,Type 3
+118,4,12,15,Femme,Type 2
+119,12.5,13,16,Femme,Type 2
+120,6.5,11,17,Homme,Type 3
+121,3.6,12,43,Femme,Type 2
+122,9.45,12,13,Homme,Type 3
+123,10.81,12,40,Femme,Type 2
+124,6.25,18,14,Homme,Type 1
+125,4.35,8,37,Femme,Type 2
+126,16,12,12,Homme,Type 1
+127,7.69,12,19,Homme,Type 2
+128,9,8,33,Homme,Type 3
+129,4.25,12,2,Femme,Type 2
+130,7.8,17,7,Homme,Type 1
+131,3.8,12,4,Femme,Type 2
+132,3.75,15,4,Homme,Type 2
+133,8,12,8,Femme,Type 2
+134,9.6,9,33,Homme,Type 2
+135,3.5,12,34,Homme,Type 2
+136,13.75,14,21,Homme,Type 2
+137,5.13,12,5,Femme,Type 2
+138,4.8,9,16,Homme,Type 3
+139,15.56,16,10,Homme,Type 1
+140,20.55,12,33,Homme,Type 3
+141,7.5,12,9,Femme,Type 2
+142,7.78,16,6,Femme,Type 1
+143,4.5,12,7,Femme,Type 3
+144,3.5,9,48,Homme,Type 2
+145,10.2,17,26,Femme,Type 1
+146,12,17,24,Femme,Type 1
+147,4,12,6,Homme,Type 3
+148,6,17,3,Femme,Type 1
+149,13.51,18,14,Homme,Type 1
+150,7.5,16,10,Homme,Type 1
+151,12,12,20,Homme,Type 3
+152,4,11,25,Femme,Type 3
+153,12.5,12,43,Homme,Type 2
+154,15,12,33,Homme,Type 3
+155,10,18,13,Femme,Type 1
+156,3.65,11,16,Homme,Type 3
+157,7,11,16,Femme,Type 2
+158,8.9,14,13,Homme,Type 3
+159,25,14,4,Homme,Type 2
+160,7,12,32,Femme,Type 1
+161,14.29,14,32,Femme,Type 2
+162,4.22,8,39,Femme,Type 3
+163,7.3,12,37,Homme,Type 3
+164,13.65,16,11,Homme,Type 1
+165,7.5,12,16,Femme,Type 2
+166,10,10,25,Femme,Type 2
+167,7.78,12,23,Homme,Type 3
+168,4.5,12,15,Femme,Type 3
+169,10.58,14,25,Homme,Type 3
+170,10,16,0,Femme,Type 1
+171,17.25,15,31,Homme,Type 1
+172,12,17,13,Homme,Type 2
+173,14,18,31,Femme,Type 1
+174,3.35,13,2,Femme,Type 2
+175,6,12,9,Homme,Type 3
+176,6.5,12,5,Homme,Type 3
+177,10,16,4,Femme,Type 1
+178,13,12,25,Homme,Type 2
+179,4.28,12,38,Femme,Type 2
+180,9.65,12,38,Femme,Type 2
+181,5.79,12,42,Femme,Type 1
+182,6.93,12,26,Homme,Type 2
+183,12.67,16,15,Homme,Type 1
+184,4.55,13,33,Femme,Type 2
+185,6.8,9,30,Femme,Type 3
+186,13,12,8,Homme,Type 3
+187,3.35,12,0,Homme,Type 3
+188,5.4,12,18,Femme,Type 2
+189,10.67,12,36,Homme,Type 3
+190,11.25,15,5,Homme,Type 1
+191,4.1,12,15,Femme,Type 2
+192,10.28,15,10,Femme,Type 1
+193,5.71,18,3,Homme,Type 1
+194,5,13,6,Femme,Type 2
+195,3.75,2,16,Homme,Type 2
+196,3.75,11,11,Homme,Type 3
+197,10.62,12,45,Femme,Type 2
+198,15.79,18,7,Homme,Type 1
+199,6.36,12,9,Homme,Type 3
+200,10.53,14,12,Femme,Type 2
+201,8.63,12,18,Femme,Type 2
+202,16,14,20,Homme,Type 3
+203,7.45,12,25,Femme,Type 1
+204,4.84,15,1,Homme,Type 1
+205,6,4,54,Homme,Type 2
+206,3.8,12,16,Femme,Type 2
+207,15,12,40,Homme,Type 3
+208,7,12,5,Homme,Type 2
+209,12,18,23,Homme,Type 1
+210,5.25,10,15,Homme,Type 3
+211,9.36,12,8,Homme,Type 3
+212,7.14,14,17,Homme,Type 2
+213,19.98,9,29,Homme,Type 3
+214,12,12,5,Homme,Type 2
+215,10.75,12,24,Homme,Type 3
+216,5.5,12,3,Homme,Type 3
+217,9.25,12,19,Homme,Type 3
+218,8.99,12,15,Femme,Type 2
+219,3.5,11,17,Femme,Type 2
+220,22.5,16,22,Homme,Type 1
+221,5,12,5,Homme,Type 3
+222,12.5,14,19,Femme,Type 2
+223,7,17,2,Homme,Type 1
+224,16.42,14,19,Homme,Type 1
+225,19.98,14,44,Homme,Type 2
+226,6.5,10,30,Homme,Type 3
+227,9.5,12,39,Femme,Type 2
+228,11.25,12,41,Homme,Type 3
+229,8.06,13,17,Homme,Type 1
+230,6,15,26,Femme,Type 2
+231,24.98,17,18,Homme,Type 1
+232,5,12,28,Femme,Type 3
+233,3.98,14,6,Femme,Type 2
+234,4.5,13,0,Femme,Type 2
+235,7.75,12,24,Femme,Type 2
+236,2.85,12,1,Homme,Type 3
+237,9,16,7,Homme,Type 1
+238,9.63,14,22,Homme,Type 2
+239,12,14,10,Femme,Type 1
+240,7.5,12,27,Femme,Type 2
+241,13.45,16,16,Homme,Type 1
+242,7.5,12,23,Femme,Type 2
+243,4.5,7,14,Homme,Type 2
+244,3.75,12,17,Femme,Type 2
+245,5.75,12,3,Homme,Type 1
+246,12.5,17,13,Femme,Type 1
+247,6.5,12,11,Femme,Type 1
+248,6.94,12,7,Femme,Type 2
+249,11.36,18,5,Homme,Type 1
+250,3.35,12,0,Femme,Type 2
+251,9.22,14,13,Femme,Type 1
+252,9.75,15,9,Femme,Type 3
+253,24.98,17,5,Femme,Type 1
+254,5.62,13,2,Femme,Type 2
+255,9.57,12,5,Femme,Type 2
+256,5.5,12,11,Femme,Type 3
+257,7,12,10,Femme,Type 2
+258,17.86,13,36,Homme,Type 1
+259,5.5,16,2,Femme,Type 2
+260,8.8,14,41,Homme,Type 1
+261,5.35,12,13,Femme,Type 2
+262,4.95,9,42,Femme,Type 3
+263,13.89,16,17,Femme,Type 1
+264,6,12,1,Homme,Type 3
+265,4.17,14,24,Femme,Type 2
+266,8.5,12,13,Homme,Type 3
+267,9.37,16,26,Femme,Type 1
+268,3.35,16,14,Femme,Type 2
+269,6.25,13,4,Femme,Type 2
+270,13,11,18,Homme,Type 2
+271,11.25,16,3,Femme,Type 1
+272,6.1,10,44,Femme,Type 3
+273,10.5,13,14,Femme,Type 1
+274,5.83,13,3,Homme,Type 2
+275,5.25,12,8,Femme,Type 2
+276,10,16,14,Homme,Type 1
+277,8.5,12,25,Femme,Type 2
+278,10.62,12,34,Homme,Type 1
+279,5.2,12,24,Femme,Type 2
+280,21.25,13,32,Homme,Type 1
+281,15,18,12,Homme,Type 1
+282,5,12,14,Femme,Type 2
+283,4.55,8,45,Femme,Type 2
+284,3.5,8,8,Homme,Type 3
+285,8,16,17,Femme,Type 1
+286,11.84,12,26,Homme,Type 1
+287,13.45,16,8,Homme,Type 1
+288,9,16,6,Femme,Type 2
+289,8.75,11,36,Femme,Type 2
+290,15,14,22,Homme,Type 2
+291,13.95,18,14,Femme,Type 1
+292,11.25,12,30,Femme,Type 1
+293,10.5,12,29,Femme,Type 2
+294,8.5,9,38,Homme,Type 3
+295,8.63,14,4,Femme,Type 1
+296,22.5,15,12,Homme,Type 1
+297,13.12,12,33,Femme,Type 2
+298,12.5,12,14,Femme,Type 2
+299,9.75,11,37,Homme,Type 3
+300,4.5,14,14,Homme,Type 2
+301,12.5,12,11,Homme,Type 3
+302,18,16,38,Homme,Type 1
+303,3.55,13,1,Femme,Type 2
+304,12.22,12,19,Homme,Type 3
+305,5.5,16,29,Homme,Type 1
+306,8.89,16,22,Femme,Type 1
+307,3.35,16,9,Homme,Type 1
+308,13.98,14,14,Homme,Type 3
+309,7.5,14,2,Homme,Type 2
+310,5.62,14,32,Femme,Type 2
+311,11.32,12,13,Femme,Type 2
+312,3.84,11,25,Femme,Type 2
+313,6.88,14,10,Femme,Type 2
+314,18.16,17,14,Homme,Type 1
+315,6,13,7,Homme,Type 3
+316,22.5,16,17,Homme,Type 1
+317,6.67,12,1,Homme,Type 3
+318,3.64,12,42,Femme,Type 1
+319,4.5,12,3,Femme,Type 3
+320,5,14,0,Homme,Type 2
+321,8.75,13,18,Homme,Type 3
+322,11.11,13,13,Homme,Type 2
+323,5,12,4,Homme,Type 1
+324,4,12,4,Homme,Type 3
+325,10.62,16,6,Femme,Type 1
+326,10,14,24,Femme,Type 2
+327,4.35,11,20,Femme,Type 2
+328,5.3,12,14,Homme,Type 1
+329,24.98,17,31,Homme,Type 1
+330,3.4,8,29,Femme,Type 2
+331,12.5,12,9,Homme,Type 3
+332,9.5,17,14,Femme,Type 1
+333,7.38,14,15,Femme,Type 1
+334,7.5,12,10,Femme,Type 2
+335,3.75,12,9,Homme,Type 3
+336,24.98,16,18,Homme,Type 1
+337,6.85,12,8,Homme,Type 2
+338,3.51,10,37,Femme,Type 2
+339,7.5,12,17,Homme,Type 1
+340,6.88,8,22,Femme,Type 3
+341,8,12,19,Femme,Type 3
+342,5.75,12,21,Femme,Type 1
+343,5.77,16,3,Homme,Type 2
+344,5,16,4,Femme,Type 2
+345,5.25,16,2,Femme,Type 2
+346,26.29,17,32,Homme,Type 1
+347,3.5,12,25,Femme,Type 2
+348,15.03,12,24,Femme,Type 2
+349,22.2,12,26,Homme,Type 3
+350,4.85,9,16,Femme,Type 3
+351,18.16,18,7,Homme,Type 1
+352,3.95,12,9,Femme,Type 2
+353,6.73,12,2,Homme,Type 3
+354,10,16,7,Homme,Type 1
+355,4,12,46,Femme,Type 3
+356,14.67,14,16,Homme,Type 2
+357,10,10,20,Homme,Type 1
+358,17.5,16,13,Homme,Type 1
+359,5,12,6,Homme,Type 3
+360,6.25,12,6,Femme,Type 3
+361,11.25,12,28,Femme,Type 1
+362,5.71,12,16,Femme,Type 3
+363,5,12,12,Homme,Type 3
+364,9.5,11,29,Homme,Type 3
+365,14,11,13,Homme,Type 3
+366,11.71,16,42,Femme,Type 2
+367,3.35,11,3,Homme,Type 3
+368,18,18,15,Homme,Type 1
+369,10,12,22,Homme,Type 3
+370,5.5,11,24,Femme,Type 2
+371,16.65,14,21,Homme,Type 1
+372,6.75,10,13,Homme,Type 3
+373,5.87,17,6,Femme,Type 2
+374,6,12,8,Homme,Type 3
+375,8.56,14,14,Femme,Type 1
+376,5.65,14,2,Homme,Type 3
+377,5,17,1,Femme,Type 3
+378,10,13,34,Homme,Type 1
+379,8.75,10,19,Homme,Type 2
+380,8,7,44,Homme,Type 3
+381,7.5,12,20,Femme,Type 2
+382,5,14,17,Femme,Type 2
+383,6.15,16,16,Femme,Type 1
+384,9,10,27,Homme,Type 3
+385,11.02,14,12,Homme,Type 2
+386,9.42,12,32,Homme,Type 2
+387,7,10,9,Homme,Type 3
+388,5,12,14,Femme,Type 2
+389,4.15,11,4,Homme,Type 2
+390,7.5,12,17,Homme,Type 3
+391,8.75,13,10,Femme,Type 2
+392,5.5,12,10,Homme,Type 2
+393,20,16,28,Femme,Type 1
+394,5.5,12,33,Femme,Type 2
+395,8.89,8,29,Femme,Type 2
+396,8,12,9,Femme,Type 2
+397,6.4,12,6,Femme,Type 2
+398,6.28,12,38,Femme,Type 3
+399,15.95,17,13,Femme,Type 1
+400,10,14,22,Homme,Type 1
+401,5.65,16,6,Femme,Type 2
+402,2.01,13,0,Homme,Type 2
+403,11,14,14,Homme,Type 3
+404,6.5,12,28,Homme,Type 3
+405,10,12,35,Homme,Type 3
+406,19.47,12,9,Homme,Type 3
+407,7,12,26,Femme,Type 2
+408,11.67,12,43,Femme,Type 2
+409,22.2,18,8,Homme,Type 1
+410,15,16,12,Homme,Type 3
+411,5.95,13,9,Homme,Type 2
+412,12,12,11,Femme,Type 1
+413,13.2,16,10,Homme,Type 1
+414,20,18,19,Femme,Type 1
+415,6,7,15,Femme,Type 3
+416,4.25,12,20,Femme,Type 2
+417,11.35,12,17,Homme,Type 3
+418,22,14,15,Homme,Type 1
+419,5.5,11,18,Homme,Type 3
+420,4.5,11,2,Homme,Type 2
+421,4.5,16,21,Homme,Type 2
+422,5.4,16,10,Femme,Type 1
+423,5.25,12,2,Homme,Type 3
+424,4.62,6,33,Femme,Type 3
+425,7.5,16,22,Femme,Type 1
+426,11.5,12,19,Homme,Type 3
+427,13,12,19,Homme,Type 3
+428,10.25,14,26,Femme,Type 1
+429,16.14,14,16,Homme,Type 1
+430,9.33,12,15,Femme,Type 2
+431,5.5,12,21,Femme,Type 2
+432,8.5,17,3,Homme,Type 2
+433,4.75,12,8,Homme,Type 3
+434,5.75,6,45,Homme,Type 3
+435,3.43,12,2,Homme,Type 2
+436,4.45,10,27,Homme,Type 3
+437,5,12,26,Femme,Type 2
+438,9,12,10,Homme,Type 2
+439,13.28,16,11,Homme,Type 3
+440,7.88,16,17,Homme,Type 2
+441,8,13,15,Femme,Type 2
+442,4,12,7,Homme,Type 2
+443,13.07,13,9,Homme,Type 3
+444,5.2,18,13,Femme,Type 2
+445,8,14,15,Femme,Type 2
+446,8.75,12,9,Homme,Type 3
+447,3.5,9,47,Homme,Type 2
+448,5.25,12,45,Femme,Type 2
+449,3.65,11,8,Femme,Type 2
+450,6.25,12,1,Homme,Type 3
+451,7.96,14,12,Femme,Type 2
+452,7.5,11,3,Homme,Type 2
+453,4.8,12,16,Femme,Type 3
+454,16.26,12,14,Homme,Type 2
+455,6.25,18,27,Homme,Type 1
+456,15,18,11,Femme,Type 1
+457,5.71,18,7,Homme,Type 1
+458,13.1,10,38,Femme,Type 2
+459,5.75,12,15,Femme,Type 2
+460,10.5,12,4,Homme,Type 3
+461,22.5,18,14,Homme,Type 1
+462,16,12,35,Homme,Type 3
+463,17.25,18,5,Homme,Type 1
+464,9.37,17,7,Homme,Type 1
+465,3.5,14,6,Femme,Type 2
+466,3.35,12,7,Femme,Type 2
+467,19.88,12,13,Homme,Type 1
+468,10.78,11,28,Homme,Type 3
+469,5.5,12,20,Homme,Type 2
+470,4,12,8,Homme,Type 2
+471,12.5,15,10,Homme,Type 1
+472,5.15,13,1,Homme,Type 2
+473,5.5,12,12,Homme,Type 3
+474,4,13,0,Homme,Type 3
+475,4.17,12,27,Femme,Type 2
+476,4,16,20,Femme,Type 2
+477,8.5,12,2,Homme,Type 2
+478,12.05,16,6,Femme,Type 1
+479,7,3,55,Homme,Type 3
+480,4.85,12,14,Femme,Type 2
+481,10.32,13,28,Femme,Type 2
+482,1,12,24,Homme,Type 1
+483,9.5,9,46,Femme,Type 2
+484,7.5,12,38,Homme,Type 3
+485,24.98,16,5,Femme,Type 1
+486,6.4,12,45,Femme,Type 2
+487,44.5,14,1,Femme,Type 1
+488,11.79,16,6,Femme,Type 1
+489,11,16,13,Homme,Type 3
+490,3.5,11,33,Femme,Type 2
+491,5.21,18,10,Homme,Type 2
+492,10.61,15,33,Femme,Type 1
+493,6.75,12,22,Homme,Type 2
+494,8.89,12,18,Homme,Type 3
+495,6,16,8,Homme,Type 1
+496,5.85,18,12,Homme,Type 1
+497,11.25,17,10,Femme,Type 1
+498,3.35,12,10,Femme,Type 3
+499,8.2,14,17,Homme,Type 3
+500,3,12,28,Femme,Type 2
+501,9.24,16,5,Homme,Type 1
+502,9.6,12,14,Femme,Type 2
+503,19.98,12,23,Homme,Type 3
+504,6.85,14,34,Homme,Type 2
+505,3.56,12,12,Femme,Type 2
+506,15,16,26,Homme,Type 1
+507,13.16,12,38,Femme,Type 1
+508,3,6,43,Femme,Type 3
+509,9,13,8,Homme,Type 3
+510,8.5,12,8,Homme,Type 3
+511,19,18,13,Homme,Type 1
+512,15,16,10,Homme,Type 1
+513,1.75,12,5,Femme,Type 2
+514,12.16,12,32,Femme,Type 2
+515,9,12,16,Homme,Type 2
+516,5.5,12,20,Homme,Type 2
+517,8.93,12,18,Femme,Type 3
+518,4.35,12,3,Femme,Type 1
+519,6.25,14,2,Homme,Type 1
+520,11.5,16,16,Homme,Type 2
+521,3.45,13,1,Femme,Type 2
+522,10,14,22,Homme,Type 1
+523,5,14,0,Homme,Type 1
+524,7.67,15,11,Femme,Type 1
+525,8.4,13,17,Homme,Type 3
+526,11.25,13,14,Homme,Type 3
+527,6.25,14,12,Femme,Type 1
+528,13.26,12,16,Homme,Type 3
+529,11.25,17,32,Femme,Type 2
+530,6.75,10,41,Homme,Type 3
+531,7.7,13,8,Femme,Type 2
+532,5.26,8,38,Femme,Type 2
+533,13.71,12,43,Homme,Type 2
+534,8,12,43,Femme,Type 2

M1/General Linear Models/TP3/TP3.rmd

@@ -0,0 +1,134 @@
+```{r}
+setwd('/Users/arthurdanjou/Workspace/studies/M1/General Linear Models/TP3')
+```
+
+# Question 1 : Import dataset and check variables
+
+```{r}
+library(dplyr)
+ozone <- read.table("ozone.txt", header = TRUE, sep = " ", dec = ".")
+ozone$vent <- as.factor(ozone$vent)
+ozone$temps <- as.factor(ozone$temps)
+ozone <- ozone %>% mutate(across(where(is.character), as.numeric))
+ozone <- ozone %>% mutate(across(where(is.integer), as.numeric))
+paged_table(ozone)
+```
+
+# Question 2 : max03 ~ T12
+
+```{r}
+model_T12 <- lm(maxO3 ~ T12, data = ozone)
+summary(model_T12)
+```
+
+```{r}
+library(ggplot2)
+
+ggplot(ozone, aes(x = T12, y = maxO3)) +
+  geom_smooth(method = 'lm', se = T) +
+  geom_point(col = 'red', size = 0.5) +
+  labs(title = "maxO3 ~ T12") +
+  theme_minimal()
+```
+
+```{r}
+library(ggfortify)
+library(car)
+
+autoplot(model_T12, 1:4)
+durbinWatsonTest(model_T12)
+```
+
+The p-value of the Durbin-Watson test is 0, so [P3] is not valid. The residuals are correlated.
+
+The model is not valid.
+
+# Question 3 : max03 ~ T12 + temps
+
+```{r}
+library(ggplot2)
+
+ggplot(ozone, aes(y = maxO3, x = temps, colour = temps, fill = temps)) +
+  geom_boxplot(alpha = 0.5, outlier.alpha = 0) +
+  geom_jitter(width = 0.25, size = 1) +
+  stat_summary(fun = mean, colour = "black", geom = "point", shape = 18, size = 3)
+```
+
+```{r}
+model_temps <- lm(maxO3 ~ -1 + temps, data = ozone)
+summary(model_temps)
+```
+
+```{r}
+autoplot(model_temps, 1:4)
+durbinWatsonTest(model_temps)
+```
+```{r}
+model_vent <- lm(maxO3 ~ -1 + vent, data = ozone)
+summary(model_vent)
+```
+
+```{r}
+autoplot(model_vent, 1:4)
+durbinWatsonTest(model_vent)
+```
+The p-value of the Durbin-Watson test is 0, so [P3] is not valid. The residuals are correlated.
+
+The model is not valid.
+```{r}
+model_temps_vent <- lm(maxO3 ~ temps * vent, data = ozone)
+summary(model_temps_vent)
+```
+
+```{r}
+autoplot(model_temps_vent, 1:4)
+durbinWatsonTest(model_temps_vent)
+```
+
+# Question 4 : Multiple linear regression
+```{r}
+model <- lm(maxO3 ~ ., data = ozone)
+summary(model)
+```
+
+```{r}
+autoplot(model, 1:4)
+durbinWatsonTest(model)
+```
+
+[P1] is verified as the 'Residuals vs Fitted' plot shows that the points are well distributed around 0
+[P2] is verified as the 'Scale-Location' plot shows that the points are well distributed around 1
+[P4] is verified as the 'QQPlot' is aligned with the 'y=x' line
+
+[P3] is verified as the p-value is 0.7 > 0.05, so we do not reject H0 so the residuals are not auto-correlated
+
+The model is valid.
+
+```{r}
+library(GGally)
+ggpairs(ozone, progress = FALSE)
+```
+```{r}
+library(MASS)
+
+model_backward <- stepAIC(model, ~., trace = FALSE, direction = c("backward"))
+summary(model_backward)
+```
+
+```{r}
+AIC(model_backward)
+autoplot(model_backward, 1:4)
+durbinWatsonTest(model_backward)
+```
+
+# Question 5 : Prediction
+```{r}
+new_obs <- list(
+  T12 = 18,
+  Ne9 = 3,
+  Vx9 = 0.7,
+  maxO3v = 85
+)
+predict(model_backward, new_obs, interval = "confidence")
+
+```

M1/General Linear Models/TP3/ozone.txt

@@ -0,0 +1,113 @@
+maxO3 T9 T12 T15 Ne9 Ne12 Ne15 Vx9 Vx12 Vx15 maxO3v vent temps
+87 15.6 18.5 18.4 4 4 8 0.6946 -1.7101 -0.6946 84 Nord Sec
+82 17 18.4 17.7 5 5 7 -4.3301 -4 -3 87 Nord Sec
+92 15.3 17.6 19.5 2 5 4 2.9544 1.8794 0.5209 82 Est Sec
+114 16.2 19.7 22.5 1 1 0 0.9848 0.3473 -0.1736 92 Nord Sec
+94 17.4 20.5 20.4 8 8 7 -0.5 -2.9544 -4.3301 114 Ouest Sec
+80 17.7 19.8 18.3 6 6 7 -5.6382 -5 -6 94 Ouest Pluie
+79 16.8 15.6 14.9 7 8 8 -4.3301 -1.8794 -3.7588 80 Ouest Sec
+79 14.9 17.5 18.9 5 5 4 0 -1.0419 -1.3892 99 Nord Sec
+101 16.1 19.6 21.4 2 4 4 -0.766 -1.0261 -2.2981 79 Nord Sec
+106 18.3 21.9 22.9 5 6 8 1.2856 -2.2981 -3.9392 101 Ouest Sec
+101 17.3 19.3 20.2 7 7 3 -1.5 -1.5 -0.8682 106 Nord Sec
+90 17.6 20.3 17.4 7 6 8 0.6946 -1.0419 -0.6946 101 Sud Sec
+72 18.3 19.6 19.4 7 5 6 -0.8682 -2.7362 -6.8944 90 Sud Sec
+70 17.1 18.2 18 7 7 7 -4.3301 -7.8785 -5.1962 72 Ouest Pluie
+83 15.4 17.4 16.6 8 7 7 -4.3301 -2.0521 -3 70 Nord Sec
+88 15.9 19.1 21.5 6 5 4 0.5209 -2.9544 -1.0261 83 Ouest Sec
+145 21 24.6 26.9 0 1 1 -0.342 -1.5321 -0.684 121 Ouest Sec
+81 16.2 22.4 23.4 8 3 1 0 0.3473 -2.5712 145 Nord Sec
+121 19.7 24.2 26.9 2 1 0 1.5321 1.7321 2 81 Est Sec
+146 23.6 28.6 28.4 1 1 2 1 -1.9284 -1.2155 121 Sud Sec
+121 20.4 25.2 27.7 1 0 0 0 -0.5209 1.0261 146 Nord Sec
+146 27 32.7 33.7 0 0 0 2.9544 6.5778 4.3301 121 Est Sec
+108 24 23.5 25.1 4 4 0 -2.5712 -3.8567 -4.6985 146 Sud Sec
+83 19.7 22.9 24.8 7 6 6 -2.5981 -3.9392 -4.924 108 Ouest Sec
+57 20.1 22.4 22.8 7 6 7 -5.6382 -3.8302 -4.5963 83 Ouest Pluie
+81 19.6 25.1 27.2 3 4 4 -1.9284 -2.5712 -4.3301 57 Sud Sec
+67 19.5 23.4 23.7 5 5 4 -1.5321 -3.0642 -0.8682 81 Ouest Sec
+70 18.8 22.7 24.9 5 2 1 0.684 0 1.3681 67 Nord Sec
+106 24.1 28.4 30.1 0 0 1 2.8191 3.9392 3.4641 70 Est Sec
+139 26.6 30.1 31.9 0 1 4 1.8794 2 1.3681 106 Sud Sec
+79 19.5 18.8 17.8 8 8 8 0.6946 -0.866 -1.0261 139 Ouest Sec
+93 16.8 18.2 22 8 8 6 0 0 1.2856 79 Sud Pluie
+97 20.8 23.7 25 2 3 4 0 1.7101 -2.7362 93 Nord Sec
+113 17.5 18.2 22.7 8 8 5 -3.7588 -3.9392 -4.6985 97 Ouest Pluie
+72 18.1 21.2 23.9 7 6 4 -2.5981 -3.9392 -3.7588 113 Ouest Pluie
+88 19.2 22 25.2 4 7 4 -1.9696 -3.0642 -4 72 Ouest Sec
+77 19.4 20.7 22.5 7 8 7 -6.5778 -5.6382 -9 88 Ouest Sec
+71 19.2 21 22.4 6 4 6 -7.8785 -6.8937 -6.8937 77 Ouest Sec
+56 13.8 17.3 18.5 8 8 6 1.5 -3.8302 -2.0521 71 Ouest Pluie
+45 14.3 14.5 15.2 8 8 8 0.684 4 2.9544 56 Est Pluie
+67 15.6 18.6 20.3 5 7 5 -3.2139 -3.7588 -4 45 Ouest Pluie
+67 16.9 19.1 19.5 5 5 6 -2.2981 -3.7588 0 67 Ouest Pluie
+84 17.4 20.4 21.4 3 4 6 0 0.3473 -2.5981 67 Sud Sec
+63 15.1 20.5 20.6 8 6 6 2 -5.3623 -6.1284 84 Ouest Pluie
+69 15.1 15.6 15.9 8 8 8 -4.5963 -3.8302 -4.3301 63 Ouest Pluie
+92 16.7 19.1 19.3 7 6 4 -2.0521 -4.4995 -2.7362 69 Nord Sec
+88 16.9 20.3 20.7 6 6 5 -2.8191 -3.4641 -3 92 Ouest Pluie
+66 18 21.6 23.3 8 6 5 -3 -3.5 -3.2139 88 Sud Sec
+72 18.6 21.9 23.6 4 7 6 0.866 -1.9696 -1.0261 66 Ouest Sec
+81 18.8 22.5 23.9 6 3 2 0.5209 -1 -2 72 Nord Sec
+83 19 22.5 24.1 2 4 6 0 -1.0261 0.5209 81 Nord Sec
+149 19.9 26.9 29 3 4 3 1 -0.9397 -0.6428 83 Ouest Sec
+153 23.8 27.7 29.4 1 1 4 0.9397 1.5 0 149 Nord Sec
+159 24 28.3 26.5 2 2 7 -0.342 1.2856 -2 153 Nord Sec
+149 23.3 27.6 28.8 4 6 3 0.866 -1.5321 -0.1736 159 Ouest Sec
+160 25 29.6 31.1 0 3 5 1.5321 -0.684 2.8191 149 Sud Sec
+156 24.9 30.5 32.2 0 1 4 -0.5 -1.8794 -1.2856 160 Ouest Sec
+84 20.5 26.3 27.8 1 0 2 -1.3681 -0.6946 0 156 Nord Sec
+126 25.3 29.5 31.2 1 4 4 3 3.7588 5 84 Est Sec
+116 21.3 23.8 22.1 7 7 8 0 -2.3941 -1.3892 126 Sud Pluie
+77 20 18.2 23.6 5 7 6 -3.4641 -2.5981 -3.7588 116 Ouest Pluie
+63 18.7 20.6 20.3 6 7 7 -5 -4.924 -5.6382 77 Ouest Pluie
+54 18.6 18.7 17.8 8 8 8 -4.6985 -2.5 -0.8682 63 Sud Pluie
+65 19.2 23 22.7 8 7 7 -3.8302 -4.924 -5.6382 54 Ouest Sec
+72 19.9 21.6 20.4 7 7 8 -3 -4.5963 -5.1962 65 Ouest Pluie
+60 18.7 21.4 21.7 7 7 7 -5.6382 -6.0622 -6.8937 72 Ouest Pluie
+70 18.4 17.1 20.5 3 6 3 -5.9088 -3.2139 -4.4995 60 Nord Pluie
+77 17.1 20 20.8 4 5 4 -1.9284 -1.0261 0.5209 70 Nord Sec
+98 17.8 22.8 24.3 1 1 0 0 -1.5321 -1 77 Ouest Pluie
+111 20.9 25.2 26.7 1 5 2 -1.0261 -3 -2.2981 98 Ouest Sec
+75 18.8 20.5 26 8 7 1 -0.866 0 0 111 Nord Sec
+116 23.5 29.8 31.7 1 3 5 1.8794 1.3681 0.6946 75 Sud Sec
+109 20.8 23.7 26.6 8 5 4 -1.0261 -1.7101 -3.2139 116 Sud Sec
+67 18.8 21.1 18.9 7 7 8 -5.3623 -5.3623 -2.5 86 Ouest Pluie
+76 17.8 21.3 24 7 5 5 -3.0642 -2.2981 -3.9392 67 Ouest Pluie
+113 20.6 24.8 27 1 1 2 1.3681 0.8682 -2.2981 76 Sud Sec
+117 21.6 26.9 28.6 6 6 4 1.5321 1.9284 1.9284 113 Sud Pluie
+131 22.7 28.4 30.1 5 3 3 0.1736 -1.9696 -1.9284 117 Ouest Sec
+166 19.8 27.2 30.8 4 0 1 0.6428 -0.866 0.684 131 Ouest Sec
+159 25 33.5 35.5 1 1 1 1 0.6946 -1.7101 166 Sud Sec
+100 20.1 22.9 27.6 8 8 6 1.2856 -1.7321 -0.684 159 Ouest Sec
+114 21 26.3 26.4 7 4 5 3.0642 2.8191 1.3681 100 Est Sec
+112 21 24.4 26.8 1 6 3 4 4 3.7588 114 Est Sec
+101 16.9 17.8 20.6 7 7 7 -2 -0.5209 1.8794 112 Nord Pluie
+76 17.5 18.6 18.7 7 7 7 -3.4641 -4 -1.7321 101 Ouest Sec
+59 16.5 20.3 20.3 5 7 6 -4.3301 -5.3623 -4.5 76 Ouest Pluie
+78 17.7 20.2 21.5 5 5 3 0 0.5209 0 59 Nord Pluie
+76 17.3 22.7 24.6 4 5 6 -2.9544 -2.9544 -2 78 Ouest Pluie
+55 15.3 16.8 19.2 8 7 5 -1.8794 -1.8794 -2.3941 76 Ouest Pluie
+71 15.9 19.2 19.5 7 5 3 -6.1284 0 -1.3892 55 Nord Pluie
+66 16.2 18.9 19.3 2 5 6 -1.3681 -0.8682 1.7101 71 Nord Pluie
+59 18.3 18.3 19 7 7 7 -3.9392 -1.9284 -1.7101 66 Nord Pluie
+68 16.9 20.8 22.5 6 5 7 -1.5 -3.4641 -3.0642 59 Ouest Pluie
+63 17.3 19.8 19.4 7 8 8 -4.5963 -6.0622 -4.3301 68 Ouest Sec
+78 14.2 22.2 22 5 5 6 -0.866 -5 -5 62 Ouest Sec
+74 15.8 18.7 19.1 8 7 7 -4.5963 -6.8937 -7.5175 78 Ouest Pluie
+71 15.2 17.9 18.6 6 5 1 -1.0419 -1.3681 -1.0419 74 Nord Pluie
+69 17.1 17.7 17.5 6 7 8 -5.1962 -2.7362 -1.0419 71 Nord Pluie
+71 15.4 17.7 16.6 4 5 5 -3.8302 0 1.3892 69 Nord Sec
+60 13.7 14 15.8 4 5 4 0 3.2139 0 71 Nord Pluie
+42 12.7 14.3 14.9 8 7 7 -2.5 -3.2139 -2.5 60 Nord Pluie
+65 14.8 16.3 15.9 7 7 7 -4.3301 -6.0622 -5.1962 42 Ouest Pluie
+71 15.5 18 17.4 7 7 6 -3.9392 -3.0642 0 65 Ouest Sec
+96 11.3 19.4 20.2 3 3 3 -0.1736 3.7588 3.8302 71 Est Pluie
+98 15.2 19.7 20.3 2 2 2 4 5 4.3301 96 Est Sec
+92 14.7 17.6 18.2 1 4 6 5.1962 5.1423 3.5 98 Nord Sec
+76 13.3 17.7 17.7 7 7 6 -0.9397 -0.766 -0.5 92 Ouest Pluie
+84 13.3 17.7 17.8 3 5 6 0 -1 -1.2856 76 Sud Sec
+77 16.2 20.8 22.1 6 5 5 -0.6946 -2 -1.3681 71 Sud Pluie
+99 16.9 23 22.6 6 4 7 1.5 0.8682 0.8682 77 Sud Sec
+83 16.9 19.8 22.1 6 5 3 -4 -3.7588 -4 99 Ouest Pluie
+70 15.7 18.6 20.7 7 7 7 0 -1.0419 -4 83 Sud Sec

M1/General Linear Models/TP4/TP4.rmd

@@ -0,0 +1,94 @@
+```{r}
+setwd('/Users/arthurdanjou/Workspace/studies/M1/General Linear Models/TP4')
+
+set.seed(0911)
+library(ggplot2)
+library(gridExtra)
+library(cowplot)
+library(plotly) # interactif plot
+library(ggfortify) # diagnostic plot
+library(forestmodel) # plot odd ratio
+library(arm) # binnedplot diagnostic plot in GLM
+
+library(knitr)
+library(dplyr)
+library(tidyverse)
+library(tidymodels)
+library(broom) # funtion augment to add columns to the original data that was modeled
+library(effects) # plot effect of covariate/factor
+library(questionr) # odd ratio
+
+library(lmtest) # LRtest
+library(survey) # Wald test
+library(vcdExtra) # deviance test
+
+library(rsample)   # for data splitting
+library(glmnet)
+library(nnet) # multinom, glm
+library(caret)
+library(ROCR)
+#library(PRROC) autre package pour courbe roc et courbe pr
+library(ISLR) # dataset for statistical learning
+
+ggplot2::theme_set(ggplot2::theme_light())# Set the graphical theme
+```
+```{r}
+car <- read.table('car_income.txt', header = TRUE, sep = ';')
+car %>% rmarkdown::paged_table()
+summary(car)
+```
+
+```{r}
+model_purchase <- glm(purchase ~ ., data = car, family = "binomial")
+summary(model_purchase)
+```
+
+```{r}
+p1 <- car %>%
+  ggplot(aes(y = purchase, x = income + age)) +
+  geom_point(alpha = .15) +
+  geom_smooth(method = "lm") +
+  ggtitle("Linear regression model fit") +
+  xlab("Income") +
+  ylab("Probability of Purchase")
+
+
+p2 <- car %>%
+  ggplot(aes(y = purchase, x = income + age)) +
+  geom_point(alpha = .15) +
+  geom_smooth(method = "glm", method.args = list(family = "binomial")) +
+  ggtitle("Logistic regression model fit") +
+  xlab("Income") +
+  ylab("Probability of Purchase")
+
+ggplotly(p1)
+ggplotly(p2)
+```
+
+```{r}
+car <- car %>%
+  mutate(old = ifelse(car$age > 3, 1, 0))
+car <- car %>%
+  mutate(rich = ifelse(car$income > 40, 1, 0))
+model_old <- glm(purchase ~ age + income + rich + old, data = car, family = "binomial")
+summary(model_old)
+```
+
+# Diabetes in Pima Indians
+```{r}
+library(MASS)
+pima.tr <- Pima.tr
+pima.te <- Pima.te
+
+model_train_pima <- glm(type ~ npreg + glu + bp + skin + bmi + ped + age, data = pima.tr, family = "binomial")
+summary(model_train_pima)
+```
+```{r}
+pima.te$pred <- predict(model_train_pima, newdata = pima.te, type = "response")
+pima.te$pred <- ifelse(pima.te$pred > 0.55, "Yes", "No")
+pima.te$pred <- as.factor(pima.te$pred)
+pima.te$type <- as.factor(pima.te$type)
+
+# Confusion matrix
+confusionMatrix(data = pima.te$type, reference = pima.te$pred, positive = 'Yes')
+```

M1/General Linear Models/TP4/car_income.txt

@@ -0,0 +1,34 @@
+purchase;income;age
+0;32;3
+0;45;2
+1;60;2
+0;53;1
+0;25;4
+1;68;1
+1;82;2
+1;38;5
+0;67;2
+1;92;2
+1;72;3
+0;21;5
+0;26;3
+1;40;4
+0;33;3
+0;45;1
+1;61;2
+0;16;3
+1;18;4
+0;22;6
+0;27;3
+1;35;3
+1;40;3
+0;10;4
+0;24;3
+1;15;4
+0;23;3
+0;19;5
+1;22;2
+0;61;2
+0;21;3
+1;32;5
+0;17;1

M1/Monte Carlo Methods/Exercise1.rmd

@@ -0,0 +1,8 @@
+# Exercise 1 : Uniform
+
+```{r}
+n <- 10e4
+U <- runif(n)
+X <- 5 * (U <= 0.4) + 6 * (0.4 < U & U <= 0.6) + 7 * (0.6 < U & U <= 0.9) + 8 * (0.9 < U)
+barplot(table(X)/n)
+```

M1/Monte Carlo Methods/Exercise10.rmd

@@ -0,0 +1,40 @@
+# Exercise 10 : Integral Calculation.
+
+## Estimation of δ using the classical Monte Carlo
+
+### Uniform + Normal distributions
+
+```{r}
+n <- 10e4
+X <- runif(n, 0, 5)
+Y <- rnorm(n, 0, sqrt(2))
+Y[Y <= 2] <- 0
+
+h <- function(x, y) {
+  5 *
+    sqrt(pi) *
+    sqrt(x + y) *
+    sin(y^4) *
+    exp(-3 * x / 2)
+}
+
+I1 <- mean(h(X, Y))
+I1
+```
+
+### Exponential + Normal distributions
+
+```{r}
+n <- 10e4
+X <- runif(n, 0, 5)
+Y <- rexp(n, 3 / 2)
+Y[Y <= 2] <- 0
+X[X <= 5] <- 0
+
+h <- function(x, y) {
+  4 / 3 * sqrt(pi) * sqrt(x + y) * sin(y^4)
+}
+
+I2 <- mean(h(X, Y))
+I2
+```

M1/Monte Carlo Methods/Exercise11.rmd

@@ -0,0 +1,35 @@
+# Exercise 11 : Importance Sampling, Cauchy Distribution
+```{r}
+set.seed(110)
+n <- 10000
+a <- 50
+k <- 5
+
+f <- function(x) {
+  1 / (pi * (1 + x^2))
+}
+
+g <- function(x, a, k) {
+  k * a^k / x^(k + 1) * (x >= a)
+}
+
+h <- function(x, a) {
+  x >= a
+}
+
+G_inv <- function(x, a, k) {
+  a / (1 - x)^(1 / k)
+}
+
+# Classical Monte Carlo method
+x1 <- rcauchy(n, 0, 1)
+p1 <- h(x1, a)
+
+# Importance sampling
+x2 <- G_inv(runif(n), a, k)
+p2 <- f(x2) / g(x2, a, k) * h(x2, a)
+
+# Results (cat the results and the var of the estimators)
+cat(sprintf("Classical Monte Carlo: mean = %f, variance = %f \n", mean(p1), var(p1)))
+cat(sprintf("Importance sampling: mean = %f, variance = %f", mean(p2), var(p2)))
+```

M1/Monte Carlo Methods/Exercise12.rmd

@@ -0,0 +1,48 @@
+# Exercise 12 : Rejection vs Importance Sampling
+```{r}
+set.seed(123)
+n <- 10000
+
+f <- function(x, y) {
+  3 / 2 * exp(-3 / 2 * x) * (x > 0) * 1 / (2 * sqrt(pi)) *
+    exp(-y^2 / 4) *
+    (x > 0)
+}
+
+g <- function(x, y, lambda) {
+  (3 / 2 * exp(-3 / 2 * x)) *
+    (x >= 0) *
+    (lambda * exp(-lambda * (y - 2))) *
+    (y >= 2)
+}
+
+h <- function(x, y) {
+  sqrt(x + y) *
+    sin(y^4) *
+    (x <= 5) *
+    (x > 0) *
+    (y >= 2) *
+    (4 * sqrt(pi) / 3)
+}
+
+X <- rexp(n, 3 / 2)
+Y <- rexp(n, 2) + 2
+
+mean(h(X, Y) * f(X, Y) / g(X, Y, 0.4))
+```
+
+### Monte Carlo method
+
+```{r}
+set.seed(123)
+n <- 10e4
+
+X <- rexp(n, 3 / 2)
+Y <- rexp(n, 3 / 2) + 2
+
+X[X > 5] <- 0
+X[X < 0] <- 0
+Y[Y < 2] <- 0
+
+mean(h(X, Y))
+```

M1/Monte Carlo Methods/Exercise13.rmd

@@ -0,0 +1,52 @@
+# Exercise 13 : Gaussian integral and Variance reduction
+
+```{r}
+set.seed(123)
+n <- 10000
+
+# Normal distribution
+h1 <- function(x) {
+  sqrt(2 * pi) *
+    exp(-x^2 / 2) *
+    (x <= 2) *
+    (x >= 0)
+}
+
+# Uniform (0, 2) distribution
+h2 <- function(x) {
+  2 * exp(-x^2)
+}
+
+X1 <- rnorm(n)
+X2 <- runif(n, 0, 2)
+
+cat(sprintf("Integral of h1(x) using normal distribution is %f and variance is %f \n", mean(h1(X1)), var(h1(X1))))
+cat(sprintf("Integral of h2(x) using normal distribution is %f and variance is %f \n", mean(h2(X2)), var(h2(X2))))
+
+X3 <- 2 - X2
+cat(sprintf("Integral of h2(x) using normal distribution is %f and variance is %f \n",
+            (mean(h2(X3)) + mean(h2(X2))) / 2,
+            (var(h2(X3)) +
+              var(h2(X2)) +
+              2 * cov(h2(X2), h2(X3))) / 4))
+
+X4 <- -X1
+cat(sprintf("Integral of h2(x) using normal distribution is %f and variance is %f",
+            (mean(h1(X1)) + mean(h1(X4))) / 2,
+            (var(h1(X1)) +
+              var(h1(X4)) +
+              2 * cov(h1(X1), h1(X4))) / 4))
+```
+
+## K-th moment of a uniform random variable on [0, 2]
+
+```{r}
+k <- 1:10
+moment <- round(2^k / (k + 1), 2)
+cat(sprintf("The k-th moment for k ∈ N* of a uniform random variable on [0, 2] is %s", paste(moment, collapse = ", ")))
+```
+
+
+```{r}
+
+```

M1/Monte Carlo Methods/Exercise2.rmd

@@ -0,0 +1,46 @@
+# Exercise 2 : Exponential distribution and related distributions
+
+### Question 1
+```{r}
+n <- 10000
+u <- runif(n)
+x <- -1 / 2 * log(1 - u)
+hist(x, breaks = 50, freq = FALSE)
+curve(dexp(x, rate = 2), add = TRUE, col = "red")
+
+qqplot(x, rexp(n, rate = 2))
+```
+
+### Question 2
+
+```{r}
+lambda <- 1.5
+n <- 10000
+d <- 10
+S <- numeric(n)
+for (i in 1:n) {
+  u <- runif(d)
+  x <- -1 / lambda * log(1 - u)
+  S[i] <- sum(x)
+}
+hist(S, freq = FALSE, breaks = 50)
+curve(dgamma(x, shape = d, rate = lambda), add = TRUE, col = "red")
+```
+
+### Question 3
+```{r}
+n <- 10000
+S <- numeric(n)
+i <- 1
+for (j in (1:n)) {
+  x <- -1 / 4 * log(1 - runif(1))
+  while (x <= 1) {
+    i <- i + 1
+    x <- x - 1 / 4 * log(1 - runif(1))
+  }
+  S[j] <- i
+  i <- 1
+}
+hist(S, freq = FALSE)
+curve(dpois(S, lambda = 4), add = TRUE, col = "red")
+```

M1/Monte Carlo Methods/Exercise3.rmd

@@ -0,0 +1,17 @@
+# Exercise 3 : Box Muller Algo
+
+```{r}
+BM <- function(n) {
+  U1 <- runif(n)
+  U2 <- runif(n)
+  X1 <- sqrt(-2 * log(U1)) * cos(2 * pi * U2)
+  X2 <- sqrt(-2 * log(U1)) * sin(2 * pi * U2)
+  return(c(X1, X2))
+}
+
+n <- 10e4
+X <- BM(n)
+
+hist(X, breaks = 50, freq = FALSE)
+curve(dnorm(x), add = TRUE, col = "red")
+```

M1/Monte Carlo Methods/Exercise5.rmd

@@ -0,0 +1,12 @@
+# Exercise 5 : Simulation of Brownian Motion
+
+```{r}
+n <- 1:1100
+brownian <- function (i) {
+  return ((i >= 1 & i <= 100)*(i/100) + (i >= 101 & i <= 110)*(1 + (i - 100)/10) + (i >= 111 & i <= 1110)*(2 + (i - 110)/1000))
+}
+t <- brownian(n)
+W0 <- 0
+Wt <- W0 + sqrt(t) * rnorm(1100)
+plot(t, Wt, type = "o")
+```

M1/Monte Carlo Methods/Exercise6.rmd

@@ -0,0 +1,25 @@
+# Exercise 6 : Rejection - A First Example
+
+```{r}
+f <- function(x) {
+  2 / pi * sqrt(1 - x^2) * (x >= -1 & x <= 1)
+}
+
+n <- 10000
+
+M <- 4 / pi
+g <- function(x) {
+  1 / 2 * (x >= -1 & x <= 1)
+}
+
+x <- numeric(0)
+while (length(x) < n) {
+  U <- runif(1)
+  X <- runif(1, -1, 1)
+  x <- append(x, X[U <= (f(X) / (M * g(X)))])
+}
+
+t <- seq(-1, 1, 0.01)
+hist(x, freq = FALSE, breaks = 50)
+lines(t, f(t), col = "red", lwd = 2)
+```

M1/Monte Carlo Methods/Exercise7.rmd

@@ -0,0 +1,32 @@
+# Exercise 7 : Rejection
+
+```{r}
+n <- 5000
+
+f <- function(x, y) {
+  return(
+    1 / pi * (x^2 + y^2 <= 1)
+  )
+}
+
+M <- 4 / pi
+g <- function(x, y) {
+  return(
+    1 / 4 * (x >= -1 & x <= 1 & y >= -1 & y <= 1)
+  )
+}
+
+x <- NULL
+y <- NULL
+while (length(x) < n) {
+  U <- runif(1)
+  X <- runif(1, -1, 1)
+  Y <- runif(1, -1, 1)
+  x <- append(x, X[U <= (f(X, Y) / (M * g(X, Y)))])
+  y <- append(y, Y[U <= (f(X, Y) / (M * g(X, Y)))])
+}
+
+t <- seq(-1, 1, 0.01)
+plot(x, y)
+contour(t, t, outer(t, t, Vectorize(f)), add = TRUE, col = "red", lwd = 2)
+```

M1/Monte Carlo Methods/Exercise8.rmd

@@ -0,0 +1,65 @@
+# Exercise 8 - a : Truncated Normal Distribution
+
+```{r}
+f <- function(x, b, mean, sd) {
+  1 / (sqrt(2 * pi * sd^2) * pnorm((mean - b) / sd)) *
+    exp(-(x - mean)^2 / (2 * sd^2)) *
+    (x >= b)
+}
+
+M <- function(b, mean, sd) {
+  1 / pnorm((mean - b) / sd)
+}
+
+g <- function(x, b, mean, sd) {
+  1 / sqrt(2 * pi * sd^2) *
+    exp(-(x - mean)^2 / (2 * sd^2))
+}
+
+n <- 10000
+mean <- 0
+sd <- 2
+b <- 2
+
+x <- numeric(0)
+while (length(x) < n) {
+  U <- runif(1)
+  X <- rnorm(1, mean, sd)
+  x <- append(x, X[U <= (f(X, b, mean, sd) / (M(b, mean, sd) * g(X, b, mean, sd)))])
+}
+
+t <- seq(b, 7, 0.01)
+hist(x, freq = FALSE, breaks = 35)
+lines(t, f(t, b, mean, sd), col = "red", lwd = 2)
+```
+
+# Exercise 8 - b : Truncated Exponential Distribution
+```{r}
+f <- function(x, b, lambda) {
+  lambda * exp(-lambda * (x - b)) * (x >= b)
+}
+
+M <- function(b, lambda) {
+  exp(lambda * b)
+}
+
+g <- function(x, lambda) {
+  lambda * exp(-lambda * x)
+}
+
+n <- 10000
+b <- 2
+lambda <- 1
+
+x <- numeric(0)
+while (length(x) < n) {
+  U <- runif(1)
+  X <- rexp(1, lambda)
+  x <- append(x, X[U <= (f(X, b, lambda) / (M(b, lambda) * g(X, lambda)))])
+}
+
+t <- seq(b, 7, 0.01)
+hist(x, freq = FALSE, breaks = 35)
+lines(t, f(t, b, lambda), col = "red", lwd = 2)
+```
+

M1/Monte Carlo Methods/Exercise9.rmd

@@ -0,0 +1,37 @@
+# Exercise 9 : Estimation of Pi
+
+## Methode 1
+
+```{r}
+n <- 15e4
+
+pi_1 <- function(n) {
+  U <- runif(n, 0, 1)
+  return(4 / n * sum(sqrt(1 - U^2)))
+}
+pi_1(n)
+```
+
+## Methode 2
+```{r}
+n <- 15e4
+
+pi_2 <- function(n) {
+  U1 <- runif(n, 0, 1)
+  U2 <- runif(n, 0, 1)
+  return(4 / n * sum(U1^2 + U2^2 <= 1))
+}
+pi_2(n)
+```
+
+## Best Estimator of pi
+```{r}
+n <- 1000
+m <- 15e4
+
+sample_1 <- replicate(n, pi_1(m))
+sample_2 <- replicate(n, pi_2(m))
+
+cat(sprintf("[Methode 1] Mean: %s. Variance: %s \n", mean(sample_1), var(sample_1)))
+cat(sprintf("[Methode 2] Mean: %s. Variance: %s", mean(sample_2), var(sample_2)))
+```

M1/Monte Carlo Methods/Project 1/003_rapport_DANJOU_DUROUSSEAU.rmd

@@ -0,0 +1,909 @@
+---
+title: "Groupe 03 Projet DANJOU - DUROUSSEAU"
+output:
+  pdf_document:
+    toc: yes
+    toc_depth: 3
+    fig_caption: yes
+---
+
+# Exercise 1 : Negative weighted mixture
+
+## Definition
+
+### Question 1
+
+The conditions for a function f to be a probability density are :
+
+-   f is defined on $\mathbb{R}$
+-   f is non-negative, ie $f(x) \ge 0$, $\forall x \in \mathbb{R}$
+-   f is Lebesgue-integrable
+-   and $\int_{\mathbb{R}} f(x) \,dx = 1$
+
+The function f, to be a density, needs to be non-negative, ie $f(|x|) \ge 0$ when $|x| \rightarrow \infty$
+
+We have, when $|x| \rightarrow \infty$, $f_i(|x|) \sim exp(\frac{-x^2}{\sigma_i^2})$ for $i = 1, 2$
+
+Then, $f(|x|) \sim exp(\frac{-x^2}{\sigma_1^2}) - exp(\frac{-x^2}{\sigma_2^2})$
+
+We want $f(|x|) \ge 0$, ie, $exp(\frac{-x^2}{\sigma_1^2}) - exp(\frac{-x^2}{\sigma_2^2}) \ge 0$
+
+$\Leftrightarrow \sigma_1^2 \ge \sigma_2^2$
+
+We can see that $f_1$ dominates the tail behavior.
+
+\
+
+### Question 2
+
+For given parameters $(\mu_1, \sigma_1^2)$ and $(\mu_2, \sigma_2^2)$, we have $\forall x \in \mathbb{R}$, $f(x) \ge 0$
+
+$\Leftrightarrow \frac{1}{\sigma_1} exp(\frac{-(x-\mu_1)^2}{2 \sigma_1^2}) \ge \frac{a}{\sigma_2} exp(\frac{-(x-\mu_2)^2}{2 \sigma_2^2})$
+
+$\Leftrightarrow 0 < a \le a^* = \min_{x \in \mathbb{R}} \frac{f_1(x)}{f_2(x)} = \min_{x \in \mathbb{R}} \frac{\sigma_2}{\sigma_1} exp(\frac{(x-\mu_2)^2}{2 \sigma_2^2} - \frac{(x-\mu_1)^2}{2 \sigma_1^2})$
+
+To find $a^*$, we just have to minimize $g(x) := \frac{(x-\mu_2)^2}{2 \sigma_2^2} - \frac{(x-\mu_1)^2}{2 \sigma_1^2}$
+
+First we derive $g$: $\forall x \in \mathbb{R}, g^{\prime}(x) = \frac{x - \mu_2}{\sigma_2^2} - \frac{x - \mu_1}{\sigma_1^2}$
+
+We search $x^*$ such that $g^{\prime}(x^*) = 0$
+
+$\Leftrightarrow x^* = \frac{\mu_2 \sigma_1^2 - \mu_1 \sigma_2^2}{\sigma_1^2 - \sigma_2^2}$
+
+Then, we compute $a^* = \frac{f_1(x^*)}{f_2(x^*)}$
+
+We call $C \in \mathbb{R}$ the normalization constant such that $f(x) = C (f_1(x) - af_2(x))$
+
+To find $C$, we know that $1 = \int_{\mathbb{R}} f(x) \,dx = \int_{\mathbb{R}} C (f_1(x) - af_2(x)) \,dx = C \int_{\mathbb{R}} f_1(x) \,dx - Ca \int_{\mathbb{R}} f_2(x) \,dx = C(1-a)$ as $f_1$ and $f_2$ are density functions and by linearity of the integrals.
+
+$\Leftrightarrow C = \frac{1}{1-a}$
+
+### Question 3
+
+```{r}
+f <- function(a, mu1, mu2, s1, s2, x) {
+  fx <- dnorm(x, mu1, s1) - a * dnorm(x, mu2, s2)
+  fx[fx < 0] <- 0
+  return(fx / (1 - a))
+}
+
+a_star <- function(mu1, mu2, s1, s2) {
+  x_star <- (mu2 * s1^2 - mu1 * s2^2) / (s1^2 - s2^2)
+  return(dnorm(x_star, mu1, s1) / dnorm(x_star, mu2, s2))
+}
+```
+
+```{r}
+mu1 <- 0
+mu2 <- 1
+s1 <- 3
+s2 <- 1
+
+x <- seq(-10, 10, length.out = 1000)
+as <- a_star(mu1, mu2, s1, s2)
+a_values <- c(0.1, 0.2, 0.3, 0.4, 0.5, as)
+
+plot(x, f(as, mu1, mu2, s1, s2, x),
+     type = "l",
+     col = "red",
+     xlab = "x",
+     ylab = "f(a, mu1, mu2, s1, s2, x)",
+     main = "Density function of f(a, mu1, mu2, s1, s2, x) for different a"
+)
+for (i in (length(a_values) - 1):1) {
+  lines(x, f(a_values[i], mu1, mu2, s1, s2, x), lty = 3, col = "blue")
+}
+legend("topright", legend = c("a = a*", "a != a*"), col = c("red", "blue"), lty = 1)
+```
+
+We observe that for small values of a, the density f is close to the density of $f_1 \sim \mathcal{N}(\mu_1, \sigma_1^2)$. When a increases, the shape of evolves into the combinaison of two normal distributions. We observe that for $a = a^*$, the density the largest value of a for which the density is still a density function, indeed for $a > a^*$, the function f takes negative values so it is no longer a density.
+
+```{r}
+s2_values <- seq(1, 10, length.out = 5)
+a <- 0.2
+
+plot(x, f(a, mu1, mu2, s1, max(s2_values), x),
+     type = "l",
+     xlab = "x",
+     ylab = "f(a, mu1, mu2, s1, s2, x)",
+     col = "red",
+     main = "Density function of f(a, mu1, mu2, s1, s2, x) for different s2"
+)
+
+for (i in length(s2_values):1) {
+  lines(x, f(a, mu1, mu2, s1, s2_values[i], x), lty = 1, col = rainbow(length(s2_values))[i])
+}
+
+legend("topright", legend = paste("s2 =", s2_values), col = rainbow(length(s2_values)), lty = 1)
+```
+
+We observe that when $\sigma_2^2 = 1$, the density $f$ has two peaks and when $\sigma_2^1 > 1$, the density $f$ has only one peak.
+
+```{r}
+mu1 <- 0
+mu2 <- 1
+sigma1 <- 3
+sigma2 <- 1
+a <- 0.2
+as <- a_star(mu1, mu2, sigma1, sigma2)
+
+cat(sprintf("a* = %f, a = %f, a <= a* [%s]", as, a, a <= as))
+```
+
+We have $\sigma_1^2 \ge \sigma_2^2$ and $0 < a \le a^*$, so the numerical values are compatible with the constraints defined above.
+
+## Inverse c.d.f Random Variable simulation
+
+### Question 4
+
+To prove that the cumulative density function F associated with f is available in closed form, we need to compute $F(x) = \int_{-\infty}^{x} f(t) \,dt = \frac{1}{1-a} (\int_{-\infty}^{x} f_1(t)\, dt - a \int_{-\infty}^{x} f_2(t)\, dt) = \frac{1}{1-a} (F_1(x) - aF_2(x))$ where $F_1$ and $F_2$ are the cumulative density functions of $f_1 \sim \mathcal{N}(\mu1, \sigma_1^2)$ and $f_2 \sim \mathcal{N}(\mu2, \sigma_2^2)$ respectively.
+
+Then, $F$ is a closed-form as a finite sum of closed forms.
+
+```{r}
+F <- function(a, mu1, mu2, s1, s2, x) {
+  Fx <- pnorm(x, mu1, s1) - a * pnorm(x, mu2, s2)
+  return(Fx / (1 - a))
+}
+```
+
+To construct an algorithm that returns the value of the inverse function method as a function of $u \in (0,1)$, of the parameters $a, \mu_1, \mu_2, \sigma_1, \sigma_2, x$, and of an approximation precision $\epsilon$, we can use the bisection method.
+
+We fixe $\epsilon > 0$.\
+We set $u \in (0, 1)$.\
+We define $L = -10$ and $U = -L$, the bounds and $M = \frac{L + U}{2}$, the middle of our interval.\
+While $U - L > \epsilon$ :
+
+-   We compute $F(M) = \frac{1}{1-a} (F_1(M) - aF_2(M))$
+-   If $F(M) < u$, we set $L = M$
+-   Else, we set $U = M$
+-   We set $M = \frac{L + U}{2}$
+
+End while
+
+For the generation of random variables from F, we can use the inverse transform sampling method.\
+
+We set $X$ as an empty array and $n$ the number of random variables we want to generate.\
+We fixe $\epsilon > 0$.\
+For $i = 1, \dots, n$ :
+
+-   We set $u \in (0, 1)$.\
+
+-   We define $L = -10$ and $U = -L$, the bounds and $M = \frac{L + U}{2}$, the middle of our interval.\
+
+-   While $U - L > \epsilon$ :
+
+-   We compute $F(M) = \frac{1}{1-a} (F_1(M) - aF_2(M))$
+
+-   If $F(M) < u$, we set $L = M$
+
+-   Else, we set $U = M$
+
+-   We set $M = \frac{L + U}{2}$
+
+-   End while
+
+-   We add $M$ to $X$
+
+End for We return $X$
+
+### Question 5
+
+```{r}
+inv_cdf <- function(n) {
+  X <- numeric(n)
+  for (i in 1:n) {
+    u <- runif(1)
+    L <- -10
+    U <- -L
+    M <- (L + U) / 2
+    while (U - L > 1e-6) {
+      FM <- F(a, mu1, mu2, s1, s2, M)
+      if (FM < u) {
+        L <- M
+      } else {
+        U <- M
+      }
+      M <- (L + U) / 2
+    }
+    X[i] <- M
+  }
+  return(X)
+}
+```
+
+```{r}
+set.seed(123)
+n <- 10000
+X <- inv_cdf(n)
+x <- seq(-10, 10, length.out = 1000)
+
+hist(X, breaks = 100, freq = FALSE, col = "lightblue", main = "Empirical density function", xlab = "x")
+lines(x, f(a, mu1, mu2, s1, s2, x), col = "red")
+legend("topright", legend = c("Theorical density", "Empirical density"), col = c("red", "lightblue"), lty = 1)
+```
+
+```{r}
+plot(ecdf(X), col = "blue", main = "Empirical cumulative distribution function", xlab = "x", ylab = "F(x)")
+lines(x, F(a, mu1, mu2, s1, s2, x), col = "red")
+legend("bottomright", legend = c("Theoretical cdf", "Empirical cdf"), col = c("red", "blue"), lty = 1)
+```
+
+We can see of both graphs that the empirical cumulative distribution function is close to the theoretical one.
+
+## Accept-Reject Random Variable simulation
+
+### Question 6
+
+To simulate under f using the accept-reject algorithm, we need to find a density function g such that $f(x) \le M g(x)$ for all $x \in \mathbb{R}$, where M is a constant.\
+
+Then, we generate $X \sim g$ and $U \sim \mathcal{U}([0,1])$.\
+We accept $Y = X$ if $U \le \frac{f(X)}{Mg(X)}$. Return to $1$ otherwise.
+
+The probability of acceptance is $\int_{\mathbb{R}} \frac{f(x)}{Mg(x)} g(x) \,dx = \frac{1}{M} \int_{\mathbb{R}} f(x) \,dx = \frac{1}{M}$
+
+Here we pose $g = f_1$.
+
+Then we have $\frac{f(x)}{g(x)} = \frac{1}{1-a} (1 - a\frac{f_2(x)}{f_1(x)})$
+
+We pose earlier that $a^* = \min_{x \in \mathbb{R}} \frac{f_1(x)}{f_2(x)} \Rightarrow \frac{1}{a^*} =  \max_{x \in \mathbb{R}} \frac{f_2(x)}{f_1(x)}$.
+
+We compute in our fist equation : $\frac{1}{1-a} (1 - a\frac{f_2(x)}{f_1(x)}) \leq  \frac{1}{1-a} (1 - \frac{a}{a^*}) \leq \frac{1}{1-a}$ because $a \leq a^* \Rightarrow 1 - \frac{a}{a^*} \leq 0$
+
+To conclude, we have $M = \frac{1}{1-a}$ and the probability of acceptance is $\frac{1}{M} = 1-a$
+
+### Question 7
+
+```{r}
+accept_reject <- function(n, a) {
+  X <- numeric(0)
+  M <- 1 / (1 - a)
+
+  while (length(X) < n) {
+    Y <- rnorm(1, mu1, s1)
+    U <- runif(1)
+
+    if (U <= f(a, mu1, mu2, s1, s2, Y) / (M * dnorm(Y, mu1, s1))) {
+      X <- append(X, Y)
+    }
+  }
+  return(X)
+}
+```
+
+```{r}
+set.seed(123)
+n <- 10000
+a <- 0.2
+X <- accept_reject(n, a)
+x <- seq(-10, 10, length.out = 1000)
+
+hist(X, breaks = 100, freq = FALSE, col = "lightblue", main = "Empirical density function", xlab = "x")
+lines(x, f(a, mu1, mu2, s1, s2, x), col = "red")
+legend("topright", legend = c("Theorical density", "Empirical density"), col = c("red", "lightblue"), lty = 1)
+```
+
+```{r}
+set.seed(123)
+
+acceptance_rate <- function(n, a = 0.2) {
+  Y <- rnorm(n, mu1, s1)
+  U <- runif(n)
+  return(mean(U <= f(a, mu1, mu2, s1, s2, Y) / (M * dnorm(Y, mu1, s1))))
+}
+
+M <- 1 / (1 - a)
+n <- 10000
+cat(sprintf("[M = %.2f] Empirical acceptance rate: %f, Theoretical acceptance rate: %f \n", M, acceptance_rate(n), 1 / M))
+```
+
+### Question 8
+
+```{r}
+set.seed(123)
+a_values <- seq(0.01, 1, length.out = 100)
+acceptance_rates <- numeric(length(a_values))
+as <- a_star(mu1, mu2, s1, s2)
+
+for (i in seq_along(a_values)) {
+  acceptance_rates[i] <- acceptance_rate(n, a_values[i])
+}
+
+plot(a_values, acceptance_rates, type = "l", col = "blue", xlab = "a", ylab = "Acceptance rate", main = "Acceptance rate as a function of a")
+points(as, acceptance_rate(n, as), col = "red", pch = 16)
+legend("topright", legend = c("Acceptance rate for all a", "Acceptance rate for a_star"), col = c("lightblue", "red"), lty = c(1, NA), pch = c(NA, 16))
+```
+
+## Random Variable simulation with stratification
+
+### Question 9
+
+We consider a partition $\mathcal{P}= (D_0,D_1,...,D_k)$, $k \in \mathbb{N}$ of $\mathbb{R}$ such that $D_0$ covers the tails of $f_1$ and $f_1$ is upper bounded and $f_2$ lower bounded in $D_1, \dots, D_k$.
+
+To simulate under $f$ using the accept-reject algorithm, we need to find a density function $g$ such that $f(x) \le M g(x)$ for all $x \in \mathbb{R}$, where M is a constant.\
+
+We generate $X \sim g$ and $U \sim \mathcal{U}([0,1])$ $\textit{(1)}$.\
+We accept $Y = X$ if $U \le \frac{f(X)}{Mg(X)}$. Otherwise, we return to $\textit{(1)}$.
+
+Here we pose $g(x) = f_1(x)$ if $x \in D_0$ and $g(x) = sup_{D_i} f_1(x)$ if $x \in D_i, i \in \{1, \dots, k\}$.
+
+To conclude, we have $M = \frac{1}{1-a}$ and the probability of acceptance is $r = \frac{1}{M} = 1-a$
+
+### Question 10
+
+Let $P_n = (D_0, \dots D_n)$ a partition of $\mathbb{R}$ for $n \in \mathbb{N}$. We have $\forall x \in P_n$ and $\forall i \in \{0, \dots, n\}$, $\lim_{n \to\infty} sup_{D_i} f_1(x) = f_1(x)$ and $\lim_{x\to\infty} inf_{D_i} f_2(x) = f_2(x)$.
+
+$\Rightarrow \lim_{x\to\infty} g(x) = f(x)$
+
+$\Rightarrow \lim_{x\to\infty} \frac{g(x)}{f(x)} = 1$ as $f(x) > 0$ as $f$ is a density function.
+
+$\Rightarrow \forall \epsilon > 0, \exists n_{\epsilon} \in \mathbb{N}$ such that $\forall n \ge n_{\epsilon}$, $M = sup_{x \in P_n} \frac{g(x)}{f(x)} < \epsilon$
+
+$\Rightarrow r = \frac{1}{M} > \frac{1}{\epsilon} := \delta \in ]0, 1]$ where $r$ is the acceptance rate defined in the question 10.
+
+### Question 11
+
+We recall the parameters and the functions of the problem.
+
+```{r}
+mu1 <- 0
+mu2 <- 1
+s1 <- 3
+s2 <- 1
+a <- 0.2
+
+f1 <- function(x) {
+  dnorm(x, mu1, s1)
+}
+
+f2 <- function(x) {
+  dnorm(x, mu2, s2)
+}
+
+f <- function(x) {
+  fx <- f1(x) - a * f2(x)
+  fx[fx < 0] <- 0
+  return(fx / (1 - a))
+}
+
+f1_bounds <- c(mu1 - 3 * s1, mu1 + 3 * s1)
+```
+
+We implement the partition, the given $g$ function to understand the behavior of $g$ compared to $f$ and the computation of the supremum and infimum of $f_1$ and $f_2$ on each partition.
+
+```{r}
+create_partition <- function(k = 10) {
+  return(seq(f1_bounds[1], f1_bounds[2], , length.out = k))
+}
+
+sup_inf <- function(f, P, i) {
+  x <- seq(P[i], P[i + 1], length.out = 1000)
+  f_values <- sapply(x, f)
+  return(c(max(f_values), min(f_values)))
+}
+
+g <- function(X, P) {
+  values <- numeric(0)
+  for (x in X) {
+    if (x <= P[1] | x >= P[length(P)]) {
+      values <- c(values, 1 / (1 - a) * f1(x))
+    } else {
+      for (i in 1:(length(P) - 1)) {
+        if (x >= P[i] & x <= P[i + 1]) {
+          values <- c(values, 1 / (1 - a) * (sup_inf(f1, P, i)[1]) - a * sup_inf(f2, P, i)[2])
+        }
+      }
+    }
+  }
+  return(values)
+}
+```
+
+We plot the function $f$ and the dominating function $g$ for different sizes of the partition.
+
+```{r}
+library(ggplot2)
+
+X <- seq(-12, 12, length.out = 1000)
+
+# Plot for different k with ggplot on same graph
+k_values <- c(10, 20, 50, 100)
+P_values <- lapply(k_values, create_partition)
+g_values <- lapply(P_values, g, X)
+
+ggplot() +
+  geom_line(aes(x = X, y = f(X)), col = "red") +
+  geom_line(aes(x = X, y = g(X, P_values[[1]])), col = "green") +
+  geom_line(aes(x = X, y = g(X, P_values[[2]])), col = "orange") +
+  geom_line(aes(x = X, y = g(X, P_values[[3]])), col = "purple") +
+  geom_line(aes(x = X, y = g(X, P_values[[4]])), col = "black") +
+  labs(title = "Dominating function g of f for different size of partition", x = "x", y = "Density") +
+  theme_minimal()
+```
+
+Here, we implement the algorithm of accept-reject with the given partition and an appropriate function $g$ to compute $f$.
+
+```{r}
+set.seed(123)
+
+g_accept_reject <- function(x, P) {
+  if (x < P[1] | x >= P[length(P)]) {
+    return(f1(x))
+  } else {
+    for (i in seq_along(P)) {
+      if (x >= P[i] & x < P[i + 1]) {
+        return(sup_inf(f1, P, i)[1])
+      }
+    }
+  }
+}
+
+stratified <- function(n, P) {
+  samples <- numeric(0)
+  rate <- 0
+  while (length(samples) < n) {
+    x <- rnorm(1, mu1, s1)
+    u <- runif(1)
+    if (u <= f(x) * (1 - a) / g_accept_reject(x, P)) {
+      samples <- c(samples, x)
+    }
+    rate <- rate + 1
+  }
+  list(samples = samples, acceptance_rate = n / rate)
+}
+
+n <- 10000
+k <- 100
+
+P <- create_partition(k)
+samples <- stratified(n, P)
+X <- seq(-10, 10, length.out = 1000)
+
+hist(samples$samples, breaks = 50, freq = FALSE, col = "lightblue", main = "Empirical density function f", xlab = "x")
+lines(X, f(X), col = "red")
+```
+
+We also compute the acceptance rate of the algorithm.
+
+```{r}
+theorical_acceptance_rate <- 1 - a
+cat(sprintf("Empirical acceptance rate: %f, Theoretical acceptance rate: %.1f \n", samples$acceptance_rate, theorical_acceptance_rate))
+```
+
+### Question 12
+
+```{r}
+set.seed(123)
+
+stratified_delta <- function(n, delta) {
+  samples <- numeric(0)
+  P <- create_partition(n * delta)
+  rate <- 0
+  while (length(samples) < n | rate < delta * n) {
+    x <- rnorm(1, mu1, s1)
+    u <- runif(1)
+    if (u <= f(x) * delta / g_accept_reject(x, P)) {
+      samples <- c(samples, x)
+    }
+    rate <- rate + 1
+  }
+  list(samples = samples, partition = P, acceptance_rate = n / rate)
+}
+
+n <- 10000
+delta <- 0.8
+
+samples_delta <- stratified_delta(n, delta)
+X <- seq(-10, 10, length.out = 1000)
+
+hist(samples_delta$samples, breaks = 50, freq = FALSE, col = "lightblue", main = "Empirical density function f", xlab = "x")
+lines(X, f(X), col = "red")
+```
+
+We also compute the acceptance rate of the algorithm.
+
+```{r}
+theorical_acceptance_rate <- 1 - a
+cat(sprintf("Empirical acceptance rate: %f, Theoretical acceptance rate: %f \n", samples_delta$acceptance_rate, theorical_acceptance_rate))
+```
+
+Now, we will test the stratified_delta function for different delta:
+
+```{r}
+set.seed(123)
+n <- 1000
+deltas <- seq(0.1, 1, by = 0.1)
+
+for (delta in deltas) {
+  samples <- stratified_delta(n, delta)
+  cat(sprintf("Delta: %.1f, Empirical acceptance rate: %f \n", delta, samples$acceptance_rate))
+}
+```
+
+## Cumulative density function.
+
+### Question 13
+
+The cumulative density function $\forall x \in \mathbb{R}$ $F_X(x) = \int_{-\infty}^{x} f(t) \,dt = \int_{\mathbb{R}} f(t) h(t), dt$ where $h(x) = \mathbb{1}_{X_n \le x}$
+
+For a given $x \in \mathbb{R}$, a Monte Carlo estimator $F_n(x) = \frac{1}{n} \sum_{i=1}^{n} h(X_i)$ where $h$ is the same function as above and $(X_i)_{i=1}^{n} \sim^{iid} X$
+
+### Question 14
+
+As $X_1, \dots, X_n$ are iid and follows the law of X, and $h$ is continuous by parts, and positive, we have $h(X_1), \dots h(X_n)$ are iid and $\mathbb{E}[h(X_i)] < + \infty$. By the law of large numbers, we have $F_n(X) = \frac{1}{n} \sum_{i=1}^{n} h(X_i) \xrightarrow{a.s} \mathbb{E}[h(X_1)] = F_X(x)$.
+
+Moreover, $\forall \epsilon > 0$, $\exists N \in \mathbb{N}$ such that $\forall n \le N$, $|F_n(x) - F_X(x)| < \epsilon$, ie, $sup_{x \in \mathbb{R}} |F_n(x) - F_X(x)| \xrightarrow{a.s} 0$, by Glivenko-Cantelli theorem.
+
+Hence, $F_n$ is a good estimate of $F_X$ as a function of $x$.
+
+### Question 15
+
+```{r}
+set.seed(123)
+n <- 10000
+Xn <- (rnorm(n, mu1, s1) - a * rnorm(n, mu2, s2)) / (1 - a)
+X <- seq(-10, 10, length.out = n)
+
+h <- function(x, Xn) {
+  return(Xn <= x)
+}
+
+# Fn empirical
+empirical_cdf <- function(x, Xn) {
+  return(mean(h(x, Xn)))
+}
+
+# F theoretical
+F <- function(x) {
+  Fx <- pnorm(x, mu1, s1) - a * pnorm(x, mu2, s2)
+  return(Fx / (1 - a))
+}
+
+cat(sprintf("Empirical cdf: %f, Theoretical cdf: %f \n", empirical_cdf(X, Xn), mean(F(Xn))))
+```
+
+Now we plot the empirical and theoretical cumulative density functions for different n.
+
+```{r}
+n_values <- c(10, 100, 1000, 10000)
+colors <- c("lightblue", "blue", "darkblue", "navy")
+
+plot(NULL, xlim = c(-10, 10), ylim = c(0, 1), xlab = "u", ylab = "Qn(u)", main = "Empirical vs Theoretical CDF")
+
+for (i in seq_along(n_values)) {
+  n <- n_values[i]
+  X <- seq(-10, 10, length.out = n)
+  Xn <- (rnorm(n, mu1, s1) - a * rnorm(n, mu2, s2)) / (1 - a)
+  lines(X, sapply(X, empirical_cdf, Xn = Xn), col = colors[i], lt = 2)
+}
+
+lines(X, F(X), col = "red", lty = 1, lw = 2)
+legend("topright", legend = c("Empirical cdf (n=10)", "Empirical cdf (n=100)", "Empirical cdf (n=1000)", "Empirical cdf (n=10000)", "Theoretical cdf"), col = c(colors, "red"), lty = 1)
+```
+
+### Question 16
+
+As $X_1, \dots, X_n$ are iid and follows the law of X, and $h$ is continuous and positive, we have $h(X_1), \dots h(X_n)$ are iid and $\mathbb{E}[h(X_i)^2] < + \infty$. By the Central Limit Theorem, we have $\sqrt{n} \frac{(F_n(x) - F_X(x))}{\sigma} \xrightarrow{d} \mathcal{N}(0, 1)$ where $\sigma^2 = Var(h(X_1))$.
+
+So we have $\lim_{x\to\infty} \mathbb{P}(\sqrt{n} \frac{(F_n(x) - F_X(x))}{\sigma} \le q_{1-\frac{\alpha}{2}}^{\mathcal{N}(0, 1)})= 1 - \alpha$
+
+So by computing the quantile of the normal distribution, we can have a confidence interval for $F_X(x)$ : $F_X(x) \in [F_n(x) - \frac{q_{1-\frac{\alpha}{2}}^{\mathcal{N}(0, 1)} \sigma}{\sqrt{n}} ; F_n(x) + \frac{q_{1-\frac{\alpha}{2}}^{\mathcal{N}(0, 1)} \sigma}{\sqrt{n}}]$
+
+```{r}
+set.seed(123)
+Fn <- empirical_cdf(X, Xn)
+sigma <- sqrt(Fn - Fn^2)
+q <- qnorm(0.975)
+interval <- c(Fn - q * sigma / sqrt(n), Fn + q * sigma / sqrt(n))
+cat(sprintf("Confidence interval: [%f, %f] \n", interval[1], interval[2]))
+```
+
+### Question 17
+
+```{r}
+compute_n_cdf <- function(x, interval_length = 0.01) {
+  q <- qnorm(0.975)
+  ceiling((q^2 * F(x) * (1 - F(x))) / interval_length^2)
+}
+
+x_values <- c(-15, -1)
+n_values <- sapply(x_values, compute_n_cdf)
+
+data.frame(x = x_values, n = n_values)
+```
+
+We notice that the size of the sample needed to estimate the cumulative density function is higher for values of x that are close to the mean of the distribution. At $x = -1$, we are on the highest peek of the function and at $x = -15$ we are on the tail of the function.
+
+## Empirical quantile function
+
+### Question 18
+
+We define the empirical quantile function defined on $(0, 1)$ by : $Q_n(u) = inf\{x \in \mathbb{R} : u \le F_n(x)\}$. We recall the estimator $F_n(x) = \frac{1}{n} \sum_{i=1}^{n} \mathbb{1}_{X_i \le x}$
+
+So we have $Q_n(u) = inf\{x \in \mathbb{R} : u \le \frac{1}{n} \sum_{i=1}^{n} \mathbb{1}_{X_i \le x}\} = inf\{x \in \mathbb{R} : n . u \le \sum_{i=1}^{n} \mathbb{1}_{X_i \le x}\}$
+
+We sort the sample $(X_1, \dots, X_n)$ in increasing order, and we define $X_{(1)} \le X_{(2)} \le \dots \le X_{(n)}$ the order statistics of the sample.
+
+As $\sum_{i=1}^{n} \mathbb{1}_{X_{(i)} \le x} = k$ where $X_{(k)} = max\{ i = 1, \dots, n ; X_{(i)} \le x \}$
+
+But as $F_n$ is a step function, we can simplify the expression to $Q_n(u) = X_{(k)}$ where $k = \lceil n \cdot u \rceil$ and $X_{(k)}$ is the k-th order statistic of the sample $(X_1, \dots, X_n)$.
+
+### Question 19
+
+We note $Y_{j,n} := \mathbb{1}_{X_{n,j} < Q(u) + \frac{t}{\sqrt{n}} \frac{\sqrt{u(1-u)}}{f(Q(u))}}$
+
+We know that $(X_{n,j})$ is iid as $X$ is bounded in j and n.
+
+Let $\Delta_{n} = \frac{t}{\sqrt{n}} \frac{\sqrt{u(1-u)}}{f(Q(u))}$. We have $F_{n}(X) = \frac{1}{n} \sum_{j=1}^{n} \mathbb{1}_{X_{n,j}} < Q(u) + \Delta_{n}$
+
+then $\frac{1}{n} \sum_{j=1}^{n}Y_{j,n} = F_{n}(Q(u) + \Delta_{n})$ by definition of the empirical quantile $F_{n}(Q_{n}(u)) = u$
+
+By Taylor formula, we got $F_{n}(Q(u) + \Delta_{n}) = F_{n}(Q(u)) + \Delta_{n}f(Q(u))$
+
+By Lindbergh-Levy Central Limit Theorem, applied to $F_{n}(Q(u))$ as $\mathbb{E}[F_{n}(Q(u))] = u < +\infty$ and $Var(F_{n}(Q(u))) = u(1-u) < +\infty$, we have $\frac{\sqrt{n}(F_{n}(Q(u)) - u)}{\sqrt{u(1-u)}} \rightarrow \mathcal{N}(0,1)$
+
+then $F_{n}(Q(u)) = u + \frac{1}{\sqrt{n}} Z$ with $Z \sim \mathcal{N}(0,u(1-u))$
+
+Thus $F_{n}(Q(u) + \Delta_{n}) = u + \frac{1}{\sqrt{n}} Z + \Delta_{n} f(Q(u))$
+
+By substituting $Q_{n}(u) = Q(u) + \Delta_{n}$, we have
+
+$$
+F_{n}(Q_{n}(u)) = F_{n}(Q(u) + \Delta_{n})\\
+\Leftrightarrow u =  u + \frac{1}{\sqrt{n}} Z + \Delta_{n} f(Q(u))\\
+\Leftrightarrow \Delta_{n} = - \frac{1}{\sqrt{n}} \frac{Z}{f(Q(u))}
+$$
+
+As $Q_{n}(u) = Q(u) + \Delta_{n} \Rightarrow \Delta_{n} = Q_{n}(u) - Q(u)$
+
+Then we have
+
+$$
+Q_{n}(u) - Q(u) = - \frac{1}{\sqrt{n}} \frac{Z}{f(Q(u))}\\
+\Leftrightarrow \sqrt{n}(Q_{n}(u) - Q(u)) = \frac{Z}{f(Q(u))}\\
+\Leftrightarrow \sqrt{n}(Q\_{n}(u) - Q(u)) \sim \mathcal{N}(0,\frac{u(1-u)}{f(Q(u))^2})
+$$
+
+### Question 20
+
+When $u \rightarrow 0$, $Q(u)$ corresponds to the lower tail of the distribution, and when $u \rightarrow 1$, $Q(u)$ corresponds to the upper tail of the distribution.
+
+So $f(Q(u))$ is higher when $u$ is close to 0 and close to 1, so the variance of the estimator is higher for values of $u$ that are close to 0 and 1. So we need a higher sample size to estimate the quantile function for values of $u$ that are close to 0 and 1.
+
+### Question 21
+
+```{r}
+set.seed(123)
+
+empirical_quantile <- function(u, Xn) {
+  sorted_Xn <- sort(Xn)
+  k <- ceiling(u * length(Xn))
+  sorted_Xn[k]
+}
+```
+
+```{r}
+set.seed(123)
+n <- 1000
+Xn <- (rnorm(n, mu1, s1) - a * rnorm(n, mu2, s2)) / (1 - a)
+u_values <- seq(0.01, 0.99, by = 0.01)
+Qn_values <- sapply(u_values, empirical_quantile, Xn = Xn)
+
+plot(u_values, Qn_values, col = "blue", xlab = "u", ylab = "Qn(u)", type = "o")
+lines(u_values, (qnorm(u_values, mu1, s1) - a * qnorm(u_values, mu2, s2)) / (1 - a), col = "red")
+legend("topright", legend = c("Empirical quantile function", "Theoretical quantile function"), col = c("blue", "red"), lty = c(2, 1))
+```
+
+### Question 22
+
+We can compute the confidence interval of the empirical quantile function using the Central Limit Theorem.
+
+We obtain the following formula for the confidence interval of the empirical quantile function:
+
+$Q(u) \in [Q_n(u) - q_{1 - \frac{\alpha}{2}}^{\mathcal{N}(0,1)} \frac{\sqrt{u (1-u)}}{\sqrt{n} f(Q(u))}; Q_n(u) + q_{1 - \frac{\alpha}{2}}^{\mathcal{N}(0,1)} \frac{\sqrt{u (1-u)}}{\sqrt{n} f(Q(u))}]$
+
+```{r}
+f_q <- function(u) {
+  f(1 / (1 - a) * (qnorm(u, mu1, s1) - a * qnorm(u, mu2, s2)))
+}
+
+compute_n_quantile <- function(u, interval_length = 0.01) {
+  q <- qnorm(0.975)
+  ceiling((q^2 * u * (1 - u)) / (interval_length^2 * f_q(u)^2))
+}
+
+u_values <- c(0.5, 0.9, 0.99, 0.999, 0.9999)
+n_values <- sapply(u_values, compute_n_quantile)
+
+data.frame(u = u_values, n = n_values)
+```
+
+We deduce that the size of the sample needed to estimate the quantile function is higher for values of u that are close to 1. This corresponds to the deduction made in question 20.
+
+## Quantile estimation Naïve Reject algorithm
+
+### Question 23
+
+We generate a sample $(X_n)_{n \in \mathbb{N}} \sim^{iid} f_X$ the c.d.f. of $X$
+
+We choose all the $i = 1, \dots, n$ such that $X_i \in A$ and plug them in a new set $(Y_n)_{n \in \mathbb{N}}$
+
+Then, the mean of $Y_n$ simulate a random variable $X$ conditional to the event $X \in A$ with $A \subset \mathbb{R}$
+
+So when n is big enough, we can estimate $\mathbb{P}(X \in A)$ with our sample $(Y_n)_{n \in \mathbb{N}}$ and the mean of $Y_n$.
+
+### Question 24
+
+```{r}
+accept_reject_quantile <- function(q, n) {
+  X_samples <- (rnorm(n, mu1, s1) - a * rnorm(n, mu2, s2)) / (1 - a)
+  return(mean(X_samples >= q))
+}
+
+set.seed(123)
+n <- 10000
+q_values <- seq(-10, 10, by = 2)
+delta_quantile <- sapply(q_values, accept_reject_quantile, n)
+data.frame(q = q_values, quantile = delta_quantile)
+```
+
+```{r}
+plot(q_values, delta_quantile, type = "o", col = "blue", xlab = "q", ylab = "Quantile estimation", main = "Quantile estimation using accept-reject algorithm")
+lines(q_values, 1 - (pnorm(q_values, mu1, s1) - a * pnorm(q_values, mu2, s2)) / (1 - a), col = "red")
+legend("topright", legend = c("Empirical quantile", "Theoretical quantile"), col = c("blue", "red"), lty = c(2, 1))
+```
+
+### Question 25
+
+Let $X_1, \dots, X_n$ iid such that $\mathbb{E}[X_i] < \infty$, we have $\mathbb{1}_{X_1 \ge q}, \dots, \mathbb{1}_{X_n \ge q}$ and $\mathbb{E}[\mathbb{1}_{X_1 \ge q}] = \mathbb{P}(X_i \ge q) \le 1 < + \infty$. By TCL, we have $\sqrt{n} \frac{(\frac{1}{n} \sum_{i=1}^{n} \mathbb{1}_{X_i \ge q} - \mathbb{E}[\mathbb{1}_{X_1 \ge q}])}{\sqrt{Var(\mathbb{1}_{X_1 \ge q}})} \rightarrow Z \sim \mathcal{N}(0, 1)$ in distribution, with
+
+-   $\mathbb{E}[\mathbb{1}_{X_1 \ge q}] = \mathbb{P}(X_i \ge q) = \delta$
+
+-   $\sqrt{Var(\mathbb{1}_{X_1 \ge q}}) = \mathbb{E}[\mathbb{1}_{X_1 \ge q}^2] - \mathbb{E}[\mathbb{1}_{X_1 \ge q}]^2 = \delta(1-\delta)$
+
+In addition, we have $\hat{\delta}^{NR}_n \rightarrow \delta$ a.s. by the LLN, as it is a consistent estimator of $\delta$ .
+
+The function $x \mapsto \sqrt{\frac{\delta(1-\delta)}{x(1-x)}}$ is continuous on $(0,1)$, we have $\sqrt{\frac{\delta(1-\delta)}{\hat{\delta}^{NR}_n(1-\hat{\delta}^{NR}_n)}} \rightarrow \sqrt{\frac{\delta(1-\delta)}{\delta(1-\delta)}} = 1$, then by Slutsky, we have $\sqrt{n} \frac{(\hat{\delta}^{NR}_n - \delta)}{\sqrt{\delta(1-\delta)})} \sqrt{\frac{\delta(1-\delta)}{\hat{\delta}^{NR}_n(1-\hat{\delta}^{NR}_n)}} = \sqrt{n} \frac{(\hat{\delta}^{NR}_n - \delta)}{\sqrt{\hat{\delta}^{NR}_n(1-\hat{\delta}^{NR}_n)})} \rightarrow Z . 1 = Z \sim \mathcal{N}(0, 1)$.
+
+Now we can compute the confident interval for $\delta$: $IC_n(\delta) = [\hat{\delta}^{NR}_n - \frac{q_{1-\frac{\alpha}{2}}^{\mathcal{N}(0,1)}}{\sqrt{n}}\hat{\delta}^{NR}_n(1-\hat{\delta}^{NR}_n);\hat{\delta}^{NR}_n + \frac{q_{1-\frac{\alpha}{2}}^{\mathcal{N}(0,1)}}{\sqrt{n}}\hat{\delta}^{NR}_n(1-\hat{\delta}^{NR}_n)]$ where $q_{1-\frac{\alpha}{2}}^{\mathcal{N}(0,1)}$ is the quantile of the normal distribution $\mathcal{N}(0,1)$
+
+```{r}
+IC_Naive <- function(delta_hat, n, alpha = 0.05) {
+  q <- qnorm(1 - alpha / 2)
+  c(lower = delta_hat - q * sqrt(delta_hat * (1 - delta_hat)) / sqrt(n),
+    upper = delta_hat + q * sqrt(delta_hat * (1 - delta_hat)) / sqrt(n))
+}
+
+set.seed(123)
+n <- 10000
+q_values <- seq(-10, 10, by = 2)
+delta_quantile_naive <- sapply(q_values, accept_reject_quantile, n)
+IC_values_naive <- sapply(delta_quantile_naive, IC_Naive, n = n)
+data.frame(q = q_values, quantile = delta_quantile_naive, IC = t(IC_values_naive))
+```
+
+## Importance Sampling
+
+### Question 26
+
+Let $X_1, \dots, X_n \sim^{iid} g$ where $g$ such that $sup(f) \subseteq sup(g)$ and $g$ density easy to simulate.
+
+We want to determine $\delta = \mathbb{P}(X \ge q) = \int_{q}^{+ \infty} f_X(x) \,dx = \int_{\mathbb{R}} f(x) h(x) \,dx = \mathbb{E}[h(X)]$ for any $q$, with $h(x) = \mathbb{1}_{x \ge q}$ and $f$ the density function of $X$.
+
+Given $X_1, \dots, X_n \sim^{iid} g$ , we have $\hat{\delta}^{IS}_n = \frac{1}{n} \sum_{i=1}^{n} \frac{f(X_i)}{g(X_i)} h(X_i)$
+
+So $\hat{\delta}^{IS}_n$ is an unbiased estimator of $\delta$, since $sup(f) \subseteq sup(g)$.
+
+The importance sampling estimator is preferred to the classical Monte Carlo estimator when the variance of the importance sampling estimator is lower than the variance of the classical Monte Carlo estimator. This is the case when q is located on the tails of the distribution $f$
+
+### Question 27
+
+The density $g$ of a Cauchy distribution for parameters $(\mu_0, \gamma)$ is given by: $g(x; \mu_0, \gamma) = \frac{1}{\pi} \frac{\gamma}{(x - \mu_0)^2 + \gamma^2}$, $\forall x \in \mathbb{R}$.
+
+The parameters $(\mu_0, \gamma)$ of the Cauchy distribution used in importance sampling are chosen based on the characteristics of the target density $f(x)$.
+
+-   $\mu_0$ is chosen such that $sup(f) \subseteq sup(g)$, where $sup(f)$ is the support of the target density $f(x)$. $\mu_0$ should be chosen to place the center of $g(x)$ in the most likely region of $f(x)$, which can be approximated by the midpoint between $\mu_1$ and $\mu_2$, ie, $\mu_0 = \frac{\mu_1 + \mu_2}{2} = \frac{0 + 1}{2} = \frac{1}{2}$.
+
+-   By centering $g(x)$ at $\mu_0$ and setting $\gamma$ to capture the spread of $f(x)$, we maximize the overlap between $f(x)$ and $g(x)$, reducing the variance of the importance sampling estimator. To cover the broader spread of $f(x)$, $\gamma$ should reflect the scale of the wider normal component. A reasonable choice is to set $\gamma$ to the largest standard deviation, ie, $\gamma = max(s_1, s_2) = max(1, 3) = 3$
+
+### Question 28
+
+We can compute the confidence interval of the importance sampling estimator using the Central Limit Theorem, with the same arguments as in the question 25, since we have a consistent estimator of $\delta$.
+
+```{r}
+mu0 <- 0.5
+gamma <- 3
+g <- function(x) {
+  dcauchy(x, mu0, gamma)
+}
+
+IS_quantile <- function(q, n) {
+  X <- rcauchy(n, mu0, gamma)
+  w <- f(X) / g(X)
+  h <- (X >= q)
+  return(mean(w * h))
+}
+```
+
+```{r}
+IC_IS <- function(delta_hat, n, alpha = 0.05) {
+  q <- qnorm(1 - alpha / 2)
+  c(lower = delta_hat - q * sqrt(delta_hat * (1 - delta_hat)) / sqrt(n),
+    upper = delta_hat + q * sqrt(delta_hat * (1 - delta_hat)) / sqrt(n))
+}
+
+set.seed(123)
+q_values <- seq(-10, 10, by = 2)
+n <- 10000
+delta_quantile_IS <- sapply(q_values, IS_quantile, n = n)
+IC_values_IS <- sapply(delta_quantile_IS, IC_IS, n = n)
+data.frame(q = q_values, quantile = delta_quantile_IS, IC = t(IC_values_IS))
+```
+
+# Control Variate
+
+### Question 29
+
+Let $X_1, \dots, X_n$ iid. For $f$ density with parameter $\theta$, we can compute the score by deriving the partial derivative of the log-likelihood function. $S(\theta) = \frac{\partial l(\theta)}{\partial \theta} = \sum^{n}_{i=1} \frac{\partial log(f(X_i | \theta)}{\partial \theta} = \frac{f_1(x|\theta_1)}{f_1(x|\theta_1) - a f_2(x|\theta_2)} \frac{x - \mu_1}{\sigma_1^2}$
+
+### Question 30
+
+We recall $\delta = \mathbb{P}(X \ge q) = \int_{q}^{+ \infty} f_X(x) \,dx = \int_\mathbb{R} f_X(x) h(x) \, dx$ where $h(x) = \mathbb{1}_{x \ge q}$. We denote $\hat{\delta}^{IC}_n = \frac{1}{n} \sum^{n}_{i=1} h(X_i) - b \cdot (S_{\mu_1}(X_i) - m) = \frac{1}{n} \sum^{n}_{i=1} \mathbb{1}_{X_i \ge q} - b \cdot S_{\mu_1}(X_i)$ where $m = \mathbb{E}[S_{\mu_1}(X_1)] = 0$ and $b=\frac{Cov(\mathbb{1}_{X_1 \ge q}, \, S_{\mu_1}(X_1))}{Var(S_{\mu_1(X_1)})}$
+
+### Question 31
+
+```{r}
+CV_quantile <- function(q, n) {
+  X <- rnorm(n, mu1, s1)
+  S <- (f1(X) / (f1(X) - a * f2(X))) * (X - mu1) / s1^2
+  h <- (X >= q)
+  b <- cov(S, h) / var(S)
+  delta <- mean(h) - b * mean(S)
+  return(delta)
+}
+```
+
+We can compute the confidence interval of the importance sampling estimator using the Central Limit Theorem, with the same arguments as in the question 25, since we have a consistent estimator of $\delta$.
+```{r}
+IC_CV <- function(delta_hat, n, alpha = 0.05) {
+  q <- qnorm(1 - alpha / 2)
+  c(lower = delta_hat - q * sqrt(delta_hat * (1 - delta_hat)) / sqrt(n),
+    upper = delta_hat + q * sqrt(delta_hat * (1 - delta_hat)) / sqrt(n))
+}
+
+set.seed(123)
+n <- 10000
+q_values <- seq(-10, 10, by = 2)
+delta_quantile_CV <- sapply(q_values, CV_quantile, n)
+IC_values_CV <- sapply(delta_quantile_CV, IC_CV, n = n)
+
+data.frame(q = q_values, quantile = delta_quantile_CV, IC = t(IC_values_CV))
+```
+
+### Question 32
+```{r}
+set.seed(123)
+delta_real <- 1 - (pnorm(q_values, mu1, s1) - a * pnorm(q_values, mu2, s2)) / (1 - a)
+
+IS <- data.frame(IC = t(IC_values_IS), length = IC_values_IS[2] - IC_values_IS[1])
+naive <- data.frame(IC = t(IC_values_naive), length = IC_values_naive[2] - IC_values_naive[1])
+CV <- data.frame(IC = t(IC_values_CV), length = IC_values_CV[2] - IC_values_CV[1])
+
+data.frame(q = q_values, real_quantile = delta_real, quantile_CV = CV, quantile_IS = IS, quantile_Naive = naive)
+```
+
+```{r}
+plot(q_values, delta_real, type = "l", col = "red", xlab = "q", ylab = "Quantile estimation", main = "Quantile estimation using different methods")
+lines(q_values, delta_quantile_IS, col = "blue")
+lines(q_values, delta_quantile_naive, col = "green")
+lines(q_values, delta_quantile_CV, col = "orange")
+legend("topright", legend = c("Real quantile", "Quantile estimation IS", "Quantile estimation Naive", "Quantile estimation CV"), col = c("red", "blue", "green", "orange"), lty = c(1, 1, 1, 1))
+```
+
+Now we compare the three methods: Naive vs Importance Sampling vs Control Variate
+
+The naive method is the easiest to implement but is the least precise for some points.
+The importance sampling method is more precise than the naive method but requires the choice of a good density $g$, that can be hard to determine in some case.
+The control variate method is the most precise but requires the choice of a good control variate, and need to compute the covariance, which require more computation time.
+
+In our case, the control variate method is the most precise, but the importance sampling method is also a good choice.

M1/Numerical Methods/TP2.ipynb

@@ -0,0 +1,103 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "c897654e0a140cbd",
+   "metadata": {},
+   "source": [
+    "# Automatic Differentiation\n",
+    "\n",
+    "### Neural Network\n",
+    "\n",
+    "Loss function: softmax layer in $\\mathbb{R}^3$\n",
+    "\n",
+    "Architecture: FC/ReLU 4-5-7-3"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 33,
+   "id": "70a4eb1d928b10d0",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-03-24T15:16:27.015669Z",
+     "start_time": "2025-03-24T15:16:23.856887Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Mean Accuracy: 94%\n",
+      "STD Accuracy: 3%\n",
+      "Max accuracy: 100%\n",
+      "Min accuracy: 88%\n"
+     ]
+    }
+   ],
+   "source": [
+    "import numpy as np\n",
+    "from sklearn.datasets import make_classification\n",
+    "from sklearn.metrics import accuracy_score\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from sklearn.neural_network import MLPClassifier\n",
+    "\n",
+    "accuracies = []\n",
+    "\n",
+    "for _ in range(10):\n",
+    "    X, y = make_classification(\n",
+    "        n_samples=1000, n_features=4, n_classes=3, n_clusters_per_class=1\n",
+    "    )\n",
+    "\n",
+    "    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)\n",
+    "    model = MLPClassifier(\n",
+    "        hidden_layer_sizes=(5, 7), activation=\"relu\", max_iter=10000, solver=\"adam\"\n",
+    "    )\n",
+    "    model.fit(X_train, y_train)\n",
+    "\n",
+    "    y_pred = model.predict(X_test)\n",
+    "    accuracies.append(accuracy_score(y_test, y_pred))\n",
+    "\n",
+    "print(f\"Mean Accuracy: {np.mean(accuracies) * 100:.0f}%\")\n",
+    "print(f\"STD Accuracy: {np.std(accuracies) * 100:.0f}%\")\n",
+    "print(f\"Max accuracy: {np.max(accuracies) * 100:.0f}%\")\n",
+    "print(f\"Min accuracy: {np.min(accuracies) * 100:.0f}%\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "96b6d46883ed5570",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-03-24T14:37:53.507776Z",
+     "start_time": "2025-03-24T14:37:53.505376Z"
+    }
+   },
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 2
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython2",
+   "version": "2.7.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

M1/Numerical Optimisation/ComputerSession2.ipynb

@@ -0,0 +1,600 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Computer session 2\n",
+    "\n",
+    "The goal of this computer class is to get a good feel of the Newton method and its\n",
+    "variants. In a (maybe) surprising way, we actually start with the dichotomy method\n",
+    "in the one-dimensional case.\n",
+    "\n",
+    "## The dichotomy method in the one-dimensional case\n",
+    "\n",
+    "When trying to solve the equation $\\phi(x) = 0$ in the one-dimensional case, the\n",
+    "most naive method, which actually turns out to be quite efficient, is the dichotomy\n",
+    "method. Namely, starting from an initial pair $(a_L , a_R ) \\in \\mathbb{R}^2$ with $a_L < a_R$ such\n",
+    "that $\\phi(a_L)\\phi(a_R)<0$, we set $b ∶=\\frac{a_L+a_R}{2}$. If $\\phi(b) = 0$, the algorithm stops. If\n",
+    "$\\phi(a_L)\\phi(b) < 0$ we set $a_L\\to a_L$ and $a_R \\to b$. In this way, we obtain a linearly\n",
+    "converging algorithm. In particular, it is globally converging.\n",
+    "\n",
+    "\n",
+    "Write a function `Dichotomy(phi,aL,aR,eps)` that take sas argument\n",
+    "a function `phi`, an initial guess `aL,aR` and a tolerance `eps` and that runs the dichotomy\n",
+    "algorithm. Your argument should check that the condition $\\phi(a_L)\\phi(a_R) < 0$ is satisfied,\n",
+    "stop when the function `phi` reaches a value lower than `eps` and return the number\n",
+    "of iteration. Run your algorithm on the function $f = tanh$ with initial guesses\n",
+    "$a_L = −20$ , $a_R = 3$.\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-03-18T16:19:14.314484Z",
+     "start_time": "2025-03-18T16:19:13.728014Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "(-2.3283064365386963e-09, 31)\n"
+     ]
+    }
+   ],
+   "source": [
+    "import numpy as np\n",
+    "\n",
+    "\n",
+    "def dichotomy(phi, aL, aR, eps=1e-8):\n",
+    "    iter = 0\n",
+    "    b = (aL + aR) / 2\n",
+    "    while (aR - aL) / 2 > eps and phi(b) != 0:\n",
+    "        b = (aL + aR) / 2\n",
+    "        if phi(aL) * phi(b) < 0:\n",
+    "            aR = b\n",
+    "        else:\n",
+    "            aL = b\n",
+    "        iter += 1\n",
+    "    return b, iter\n",
+    "\n",
+    "\n",
+    "def f(x):\n",
+    "    return np.tanh(x)\n",
+    "aL, aR = -20, 3\n",
+    "print(dichotomy(f, aL, aR))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Solving one-dimensional equation with the Newton and the secant method\n",
+    "\n",
+    "We work again in the one-dimensional case with a function φ we want to find the\n",
+    "zeros of.\n",
+    "\n",
+    "### Newton method\n",
+    "\n",
+    "Write a function `Newton(phi,dphi,x0,eps)` that takes, as arguments, a function\n",
+    "`phi`, its derivative `dphi`, an initial guess `x0` and a tolerance `eps`\n",
+    "and that returns an approximation of the solutions of the equation $\\phi(x) = 0$. The\n",
+    "tolerance criterion should again be that $|\\phi| ≤\\text{\\texttt{eps}}$. Your\n",
+    "algorithm should return an error message in the following cases:\n",
+    "1. If the derivative is zero (look up the `try` and `except` commands in Python).\n",
+    "2. If the method diverges.\n",
+    "\n",
+    "Apply this code to the minimisation of $x\\mapsto \\ln(e^x + e^{−x})$, with initial condition `x0=1.8`.\n",
+    "Compare this with the results of Exercise 3.10."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-03-18T16:19:17.447647Z",
+     "start_time": "2025-03-18T16:19:17.442560Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "(inf, 'Method diverges')\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/var/folders/tp/_ld5_pzs6nx6mv1pbjhq1l740000gn/T/ipykernel_25957/3868809151.py:14: RuntimeWarning: overflow encountered in exp\n",
+      "  f = lambda x: np.log(np.exp(x) + np.exp(-x))\n"
+     ]
+    }
+   ],
+   "source": [
+    "def Newton(phi, dphi, x0, eps=1e-10):\n",
+    "    iter = 0\n",
+    "    while abs(phi(x0)) > eps:\n",
+    "        try:\n",
+    "            x0 -= phi(x0) / dphi(x0)\n",
+    "        except ZeroDivisionError:\n",
+    "            return np.inf, \"Derivative is zero\"\n",
+    "        iter += 1\n",
+    "        if iter > 10000 or phi(x0) == np.inf:\n",
+    "            return np.inf, \"Method diverges\"\n",
+    "    return x0, iter\n",
+    "\n",
+    "\n",
+    "def f(x):\n",
+    "    return np.log(np.exp(x) + np.exp(-x))\n",
+    "x0 = 1.8\n",
+    "def df(x):\n",
+    "    return (np.exp(x) - np.exp(-x)) / (np.exp(x) + np.exp(-x))\n",
+    "print(Newton(f, df, x0))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Secant method\n",
+    "\n",
+    "Write a function `Secant(phi,x0,x1,eps)` that takes, as arguments, a function `phi`, two initial positions `x0`, `x1` and a tolerance\n",
+    "`eps` and that returns an approximation of the solutions of the equation\n",
+    "$\\phi(x) = 0$. The tolerance criterion should again be that $|\\phi| ≤\\text{\\texttt{eps}}$. Apply this code to the minimisation\n",
+    "of $x\\mapsto \\ln(e^x + e^{−x})$, with initial conditions `x0=1`, `x1=1.9`, then\n",
+    "`x0=1`, `x1=2.3` and\n",
+    "`x0=1`, `x1=2.4`. Compare with the results of Exercise 3.10."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-03-18T16:19:19.649523Z",
+     "start_time": "2025-03-18T16:19:19.456149Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "(inf, 'Method diverges')\n",
+      "(inf, 'Method diverges')\n",
+      "(inf, 'Method diverges')\n"
+     ]
+    }
+   ],
+   "source": [
+    "def Secant(phi, x0, x1, eps=1e-8):\n",
+    "    iter = 0\n",
+    "    while abs(phi(x1)) > eps:\n",
+    "        x1, x0 = x1 - phi(x1) * (x1 - x0) / (phi(x1) - phi(x0)), x0\n",
+    "        iter += 1\n",
+    "        if iter > 10000:\n",
+    "            return np.inf, \"Method diverges\"\n",
+    "    return x0, iter\n",
+    "\n",
+    "\n",
+    "def f(x):\n",
+    "    return np.log(np.exp(x) + np.exp(-x))\n",
+    "xx = [(1, 1.9), (1, 2.3), (1, 2.4)]\n",
+    "\n",
+    "for x0, x1 in xx:\n",
+    "    print(Secant(f, x0, x1))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Combining dichotomy and the Newton method\n",
+    "\n",
+    "A possibility to leverage the advantages of dichotomy (the global convergence of\n",
+    "the method) and of the Newton method (the quadratic convergence rate) is to\n",
+    "combine both: start from an initial interval `[aL,aR]` of length `InitialLength`\n",
+    "with $\\phi(a_L)\\phi(a_R)<0$ and fix a real\n",
+    "number $s \\in [0; 1]$. Run the dichotomy algorithm until the new interval is of length\n",
+    "`s*InitialLength`. From this point on, apply the Newton method.\n",
+    "\n",
+    "Implement this algorithm with `s = 0.1`. Include a possibility to switch\n",
+    "back to the dichotomy method if, when switching to the Newton method, the new\n",
+    "iterate falls outside of the computed interval `[aL,aR]`. Apply this to the minimisation\n",
+    "of the function $f ∶ x\\mapsto \\ln(e^x + e^{−x})$ with an initial condition that made the Newton\n",
+    "method diverge. What can you  say about the number of iterations?"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-03-18T16:44:41.592150Z",
+     "start_time": "2025-03-18T16:44:41.584318Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "(inf, 'Method diverges')\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/var/folders/tp/_ld5_pzs6nx6mv1pbjhq1l740000gn/T/ipykernel_25957/1578277506.py:23: RuntimeWarning: overflow encountered in exp\n",
+      "  f = lambda x: np.log(np.exp(x) + np.exp(-x))\n"
+     ]
+    }
+   ],
+   "source": [
+    "def DichotomyNewton(phi, dphi, aL, aR, s=0.1, eps=1e-10):\n",
+    "    iter = 0\n",
+    "    inital_length = aR - aL\n",
+    "    while (aR - aL) >= s * inital_length:\n",
+    "        b = (aL + aR) / 2\n",
+    "        if phi(aL) * phi(b) < 0:\n",
+    "            aR = b\n",
+    "        else:\n",
+    "            aL = b\n",
+    "        iter += 1\n",
+    "    x0 = (aL + aR) / 2\n",
+    "    while abs(phi(x0)) > eps:\n",
+    "        try:\n",
+    "            x0 -= phi(x0) / dphi(x0)\n",
+    "        except ZeroDivisionError:\n",
+    "            return np.inf, \"Derivative is zero\"\n",
+    "        iter += 1\n",
+    "        if iter > 10000 or phi(x0) == np.inf:\n",
+    "            return np.inf, \"Method diverges\"\n",
+    "    return x0, iter\n",
+    "\n",
+    "\n",
+    "def f(x):\n",
+    "    return np.log(np.exp(x) + np.exp(-x))\n",
+    "def df(x):\n",
+    "    return (np.exp(x) - np.exp(-x)) / (np.exp(x) + np.exp(-x))\n",
+    "print(DichotomyNewton(f, df, -20, 3))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Solving an optimisation problem using the Newton method\n",
+    "\n",
+    "An island (denoted by a point $I$ below) is situated 2 kilometers from the shore (its projection on the shore\n",
+    "is a point $P$). A guest staying at a nearby hotel $H$ wants to go from the hotel to the\n",
+    "island and decides that he will run at 8km/hr for a distance $x$, before swimming at\n",
+    "speed 3km/hr to reach the island.\n",
+    "\n",
+    "![illustration of the problem](./images/optiNewton.png)\n",
+    "\n",
+    "Taking into account the fact that there are 6 kilometers between the hotel $H$ and $P$,\n",
+    "how far should the visitor run before swimming?\n",
+    "\n",
+    "Model the situation as a minimisation problem, and solve it numerically.\n",
+    "Compare the efficiency of the dichotomy method and of the Newton algorithm."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 38,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-03-18T17:43:43.061916Z",
+     "start_time": "2025-03-18T17:43:43.042625Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Optimal point (Newton): 0.9299901531755377\n",
+      "Objective function value at optimal point (Newton): 1.9329918821224974\n",
+      "Number of iterations (Newton): 100\n",
+      "Optimal point (Dichotomy): inf\n",
+      "Objective function value at optimal point (Dichotomy): inf\n",
+      "Number of iterations (Dichotomy): Method diverges\n"
+     ]
+    }
+   ],
+   "source": [
+    "def u(x):\n",
+    "    return np.sqrt((6 - x) ** 2 + 4)\n",
+    "\n",
+    "\n",
+    "def objective_function(x):\n",
+    "    return x / 8 + u(x) / 3\n",
+    "\n",
+    "\n",
+    "def gradient(x):\n",
+    "    return 1 / 8 + (6 - x) / (3 * u(x))\n",
+    "\n",
+    "\n",
+    "def hessian(x):\n",
+    "    return (12 * u(x) - (2 * x - 12) ** 2 / 12 * u(x)) / 36 * u(x) ** 2\n",
+    "\n",
+    "\n",
+    "# Newton's method for optimization\n",
+    "def newton_method(initial_guess, tolerance=1e-6, max_iterations=100):\n",
+    "    x = initial_guess\n",
+    "    iterations = 0\n",
+    "    while iterations < max_iterations:\n",
+    "        grad = gradient(x)\n",
+    "        hess = hessian(x)\n",
+    "        if np.abs(grad) < tolerance:\n",
+    "            break\n",
+    "        x -= grad / hess\n",
+    "        iterations += 1\n",
+    "    return x, iterations\n",
+    "\n",
+    "\n",
+    "# Dichotomy method for optimization\n",
+    "def dichotomy_method(aL, aR, eps=1e-6, max_iterations=1000):\n",
+    "    iterations = 0\n",
+    "    x0 = (aL + aR) / 2\n",
+    "    grad = gradient(x0)\n",
+    "    hess = hessian(x0)\n",
+    "    while abs(grad) > eps:\n",
+    "        try:\n",
+    "            x0 -= grad / hess\n",
+    "        except ZeroDivisionError:\n",
+    "            return np.inf, \"Derivative is zero\"\n",
+    "        iterations += 1\n",
+    "        if iterations > max_iterations or grad == np.inf:\n",
+    "            return np.inf, \"Method diverges\"\n",
+    "        grad = gradient(x0)\n",
+    "        hess = hessian(x0)\n",
+    "    return x0, iterations\n",
+    "\n",
+    "\n",
+    "# Initial guess for Newton's method\n",
+    "initial_guess_newton = 4\n",
+    "\n",
+    "# Run Newton's method\n",
+    "optimal_point_newton, iterations_newton = newton_method(initial_guess_newton)\n",
+    "print(f\"Optimal point (Newton): {optimal_point_newton}\")\n",
+    "print(\n",
+    "    f\"Objective function value at optimal point (Newton): {objective_function(optimal_point_newton)}\"\n",
+    ")\n",
+    "print(f\"Number of iterations (Newton): {iterations_newton}\")\n",
+    "\n",
+    "# Initial interval for dichotomy method\n",
+    "aL, aR = 0, 6\n",
+    "\n",
+    "# Run dichotomy method\n",
+    "optimal_point_dichotomy, iterations_dichotomy = dichotomy_method(aL, aR)\n",
+    "print(f\"Optimal point (Dichotomy): {optimal_point_dichotomy}\")\n",
+    "print(\n",
+    "    f\"Objective function value at optimal point (Dichotomy): {objective_function(optimal_point_dichotomy)}\"\n",
+    ")\n",
+    "print(f\"Number of iterations (Dichotomy): {iterations_dichotomy}\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## The Newton method to solve boundary value problems\n",
+    "\n",
+    "### Shooting method\n",
+    "\n",
+    "We consider the following non-linear ODE\n",
+    "\n",
+    "\\begin{equation}\n",
+    "y''= f(x,y,y'),\\quad x\\in[a,b],\\quad y(a)=\\alpha, y(b)=\\beta.\n",
+    "\\end{equation}\n",
+    "\n",
+    "\n",
+    "To classically integrate such an ODE, we usually don’t have endpoints for $y$,\n",
+    "but initial values for $y$ and $y'$. So, we cannot start at $x=a $ and integrate\n",
+    "up to $x=b$. This is a _boundary value problem_.\n",
+    "\n",
+    "One approach is to approximate $y$ by somme finite difference and then arrive at\n",
+    "a system for the discrete values $y(x_i)$ and finally solve large linear\n",
+    "systems.\n",
+    "\n",
+    "Here, we will see how we can formulate the problem as a _shooting_ method, and\n",
+    "use Newton method so solve it.\n",
+    "\n",
+    "The idea is to use a _guess_ for the initial value of $y'$. Let $s$ be a\n",
+    "parameter for a fonction $y(\\;\\cdot\\;;s)$ solution of (1) such that\n",
+    "$$y(a;s)=\\alpha,\\text{ and }y'(a;s)=s.$$\n",
+    "\n",
+    "There is no chance that $y(b;s)=y(b)=\\beta$ but we can adjust the value of $s$,\n",
+    "refining the guess until it is (nearly equal to) the right value.\n",
+    "\n",
+    "This method is known as _shooting_ method in analogy to shooting a ball at a\n",
+    "goal, determining the unknown correct velocity by throwing it too fast/too\n",
+    "slow until it hits the goal exactly.\n",
+    "\n",
+    "#### In Practice\n",
+    "\n",
+    "For the parameter $s$, we integrate the following ODE:\n",
+    "\n",
+    "\\begin{equation}\n",
+    "y''= f(x,y,y'),\\quad x\\in[a,b],\\quad y(a)=\\alpha, y'(a)=s.\n",
+    "\\end{equation}\n",
+    "\n",
+    "We denote $y(\\;\\cdot\\;;s)$ solution of (2).\n",
+    "\n",
+    "Let us now define the _goal function_. Here, we want that $y(b;s)=\\beta$, hence,\n",
+    "we define:\n",
+    "$$g:s\\mapsto \\left.y(x;s)\\right|_{x=b}-\\beta$$\n",
+    "\n",
+    "We seek $s^*$ such that $g(s^*)=0$.\n",
+    "\n",
+    "Note that computing $g(s)$ involves the integration of an ODE, so each\n",
+    "evaluation of $g$ is  expensive. Newton’s method seems then to be a good\n",
+    "way due to its fast convergence.\n",
+    "\n",
+    "To be able to code a Newton’s method, we need to compute the derivative of $g$.\n",
+    "For this purpose, let define\n",
+    "$$z(x;s)=\\frac{\\partial y(x;s)}{\\partial s}.$$\n",
+    "\n",
+    "Then by differentiating (2) with respect to $s$, we get\n",
+    "$$z''=\\frac{\\partial f}{\\partial y}z+\\frac{\\partial f}{\\partial y'}z',\\quad\n",
+    "z(a;s)=0,\\text{ and }z'(a;s)=1.$$\n",
+    "\n",
+    "The derivative of $g$ can now be expressed in term of $z$:\n",
+    "$$g'(z)=z(b;s).$$\n",
+    "\n",
+    "Putting this together, we can code the Newton's method:\n",
+    "$$s_{n+1}=s_n-\\frac{g(s_n)}{g'(s_n)}.$$\n",
+    "\n",
+    "To sum up, a shooting method requires an ODE solver and a Newton solver.\n",
+    "\n",
+    "#### Example\n",
+    "\n",
+    "Apply this method to\n",
+    "$$y''=2y^3-6y-2x^3,\\quad y(1)=2,y(2)=5/2,$$\n",
+    "with standard library for integration, and your own Newton implementation.\n",
+    "\n",
+    "Note that you may want to express this with one order ODE. Moreover, it may be\n",
+    "simpler to solve only one ODE for both $g$ and $g'$.\n",
+    "\n",
+    "With python, you can use `scipy.integrate.solve_ivp` function:\n",
+    "https://docs.scipy.org/doc/scipy/reference/generated/scipy.integrate.solve_ivp.html#scipy.integrate.solve_ivp\n",
+    "\n",
+    "Plot the solution $y$.\n",
+    "\n",
+    "For numerical parameters, compute the solution up to a precision of $10^{-8}$\n",
+    "and get the function on a grid of 1000 points.\n",
+    "\n",
+    "## Finite differences\n",
+    "\n",
+    "Here, we are going to use a different approach to solve the boundary value\n",
+    "problem:\n",
+    "\n",
+    "\\begin{equation}\n",
+    "y''= f(x,y,y'),\\quad x\\in[a,b],\\quad y(a)=\\alpha, y(b)=\\beta.\n",
+    "\\end{equation}\n",
+    "\n",
+    "This problem can be solved by the following direct process:\n",
+    "\n",
+    "1. We discretize the domain choosing an integer $N$, grid points $\\{x_n\\}_{n=0,\\dots,N}$ and\n",
+    "   we define the discrete solution $\\{y_n\\}_{n=0,\\dots,N}$.\n",
+    "1. We discretize the ODE using derivative approximation with finite differences\n",
+    "   in the interior of the domain.\n",
+    "1. We inject the boundary conditions (here $y_0=\\alpha$ and $y_N=\\beta$) in the\n",
+    "   discretized ODE.\n",
+    "1. Solve the system of equation for the unknows $\\{y_n\\}_{n=1,\\dots,N-1}$.\n",
+    "\n",
+    "We use here a uniform grid :\n",
+    "$$h:=(b-a)/N, \\quad \\forall n=0,\\dots, N\\quad x_n=hn.$$\n",
+    "If we use a centered difference formula for $y''$ and $y'$, we obtain:\n",
+    "$$\\forall n=1,\\dots,N-1,\\quad \\frac{y_{n+1}-2y_n+y_{n-1}}{h^2}=f\\left(x_n,y_n,\\frac{y_{n+1}-y_{n-1}}{2h}\\right).$$"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "The result is a system of equations for $\\mathbf{y}=(y_1,\\dots,y_{N-1})$ :\n",
+    "$$G(\\mathbf{y})=0,\\quad G:\\mathbb{R}^{N-1}\\to\\mathbb{R}^{N-1}.$$"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "This system can be solved using Newton's method. Note that the Jacobian\n",
+    "$\\partial G/\\partial \\mathbb{y}$ is _tridiagonal_.\n",
+    "\n",
+    "Of course, here, we are in the multidimensional context, so you will have to\n",
+    "code a Newton algorithm well suited.\n",
+    "\n",
+    "#### Example\n",
+    "\n",
+    "Apply this method to\n",
+    "$$y''=2y^3-6y-2x^3,\\quad y(1)=2,y(2)=5/2.$$\n",
+    "\n",
+    "Plot the solution $y$.\n",
+    "\n",
+    "For numerical parameters, compute the solution up to a precision of $10^{-8}$\n",
+    "and get the function on a grid of 1000 points."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "**Remark:** In the context of numerical optimal control, these two numerical\n",
+    "methods are often called _indirect method_ (for the shooting method) and _direct\n",
+    "method_ (for the finite difference method)."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Who’s the best?\n",
+    "\n",
+    "Compare the two methods playing with parameters (grid discretization, precision,\n",
+    "initialization, etc.). Mesure the time computation."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "base",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.2"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

M1/Portfolio Management/TP-Project.ipynb

@@ -0,0 +1,523 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "81049114d821d00e",
+   "metadata": {},
+   "source": [
+    "# Project - Portfolio Management\n",
+    "\n",
+    "## Group: Danjou Arthur & Forest Thais\n",
+    "\n",
+    "### Time period studied from 2017-01-01 to 2018-01-01\n",
+    "\n",
+    "### Risk-free rate: 2%"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 51,
+   "id": "initial_id",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-11-25T13:43:46.298758Z",
+     "start_time": "2024-11-25T13:43:46.293696Z"
+    },
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "import yfinance as yf"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 52,
+   "id": "9f9fc36832c97e0",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-11-25T13:43:47.318911Z",
+     "start_time": "2024-11-25T13:43:47.198820Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[*********************100%***********************]  1 of 1 completed\n",
+      "[*********************100%***********************]  1 of 1 completed\n",
+      "[*********************100%***********************]  1 of 1 completed\n",
+      "[*********************100%***********************]  1 of 1 completed\n",
+      "/var/folders/tp/_ld5_pzs6nx6mv1pbjhq1l740000gn/T/ipykernel_92506/348989065.py:9: FutureWarning: DataFrame.interpolate with method=pad is deprecated and will raise in a future version. Use obj.ffill() or obj.bfill() instead.\n",
+      "  S = S.interpolate(method=\"pad\")\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>^RUT</th>\n",
+       "      <th>^IXIC</th>\n",
+       "      <th>^GSPC</th>\n",
+       "      <th>XWD.TO</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Date</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>2017-01-03 00:00:00+00:00</th>\n",
+       "      <td>1365.489990</td>\n",
+       "      <td>5429.080078</td>\n",
+       "      <td>2257.830078</td>\n",
+       "      <td>38.499630</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2017-01-04 00:00:00+00:00</th>\n",
+       "      <td>1387.949951</td>\n",
+       "      <td>5477.000000</td>\n",
+       "      <td>2270.750000</td>\n",
+       "      <td>38.553375</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2017-01-05 00:00:00+00:00</th>\n",
+       "      <td>1371.939941</td>\n",
+       "      <td>5487.939941</td>\n",
+       "      <td>2269.000000</td>\n",
+       "      <td>38.481716</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2017-01-06 00:00:00+00:00</th>\n",
+       "      <td>1367.280029</td>\n",
+       "      <td>5521.060059</td>\n",
+       "      <td>2276.979980</td>\n",
+       "      <td>38.517544</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2017-01-09 00:00:00+00:00</th>\n",
+       "      <td>1357.489990</td>\n",
+       "      <td>5531.819824</td>\n",
+       "      <td>2268.899902</td>\n",
+       "      <td>38.383186</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                                  ^RUT        ^IXIC        ^GSPC     XWD.TO\n",
+       "Date                                                                       \n",
+       "2017-01-03 00:00:00+00:00  1365.489990  5429.080078  2257.830078  38.499630\n",
+       "2017-01-04 00:00:00+00:00  1387.949951  5477.000000  2270.750000  38.553375\n",
+       "2017-01-05 00:00:00+00:00  1371.939941  5487.939941  2269.000000  38.481716\n",
+       "2017-01-06 00:00:00+00:00  1367.280029  5521.060059  2276.979980  38.517544\n",
+       "2017-01-09 00:00:00+00:00  1357.489990  5531.819824  2268.899902  38.383186"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>^RUT</th>\n",
+       "      <th>^IXIC</th>\n",
+       "      <th>^GSPC</th>\n",
+       "      <th>XWD.TO</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Date</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>2017-12-22 00:00:00+00:00</th>\n",
+       "      <td>1542.930054</td>\n",
+       "      <td>6959.959961</td>\n",
+       "      <td>2683.340088</td>\n",
+       "      <td>44.323349</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2017-12-26 00:00:00+00:00</th>\n",
+       "      <td>1544.229980</td>\n",
+       "      <td>6936.250000</td>\n",
+       "      <td>2680.500000</td>\n",
+       "      <td>44.323349</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2017-12-27 00:00:00+00:00</th>\n",
+       "      <td>1543.939941</td>\n",
+       "      <td>6939.339844</td>\n",
+       "      <td>2682.620117</td>\n",
+       "      <td>44.052303</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2017-12-28 00:00:00+00:00</th>\n",
+       "      <td>1548.930054</td>\n",
+       "      <td>6950.160156</td>\n",
+       "      <td>2687.540039</td>\n",
+       "      <td>43.857414</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2017-12-29 00:00:00+00:00</th>\n",
+       "      <td>1535.510010</td>\n",
+       "      <td>6903.390137</td>\n",
+       "      <td>2673.610107</td>\n",
+       "      <td>43.784576</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                                  ^RUT        ^IXIC        ^GSPC     XWD.TO\n",
+       "Date                                                                       \n",
+       "2017-12-22 00:00:00+00:00  1542.930054  6959.959961  2683.340088  44.323349\n",
+       "2017-12-26 00:00:00+00:00  1544.229980  6936.250000  2680.500000  44.323349\n",
+       "2017-12-27 00:00:00+00:00  1543.939941  6939.339844  2682.620117  44.052303\n",
+       "2017-12-28 00:00:00+00:00  1548.930054  6950.160156  2687.540039  43.857414\n",
+       "2017-12-29 00:00:00+00:00  1535.510010  6903.390137  2673.610107  43.784576"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "(251, 4)\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Data Extraction\n",
+    "Tickers = [\"^RUT\", \"^IXIC\", \"^GSPC\", \"XWD.TO\"]\n",
+    "start_input = \"2017-01-01\"\n",
+    "end_input = \"2018-01-01\"\n",
+    "S = pd.DataFrame()\n",
+    "for t in Tickers:\n",
+    "    S[t] = yf.Tickers(t).history(start=start_input, end=end_input)[\"Close\"]\n",
+    "\n",
+    "S = S.interpolate(method=\"pad\")\n",
+    "\n",
+    "# Show the first five and last five values extracted\n",
+    "display(S.head())\n",
+    "display(S.tail())\n",
+    "print(S.shape)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 53,
+   "id": "53483cf3a925a4db",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-11-25T13:43:50.080380Z",
+     "start_time": "2024-11-25T13:43:50.073119Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "R = S / S.shift() - 1\n",
+    "R = R[1:]\n",
+    "mean_d = R.mean()\n",
+    "covar_d = R.cov()\n",
+    "corr = R.corr()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 54,
+   "id": "c327ed5967b1f442",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-11-25T13:43:50.965092Z",
+     "start_time": "2024-11-25T13:43:50.961969Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "mean = mean_d * 252\n",
+    "covar = covar_d * 252\n",
+    "std = np.sqrt(np.diag(covar))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 55,
+   "id": "6bc6a850bf06cc9d",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-11-25T13:43:51.701725Z",
+     "start_time": "2024-11-25T13:43:51.695020Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Mean:\n",
+      "\n",
+      "^RUT      0.125501\n",
+      "^IXIC     0.246863\n",
+      "^GSPC     0.172641\n",
+      "XWD.TO    0.133175\n",
+      "dtype: float64\n",
+      "\n",
+      "Covariance:\n",
+      "\n",
+      "            ^RUT     ^IXIC     ^GSPC    XWD.TO\n",
+      "^RUT    0.014417  0.008400  0.006485  0.004797\n",
+      "^IXIC   0.008400  0.009182  0.005583  0.004337\n",
+      "^GSPC   0.006485  0.005583  0.004426  0.003309\n",
+      "XWD.TO  0.004797  0.004337  0.003309  0.006996\n",
+      "\n",
+      "Standard Deviation:\n",
+      "\n",
+      "[0.12007222 0.09582499 0.06653127 0.08364295]\n",
+      "\n",
+      "Correlation:\n",
+      "\n",
+      "            ^RUT     ^IXIC     ^GSPC    XWD.TO\n",
+      "^RUT    1.000000  0.730047  0.811734  0.477668\n",
+      "^IXIC   0.730047  1.000000  0.875687  0.541087\n",
+      "^GSPC   0.811734  0.875687  1.000000  0.594658\n",
+      "XWD.TO  0.477668  0.541087  0.594658  1.000000\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(\"Mean:\\n\")\n",
+    "print(mean)\n",
+    "print(\"\\nCovariance:\\n\")\n",
+    "print(covar)\n",
+    "print(\"\\nStandard Deviation:\\n\")\n",
+    "print(std)\n",
+    "print(\"\\nCorrelation:\\n\")\n",
+    "print(corr)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "fc4bec874f710f7c",
+   "metadata": {},
+   "source": "# Question 1"
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 56,
+   "id": "780c9cca6e0ed2d3",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-11-25T13:43:53.113423Z",
+     "start_time": "2024-11-25T13:43:53.109514Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "r = 0.02\n",
+    "d = len(Tickers)\n",
+    "vec1 = np.linspace(1, 1, d)\n",
+    "sigma = covar\n",
+    "inv_sigma = np.linalg.inv(sigma)\n",
+    "\n",
+    "a = vec1.T.dot(inv_sigma).dot(vec1)\n",
+    "b = mean.T.dot(inv_sigma).dot(vec1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 57,
+   "id": "81c956f147c68070",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-11-25T13:43:54.545400Z",
+     "start_time": "2024-11-25T13:43:54.541579Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Expected return m_T: 0.2364033641931515\n",
+      "Standard deviation sd_T: 0.07276528490265963\n",
+      "Allocation pi_T: [-0.60853811  0.45748917  1.17944152 -0.02839259]\n",
+      "We can verify that the allocation is possible as the sum of the allocations for the different indices is 0.9999999999999993, that is very close to 1\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Tangent portfolio\n",
+    "pi_T = inv_sigma.dot(mean - r * vec1) / (b - r * a)\n",
+    "sd_T = np.sqrt(pi_T.T.dot(sigma).dot(pi_T))  # Variance\n",
+    "m_T = pi_T.T.dot(mean)  # expected return\n",
+    "\n",
+    "print(f\"Expected return m_T: {m_T}\")\n",
+    "print(f\"Standard deviation sd_T: {sd_T}\")\n",
+    "print(f\"Allocation pi_T: {pi_T}\")\n",
+    "print(\n",
+    "    f\"We can verify that the allocation is possible as the sum of the allocations for the different indices is {sum(pi_T)}, that is very close to 1\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2e121c2dfb946f3c",
+   "metadata": {},
+   "source": "# Question 2"
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 58,
+   "id": "c169808384ca1112",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-11-25T13:43:59.797115Z",
+     "start_time": "2024-11-25T13:43:59.792462Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "The annualized volatilities of the index ^RUT is 0.12007221535411407\n",
+      "The annualized expected returns of the index ^RUT is 0.12550141384538263\n",
+      "\n",
+      "The annualized volatilities of the index ^IXIC is 0.09582499431305072\n",
+      "The annualized expected returns of the index ^IXIC is 0.24686267015709437\n",
+      "\n",
+      "The annualized volatilities of the index ^GSPC is 0.06653126757186174\n",
+      "The annualized expected returns of the index ^GSPC is 0.17264098207081371\n",
+      "\n",
+      "The annualized volatilities of the index XWD.TO is 0.08364295296865466\n",
+      "The annualized expected returns of the index XWD.TO is 0.1331750489518068\n",
+      "\n",
+      "The annualized volatility of the Tangent Portfolio is 1.155113087587201\n",
+      "The annualized expected return of the Tangent Portfolio is 59.57364777667418\n"
+     ]
+    }
+   ],
+   "source": [
+    "for i in range(len(std)):\n",
+    "    print(f\"The annualized volatilities of the index {Tickers[i]} is {std[i]}\")\n",
+    "    print(\n",
+    "        f\"The annualized expected returns of the index {Tickers[i]} is {mean[Tickers[i]]}\"\n",
+    "    )\n",
+    "    print(\"\")\n",
+    "\n",
+    "print(f\"The annualized volatility of the Tangent Portfolio is {sd_T * np.sqrt(252)}\")\n",
+    "print(f\"The annualized expected return of the Tangent Portfolio is {m_T * 252}\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "af8d29ecdbf2ae1",
+   "metadata": {},
+   "source": "# Question 3"
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 59,
+   "id": "2e0215ab7904906a",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-11-25T13:44:01.393591Z",
+     "start_time": "2024-11-25T13:44:01.388830Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "sharpe ratio of the Tangent portfolio : 2.9739918490340687\n",
+      "the sharpe ratio of the index ^RUT is 0.8786496820620858\n",
+      "the sharpe ratio of the index ^IXIC is 2.3674686524473625\n",
+      "the sharpe ratio of the index ^GSPC is 2.294274371158541\n",
+      "the sharpe ratio of the index XWD.TO is 1.353073330567601\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(\"sharpe ratio of the Tangent portfolio :\", (m_T - r) / sd_T)\n",
+    "\n",
+    "for i in range(4):\n",
+    "    print(\n",
+    "        f\"the sharpe ratio of the index {Tickers[i]} is {(mean[Tickers[i]] - r) / std[i]}\"\n",
+    "    )"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 2
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython2",
+   "version": "2.7.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

M1/Statistical Learning/data/Hitters.csv

@@ -0,0 +1,323 @@
+"Name","AtBat","Hits","HmRun","Runs","RBI","Walks","Years","CAtBat","CHits","CHmRun","CRuns","CRBI","CWalks","League","Division","PutOuts","Assists","Errors","Salary","NewLeague"
+"-Andy Allanson",293,66,1,30,29,14,1,293,66,1,30,29,14,"A","E",446,33,20,NA,"A"
+"-Alan Ashby",315,81,7,24,38,39,14,3449,835,69,321,414,375,"N","W",632,43,10,475,"N"
+"-Alvin Davis",479,130,18,66,72,76,3,1624,457,63,224,266,263,"A","W",880,82,14,480,"A"
+"-Andre Dawson",496,141,20,65,78,37,11,5628,1575,225,828,838,354,"N","E",200,11,3,500,"N"
+"-Andres Galarraga",321,87,10,39,42,30,2,396,101,12,48,46,33,"N","E",805,40,4,91.5,"N"
+"-Alfredo Griffin",594,169,4,74,51,35,11,4408,1133,19,501,336,194,"A","W",282,421,25,750,"A"
+"-Al Newman",185,37,1,23,8,21,2,214,42,1,30,9,24,"N","E",76,127,7,70,"A"
+"-Argenis Salazar",298,73,0,24,24,7,3,509,108,0,41,37,12,"A","W",121,283,9,100,"A"
+"-Andres Thomas",323,81,6,26,32,8,2,341,86,6,32,34,8,"N","W",143,290,19,75,"N"
+"-Andre Thornton",401,92,17,49,66,65,13,5206,1332,253,784,890,866,"A","E",0,0,0,1100,"A"
+"-Alan Trammell",574,159,21,107,75,59,10,4631,1300,90,702,504,488,"A","E",238,445,22,517.143,"A"
+"-Alex Trevino",202,53,4,31,26,27,9,1876,467,15,192,186,161,"N","W",304,45,11,512.5,"N"
+"-Andy VanSlyke",418,113,13,48,61,47,4,1512,392,41,205,204,203,"N","E",211,11,7,550,"N"
+"-Alan Wiggins",239,60,0,30,11,22,6,1941,510,4,309,103,207,"A","E",121,151,6,700,"A"
+"-Bill Almon",196,43,7,29,27,30,13,3231,825,36,376,290,238,"N","E",80,45,8,240,"N"
+"-Billy Beane",183,39,3,20,15,11,3,201,42,3,20,16,11,"A","W",118,0,0,NA,"A"
+"-Buddy Bell",568,158,20,89,75,73,15,8068,2273,177,1045,993,732,"N","W",105,290,10,775,"N"
+"-Buddy Biancalana",190,46,2,24,8,15,5,479,102,5,65,23,39,"A","W",102,177,16,175,"A"
+"-Bruce Bochte",407,104,6,57,43,65,12,5233,1478,100,643,658,653,"A","W",912,88,9,NA,"A"
+"-Bruce Bochy",127,32,8,16,22,14,8,727,180,24,67,82,56,"N","W",202,22,2,135,"N"
+"-Barry Bonds",413,92,16,72,48,65,1,413,92,16,72,48,65,"N","E",280,9,5,100,"N"
+"-Bobby Bonilla",426,109,3,55,43,62,1,426,109,3,55,43,62,"A","W",361,22,2,115,"N"
+"-Bob Boone",22,10,1,4,2,1,6,84,26,2,9,9,3,"A","W",812,84,11,NA,"A"
+"-Bob Brenly",472,116,16,60,62,74,6,1924,489,67,242,251,240,"N","W",518,55,3,600,"N"
+"-Bill Buckner",629,168,18,73,102,40,18,8424,2464,164,1008,1072,402,"A","E",1067,157,14,776.667,"A"
+"-Brett Butler",587,163,4,92,51,70,6,2695,747,17,442,198,317,"A","E",434,9,3,765,"A"
+"-Bob Dernier",324,73,4,32,18,22,7,1931,491,13,291,108,180,"N","E",222,3,3,708.333,"N"
+"-Bo Diaz",474,129,10,50,56,40,10,2331,604,61,246,327,166,"N","W",732,83,13,750,"N"
+"-Bill Doran",550,152,6,92,37,81,5,2308,633,32,349,182,308,"N","W",262,329,16,625,"N"
+"-Brian Downing",513,137,20,90,95,90,14,5201,1382,166,763,734,784,"A","W",267,5,3,900,"A"
+"-Bobby Grich",313,84,9,42,30,39,17,6890,1833,224,1033,864,1087,"A","W",127,221,7,NA,"A"
+"-Billy Hatcher",419,108,6,55,36,22,3,591,149,8,80,46,31,"N","W",226,7,4,110,"N"
+"-Bob Horner",517,141,27,70,87,52,9,3571,994,215,545,652,337,"N","W",1378,102,8,NA,"N"
+"-Brook Jacoby",583,168,17,83,80,56,5,1646,452,44,219,208,136,"A","E",109,292,25,612.5,"A"
+"-Bob Kearney",204,49,6,23,25,12,7,1309,308,27,126,132,66,"A","W",419,46,5,300,"A"
+"-Bill Madlock",379,106,10,38,60,30,14,6207,1906,146,859,803,571,"N","W",72,170,24,850,"N"
+"-Bobby Meacham",161,36,0,19,10,17,4,1053,244,3,156,86,107,"A","E",70,149,12,NA,"A"
+"-Bob Melvin",268,60,5,24,25,15,2,350,78,5,34,29,18,"N","W",442,59,6,90,"N"
+"-Ben Oglivie",346,98,5,31,53,30,16,5913,1615,235,784,901,560,"A","E",0,0,0,NA,"A"
+"-Bip Roberts",241,61,1,34,12,14,1,241,61,1,34,12,14,"N","W",166,172,10,NA,"N"
+"-BillyJo Robidoux",181,41,1,15,21,33,2,232,50,4,20,29,45,"A","E",326,29,5,67.5,"A"
+"-Bill Russell",216,54,0,21,18,15,18,7318,1926,46,796,627,483,"N","W",103,84,5,NA,"N"
+"-Billy Sample",200,57,6,23,14,14,9,2516,684,46,371,230,195,"N","W",69,1,1,NA,"N"
+"-Bill Schroeder",217,46,7,32,19,9,4,694,160,32,86,76,32,"A","E",307,25,1,180,"A"
+"-Butch Wynegar",194,40,7,19,29,30,11,4183,1069,64,486,493,608,"A","E",325,22,2,NA,"A"
+"-Chris Bando",254,68,2,28,26,22,6,999,236,21,108,117,118,"A","E",359,30,4,305,"A"
+"-Chris Brown",416,132,7,57,49,33,3,932,273,24,113,121,80,"N","W",73,177,18,215,"N"
+"-Carmen Castillo",205,57,8,34,32,9,5,756,192,32,117,107,51,"A","E",58,4,4,247.5,"A"
+"-Cecil Cooper",542,140,12,46,75,41,16,7099,2130,235,987,1089,431,"A","E",697,61,9,NA,"A"
+"-Chili Davis",526,146,13,71,70,84,6,2648,715,77,352,342,289,"N","W",303,9,9,815,"N"
+"-Carlton Fisk",457,101,14,42,63,22,17,6521,1767,281,1003,977,619,"A","W",389,39,4,875,"A"
+"-Curt Ford",214,53,2,30,29,23,2,226,59,2,32,32,27,"N","E",109,7,3,70,"N"
+"-Cliff Johnson",19,7,0,1,2,1,4,41,13,1,3,4,4,"A","E",0,0,0,NA,"A"
+"-Carney Lansford",591,168,19,80,72,39,9,4478,1307,113,634,563,319,"A","W",67,147,4,1200,"A"
+"-Chet Lemon",403,101,12,45,53,39,12,5150,1429,166,747,666,526,"A","E",316,6,5,675,"A"
+"-Candy Maldonado",405,102,18,49,85,20,6,950,231,29,99,138,64,"N","W",161,10,3,415,"N"
+"-Carmelo Martinez",244,58,9,28,25,35,4,1335,333,49,164,179,194,"N","W",142,14,2,340,"N"
+"-Charlie Moore",235,61,3,24,39,21,14,3926,1029,35,441,401,333,"A","E",425,43,4,NA,"A"
+"-Craig Reynolds",313,78,6,32,41,12,12,3742,968,35,409,321,170,"N","W",106,206,7,416.667,"N"
+"-Cal Ripken",627,177,25,98,81,70,6,3210,927,133,529,472,313,"A","E",240,482,13,1350,"A"
+"-Cory Snyder",416,113,24,58,69,16,1,416,113,24,58,69,16,"A","E",203,70,10,90,"A"
+"-Chris Speier",155,44,6,21,23,15,16,6631,1634,98,698,661,777,"N","E",53,88,3,275,"N"
+"-Curt Wilkerson",236,56,0,27,15,11,4,1115,270,1,116,64,57,"A","W",125,199,13,230,"A"
+"-Dave Anderson",216,53,1,31,15,22,4,926,210,9,118,69,114,"N","W",73,152,11,225,"N"
+"-Doug Baker",24,3,0,1,0,2,3,159,28,0,20,12,9,"A","W",80,4,0,NA,"A"
+"-Don Baylor",585,139,31,93,94,62,17,7546,1982,315,1141,1179,727,"A","E",0,0,0,950,"A"
+"-Dann Bilardello",191,37,4,12,17,14,4,773,163,16,61,74,52,"N","E",391,38,8,NA,"N"
+"-Daryl Boston",199,53,5,29,22,21,3,514,120,8,57,40,39,"A","W",152,3,5,75,"A"
+"-Darnell Coles",521,142,20,67,86,45,4,815,205,22,99,103,78,"A","E",107,242,23,105,"A"
+"-Dave Collins",419,113,1,44,27,44,12,4484,1231,32,612,344,422,"A","E",211,2,1,NA,"A"
+"-Dave Concepcion",311,81,3,42,30,26,17,8247,2198,100,950,909,690,"N","W",153,223,10,320,"N"
+"-Darren Daulton",138,31,8,18,21,38,3,244,53,12,33,32,55,"N","E",244,21,4,NA,"N"
+"-Doug DeCinces",512,131,26,69,96,52,14,5347,1397,221,712,815,548,"A","W",119,216,12,850,"A"
+"-Darrell Evans",507,122,29,78,85,91,18,7761,1947,347,1175,1152,1380,"A","E",808,108,2,535,"A"
+"-Dwight Evans",529,137,26,86,97,97,15,6661,1785,291,1082,949,989,"A","E",280,10,5,933.333,"A"
+"-Damaso Garcia",424,119,6,57,46,13,9,3651,1046,32,461,301,112,"A","E",224,286,8,850,"N"
+"-Dan Gladden",351,97,4,55,29,39,4,1258,353,16,196,110,117,"N","W",226,7,3,210,"A"
+"-Danny Heep",195,55,5,24,33,30,8,1313,338,25,144,149,153,"N","E",83,2,1,NA,"N"
+"-Dave Henderson",388,103,15,59,47,39,6,2174,555,80,285,274,186,"A","W",182,9,4,325,"A"
+"-Donnie Hill",339,96,4,37,29,23,4,1064,290,11,123,108,55,"A","W",104,213,9,275,"A"
+"-Dave Kingman",561,118,35,70,94,33,16,6677,1575,442,901,1210,608,"A","W",463,32,8,NA,"A"
+"-Davey Lopes",255,70,7,49,35,43,15,6311,1661,154,1019,608,820,"N","E",51,54,8,450,"N"
+"-Don Mattingly",677,238,31,117,113,53,5,2223,737,93,349,401,171,"A","E",1377,100,6,1975,"A"
+"-Darryl Motley",227,46,7,23,20,12,5,1325,324,44,156,158,67,"A","W",92,2,2,NA,"A"
+"-Dale Murphy",614,163,29,89,83,75,11,5017,1388,266,813,822,617,"N","W",303,6,6,1900,"N"
+"-Dwayne Murphy",329,83,9,50,39,56,9,3828,948,145,575,528,635,"A","W",276,6,2,600,"A"
+"-Dave Parker",637,174,31,89,116,56,14,6727,2024,247,978,1093,495,"N","W",278,9,9,1041.667,"N"
+"-Dan Pasqua",280,82,16,44,45,47,2,428,113,25,61,70,63,"A","E",148,4,2,110,"A"
+"-Darrell Porter",155,41,12,21,29,22,16,5409,1338,181,746,805,875,"A","W",165,9,1,260,"A"
+"-Dick Schofield",458,114,13,67,57,48,4,1350,298,28,160,123,122,"A","W",246,389,18,475,"A"
+"-Don Slaught",314,83,13,39,46,16,5,1457,405,28,156,159,76,"A","W",533,40,4,431.5,"A"
+"-Darryl Strawberry",475,123,27,76,93,72,4,1810,471,108,292,343,267,"N","E",226,10,6,1220,"N"
+"-Dale Sveum",317,78,7,35,35,32,1,317,78,7,35,35,32,"A","E",45,122,26,70,"A"
+"-Danny Tartabull",511,138,25,76,96,61,3,592,164,28,87,110,71,"A","W",157,7,8,145,"A"
+"-Dickie Thon",278,69,3,24,21,29,8,2079,565,32,258,192,162,"N","W",142,210,10,NA,"N"
+"-Denny Walling",382,119,13,54,58,36,12,2133,594,41,287,294,227,"N","W",59,156,9,595,"N"
+"-Dave Winfield",565,148,24,90,104,77,14,7287,2083,305,1135,1234,791,"A","E",292,9,5,1861.46,"A"
+"-Enos Cabell",277,71,2,27,29,14,15,5952,1647,60,753,596,259,"N","W",360,32,5,NA,"N"
+"-Eric Davis",415,115,27,97,71,68,3,711,184,45,156,119,99,"N","W",274,2,7,300,"N"
+"-Eddie Milner",424,110,15,70,47,36,7,2130,544,38,335,174,258,"N","W",292,6,3,490,"N"
+"-Eddie Murray",495,151,17,61,84,78,10,5624,1679,275,884,1015,709,"A","E",1045,88,13,2460,"A"
+"-Ernest Riles",524,132,9,69,47,54,2,972,260,14,123,92,90,"A","E",212,327,20,NA,"A"
+"-Ed Romero",233,49,2,41,23,18,8,1350,336,7,166,122,106,"A","E",102,132,10,375,"A"
+"-Ernie Whitt",395,106,16,48,56,35,10,2303,571,86,266,323,248,"A","E",709,41,7,NA,"A"
+"-Fred Lynn",397,114,23,67,67,53,13,5589,1632,241,906,926,716,"A","E",244,2,4,NA,"A"
+"-Floyd Rayford",210,37,8,15,19,15,6,994,244,36,107,114,53,"A","E",40,115,15,NA,"A"
+"-Franklin Stubbs",420,95,23,55,58,37,3,646,139,31,77,77,61,"N","W",206,10,7,NA,"N"
+"-Frank White",566,154,22,76,84,43,14,6100,1583,131,743,693,300,"A","W",316,439,10,750,"A"
+"-George Bell",641,198,31,101,108,41,5,2129,610,92,297,319,117,"A","E",269,17,10,1175,"A"
+"-Glenn Braggs",215,51,4,19,18,11,1,215,51,4,19,18,11,"A","E",116,5,12,70,"A"
+"-George Brett",441,128,16,70,73,80,14,6675,2095,209,1072,1050,695,"A","W",97,218,16,1500,"A"
+"-Greg Brock",325,76,16,33,52,37,5,1506,351,71,195,219,214,"N","W",726,87,3,385,"A"
+"-Gary Carter",490,125,24,81,105,62,13,6063,1646,271,847,999,680,"N","E",869,62,8,1925.571,"N"
+"-Glenn Davis",574,152,31,91,101,64,3,985,260,53,148,173,95,"N","W",1253,111,11,215,"N"
+"-George Foster",284,64,14,30,42,24,18,7023,1925,348,986,1239,666,"N","E",96,4,4,NA,"N"
+"-Gary Gaetti",596,171,34,91,108,52,6,2862,728,107,361,401,224,"A","W",118,334,21,900,"A"
+"-Greg Gagne",472,118,12,63,54,30,4,793,187,14,102,80,50,"A","W",228,377,26,155,"A"
+"-George Hendrick",283,77,14,45,47,26,16,6840,1910,259,915,1067,546,"A","W",144,6,5,700,"A"
+"-Glenn Hubbard",408,94,4,42,36,66,9,3573,866,59,429,365,410,"N","W",282,487,19,535,"N"
+"-Garth Iorg",327,85,3,30,44,20,8,2140,568,16,216,208,93,"A","E",91,185,12,362.5,"A"
+"-Gary Matthews",370,96,21,49,46,60,15,6986,1972,231,1070,955,921,"N","E",137,5,9,733.333,"N"
+"-Graig Nettles",354,77,16,36,55,41,20,8716,2172,384,1172,1267,1057,"N","W",83,174,16,200,"N"
+"-Gary Pettis",539,139,5,93,58,69,5,1469,369,12,247,126,198,"A","W",462,9,7,400,"A"
+"-Gary Redus",340,84,11,62,33,47,5,1516,376,42,284,141,219,"N","E",185,8,4,400,"A"
+"-Garry Templeton",510,126,2,42,44,35,11,5562,1578,44,703,519,256,"N","W",207,358,20,737.5,"N"
+"-Gorman Thomas",315,59,16,45,36,58,13,4677,1051,268,681,782,697,"A","W",0,0,0,NA,"A"
+"-Greg Walker",282,78,13,37,51,29,5,1649,453,73,211,280,138,"A","W",670,57,5,500,"A"
+"-Gary Ward",380,120,5,54,51,31,8,3118,900,92,444,419,240,"A","W",237,8,1,600,"A"
+"-Glenn Wilson",584,158,15,70,84,42,5,2358,636,58,265,316,134,"N","E",331,20,4,662.5,"N"
+"-Harold Baines",570,169,21,72,88,38,7,3754,1077,140,492,589,263,"A","W",295,15,5,950,"A"
+"-Hubie Brooks",306,104,14,50,58,25,7,2954,822,55,313,377,187,"N","E",116,222,15,750,"N"
+"-Howard Johnson",220,54,10,30,39,31,5,1185,299,40,145,154,128,"N","E",50,136,20,297.5,"N"
+"-Hal McRae",278,70,7,22,37,18,18,7186,2081,190,935,1088,643,"A","W",0,0,0,325,"A"
+"-Harold Reynolds",445,99,1,46,24,29,4,618,129,1,72,31,48,"A","W",278,415,16,87.5,"A"
+"-Harry Spilman",143,39,5,18,30,15,9,639,151,16,80,97,61,"N","W",138,15,1,175,"N"
+"-Herm Winningham",185,40,4,23,11,18,3,524,125,7,58,37,47,"N","E",97,2,2,90,"N"
+"-Jesse Barfield",589,170,40,107,108,69,6,2325,634,128,371,376,238,"A","E",368,20,3,1237.5,"A"
+"-Juan Beniquez",343,103,6,48,36,40,15,4338,1193,70,581,421,325,"A","E",211,56,13,430,"A"
+"-Juan Bonilla",284,69,1,33,18,25,5,1407,361,6,139,98,111,"A","E",122,140,5,NA,"N"
+"-John Cangelosi",438,103,2,65,32,71,2,440,103,2,67,32,71,"A","W",276,7,9,100,"N"
+"-Jose Canseco",600,144,33,85,117,65,2,696,173,38,101,130,69,"A","W",319,4,14,165,"A"
+"-Joe Carter",663,200,29,108,121,32,4,1447,404,57,210,222,68,"A","E",241,8,6,250,"A"
+"-Jack Clark",232,55,9,34,23,45,12,4405,1213,194,702,705,625,"N","E",623,35,3,1300,"N"
+"-Jose Cruz",479,133,10,48,72,55,17,7472,2147,153,980,1032,854,"N","W",237,5,4,773.333,"N"
+"-Julio Cruz",209,45,0,38,19,42,10,3859,916,23,557,279,478,"A","W",132,205,5,NA,"A"
+"-Jody Davis",528,132,21,61,74,41,6,2641,671,97,273,383,226,"N","E",885,105,8,1008.333,"N"
+"-Jim Dwyer",160,39,8,18,31,22,14,2128,543,56,304,268,298,"A","E",33,3,0,275,"A"
+"-Julio Franco",599,183,10,80,74,32,5,2482,715,27,330,326,158,"A","E",231,374,18,775,"A"
+"-Jim Gantner",497,136,7,58,38,26,11,3871,1066,40,450,367,241,"A","E",304,347,10,850,"A"
+"-Johnny Grubb",210,70,13,32,51,28,15,4040,1130,97,544,462,551,"A","E",0,0,0,365,"A"
+"-Jerry Hairston",225,61,5,32,26,26,11,1568,408,25,202,185,257,"A","W",132,9,0,NA,"A"
+"-Jack Howell",151,41,4,26,21,19,2,288,68,9,45,39,35,"A","W",28,56,2,95,"A"
+"-John Kruk",278,86,4,33,38,45,1,278,86,4,33,38,45,"N","W",102,4,2,110,"N"
+"-Jeffrey Leonard",341,95,6,48,42,20,10,2964,808,81,379,428,221,"N","W",158,4,5,100,"N"
+"-Jim Morrison",537,147,23,58,88,47,10,2744,730,97,302,351,174,"N","E",92,257,20,277.5,"N"
+"-John Moses",399,102,3,56,34,34,5,670,167,4,89,48,54,"A","W",211,9,3,80,"A"
+"-Jerry Mumphrey",309,94,5,37,32,26,13,4618,1330,57,616,522,436,"N","E",161,3,3,600,"N"
+"-Joe Orsulak",401,100,2,60,19,28,4,876,238,2,126,44,55,"N","E",193,11,4,NA,"N"
+"-Jorge Orta",336,93,9,35,46,23,15,5779,1610,128,730,741,497,"A","W",0,0,0,NA,"A"
+"-Jim Presley",616,163,27,83,107,32,3,1437,377,65,181,227,82,"A","W",110,308,15,200,"A"
+"-Jamie Quirk",219,47,8,24,26,17,12,1188,286,23,100,125,63,"A","W",260,58,4,NA,"A"
+"-Johnny Ray",579,174,7,67,78,58,6,3053,880,32,366,337,218,"N","E",280,479,5,657,"N"
+"-Jeff Reed",165,39,2,13,9,16,3,196,44,2,18,10,18,"A","W",332,19,2,75,"N"
+"-Jim Rice",618,200,20,98,110,62,13,7127,2163,351,1104,1289,564,"A","E",330,16,8,2412.5,"A"
+"-Jerry Royster",257,66,5,31,26,32,14,3910,979,33,518,324,382,"N","W",87,166,14,250,"A"
+"-John Russell",315,76,13,35,60,25,3,630,151,24,68,94,55,"N","E",498,39,13,155,"N"
+"-Juan Samuel",591,157,16,90,78,26,4,2020,541,52,310,226,91,"N","E",290,440,25,640,"N"
+"-John Shelby",404,92,11,54,49,18,6,1354,325,30,188,135,63,"A","E",222,5,5,300,"A"
+"-Joel Skinner",315,73,5,23,37,16,4,450,108,6,38,46,28,"A","W",227,15,3,110,"A"
+"-Jeff Stone",249,69,6,32,19,20,4,702,209,10,97,48,44,"N","E",103,8,2,NA,"N"
+"-Jim Sundberg",429,91,12,41,42,57,13,5590,1397,83,578,579,644,"A","W",686,46,4,825,"N"
+"-Jim Traber",212,54,13,28,44,18,2,233,59,13,31,46,20,"A","E",243,23,5,NA,"A"
+"-Jose Uribe",453,101,3,46,43,61,3,948,218,6,96,72,91,"N","W",249,444,16,195,"N"
+"-Jerry Willard",161,43,4,17,26,22,3,707,179,21,77,99,76,"A","W",300,12,2,NA,"A"
+"-Joel Youngblood",184,47,5,20,28,18,11,3327,890,74,419,382,304,"N","W",49,2,0,450,"N"
+"-Kevin Bass",591,184,20,83,79,38,5,1689,462,40,219,195,82,"N","W",303,12,5,630,"N"
+"-Kal Daniels",181,58,6,34,23,22,1,181,58,6,34,23,22,"N","W",88,0,3,86.5,"N"
+"-Kirk Gibson",441,118,28,84,86,68,8,2723,750,126,433,420,309,"A","E",190,2,2,1300,"A"
+"-Ken Griffey",490,150,21,69,58,35,14,6126,1839,121,983,707,600,"A","E",96,5,3,1000,"N"
+"-Keith Hernandez",551,171,13,94,83,94,13,6090,1840,128,969,900,917,"N","E",1199,149,5,1800,"N"
+"-Kent Hrbek",550,147,29,85,91,71,6,2816,815,117,405,474,319,"A","W",1218,104,10,1310,"A"
+"-Ken Landreaux",283,74,4,34,29,22,10,3919,1062,85,505,456,283,"N","W",145,5,7,737.5,"N"
+"-Kevin McReynolds",560,161,26,89,96,66,4,1789,470,65,233,260,155,"N","W",332,9,8,625,"N"
+"-Kevin Mitchell",328,91,12,51,43,33,2,342,94,12,51,44,33,"N","E",145,59,8,125,"N"
+"-Keith Moreland",586,159,12,72,79,53,9,3082,880,83,363,477,295,"N","E",181,13,4,1043.333,"N"
+"-Ken Oberkfell",503,136,5,62,48,83,10,3423,970,20,408,303,414,"N","W",65,258,8,725,"N"
+"-Ken Phelps",344,85,24,69,64,88,7,911,214,64,150,156,187,"A","W",0,0,0,300,"A"
+"-Kirby Puckett",680,223,31,119,96,34,3,1928,587,35,262,201,91,"A","W",429,8,6,365,"A"
+"-Kurt Stillwell",279,64,0,31,26,30,1,279,64,0,31,26,30,"N","W",107,205,16,75,"N"
+"-Leon Durham",484,127,20,66,65,67,7,3006,844,116,436,458,377,"N","E",1231,80,7,1183.333,"N"
+"-Len Dykstra",431,127,8,77,45,58,2,667,187,9,117,64,88,"N","E",283,8,3,202.5,"N"
+"-Larry Herndon",283,70,8,33,37,27,12,4479,1222,94,557,483,307,"A","E",156,2,2,225,"A"
+"-Lee Lacy",491,141,11,77,47,37,15,4291,1240,84,615,430,340,"A","E",239,8,2,525,"A"
+"-Len Matuszek",199,52,9,26,28,21,6,805,191,30,113,119,87,"N","W",235,22,5,265,"N"
+"-Lloyd Moseby",589,149,21,89,86,64,7,3558,928,102,513,471,351,"A","E",371,6,6,787.5,"A"
+"-Lance Parrish",327,84,22,53,62,38,10,4273,1123,212,577,700,334,"A","E",483,48,6,800,"N"
+"-Larry Parrish",464,128,28,67,94,52,13,5829,1552,210,740,840,452,"A","W",0,0,0,587.5,"A"
+"-Luis Rivera",166,34,0,20,13,17,1,166,34,0,20,13,17,"N","E",64,119,9,NA,"N"
+"-Larry Sheets",338,92,18,42,60,21,3,682,185,36,88,112,50,"A","E",0,0,0,145,"A"
+"-Lonnie Smith",508,146,8,80,44,46,9,3148,915,41,571,289,326,"A","W",245,5,9,NA,"A"
+"-Lou Whitaker",584,157,20,95,73,63,10,4704,1320,93,724,522,576,"A","E",276,421,11,420,"A"
+"-Mike Aldrete",216,54,2,27,25,33,1,216,54,2,27,25,33,"N","W",317,36,1,75,"N"
+"-Marty Barrett",625,179,4,94,60,65,5,1696,476,12,216,163,166,"A","E",303,450,14,575,"A"
+"-Mike Brown",243,53,4,18,26,27,4,853,228,23,101,110,76,"N","E",107,3,3,NA,"N"
+"-Mike Davis",489,131,19,77,55,34,7,2051,549,62,300,263,153,"A","W",310,9,9,780,"A"
+"-Mike Diaz",209,56,12,22,36,19,2,216,58,12,24,37,19,"N","E",201,6,3,90,"N"
+"-Mariano Duncan",407,93,8,47,30,30,2,969,230,14,121,69,68,"N","W",172,317,25,150,"N"
+"-Mike Easler",490,148,14,64,78,49,13,3400,1000,113,445,491,301,"A","E",0,0,0,700,"N"
+"-Mike Fitzgerald",209,59,6,20,37,27,4,884,209,14,66,106,92,"N","E",415,35,3,NA,"N"
+"-Mel Hall",442,131,18,68,77,33,6,1416,398,47,210,203,136,"A","E",233,7,7,550,"A"
+"-Mickey Hatcher",317,88,3,40,32,19,8,2543,715,28,269,270,118,"A","W",220,16,4,NA,"A"
+"-Mike Heath",288,65,8,30,36,27,9,2815,698,55,315,325,189,"N","E",259,30,10,650,"A"
+"-Mike Kingery",209,54,3,25,14,12,1,209,54,3,25,14,12,"A","W",102,6,3,68,"A"
+"-Mike LaValliere",303,71,3,18,30,36,3,344,76,3,20,36,45,"N","E",468,47,6,100,"N"
+"-Mike Marshall",330,77,19,47,53,27,6,1928,516,90,247,288,161,"N","W",149,8,6,670,"N"
+"-Mike Pagliarulo",504,120,28,71,71,54,3,1085,259,54,150,167,114,"A","E",103,283,19,175,"A"
+"-Mark Salas",258,60,8,28,33,18,3,638,170,17,80,75,36,"A","W",358,32,8,137,"A"
+"-Mike Schmidt",20,1,0,0,0,0,2,41,9,2,6,7,4,"N","E",78,220,6,2127.333,"N"
+"-Mike Scioscia",374,94,5,36,26,62,7,1968,519,26,181,199,288,"N","W",756,64,15,875,"N"
+"-Mickey Tettleton",211,43,10,26,35,39,3,498,116,14,59,55,78,"A","W",463,32,8,120,"A"
+"-Milt Thompson",299,75,6,38,23,26,3,580,160,8,71,33,44,"N","E",212,1,2,140,"N"
+"-Mitch Webster",576,167,8,89,49,57,4,822,232,19,132,83,79,"N","E",325,12,8,210,"N"
+"-Mookie Wilson",381,110,9,61,45,32,7,3015,834,40,451,249,168,"N","E",228,7,5,800,"N"
+"-Marvell Wynne",288,76,7,34,37,15,4,1644,408,16,198,120,113,"N","W",203,3,3,240,"N"
+"-Mike Young",369,93,9,43,42,49,5,1258,323,54,181,177,157,"A","E",149,1,6,350,"A"
+"-Nick Esasky",330,76,12,35,41,47,4,1367,326,55,167,198,167,"N","W",512,30,5,NA,"N"
+"-Ozzie Guillen",547,137,2,58,47,12,2,1038,271,3,129,80,24,"A","W",261,459,22,175,"A"
+"-Oddibe McDowell",572,152,18,105,49,65,2,978,249,36,168,91,101,"A","W",325,13,3,200,"A"
+"-Omar Moreno",359,84,4,46,27,21,12,4992,1257,37,699,386,387,"N","W",151,8,5,NA,"N"
+"-Ozzie Smith",514,144,0,67,54,79,9,4739,1169,13,583,374,528,"N","E",229,453,15,1940,"N"
+"-Ozzie Virgil",359,80,15,45,48,63,7,1493,359,61,176,202,175,"N","W",682,93,13,700,"N"
+"-Phil Bradley",526,163,12,88,50,77,4,1556,470,38,245,167,174,"A","W",250,11,1,750,"A"
+"-Phil Garner",313,83,9,43,41,30,14,5885,1543,104,751,714,535,"N","W",58,141,23,450,"N"
+"-Pete Incaviglia",540,135,30,82,88,55,1,540,135,30,82,88,55,"A","W",157,6,14,172,"A"
+"-Paul Molitor",437,123,9,62,55,40,9,4139,1203,79,676,390,364,"A","E",82,170,15,1260,"A"
+"-Pete O'Brien",551,160,23,86,90,87,5,2235,602,75,278,328,273,"A","W",1224,115,11,NA,"A"
+"-Pete Rose",237,52,0,15,25,30,24,14053,4256,160,2165,1314,1566,"N","W",523,43,6,750,"N"
+"-Pat Sheridan",236,56,6,41,19,21,5,1257,329,24,166,125,105,"A","E",172,1,4,190,"A"
+"-Pat Tabler",473,154,6,61,48,29,6,1966,566,29,250,252,178,"A","E",846,84,9,580,"A"
+"-Rafael Belliard",309,72,0,33,31,26,5,354,82,0,41,32,26,"N","E",117,269,12,130,"N"
+"-Rick Burleson",271,77,5,35,29,33,12,4933,1358,48,630,435,403,"A","W",62,90,3,450,"A"
+"-Randy Bush",357,96,7,50,45,39,5,1394,344,43,178,192,136,"A","W",167,2,4,300,"A"
+"-Rick Cerone",216,56,4,22,18,15,12,2796,665,43,266,304,198,"A","E",391,44,4,250,"A"
+"-Ron Cey",256,70,13,42,36,44,16,7058,1845,312,965,1128,990,"N","E",41,118,8,1050,"A"
+"-Rob Deer",466,108,33,75,86,72,3,652,142,44,102,109,102,"A","E",286,8,8,215,"A"
+"-Rick Dempsey",327,68,13,42,29,45,18,3949,939,78,438,380,466,"A","E",659,53,7,400,"A"
+"-Rich Gedman",462,119,16,49,65,37,7,2131,583,69,244,288,150,"A","E",866,65,6,NA,"A"
+"-Ron Hassey",341,110,9,45,49,46,9,2331,658,50,249,322,274,"A","E",251,9,4,560,"A"
+"-Rickey Henderson",608,160,28,130,74,89,8,4071,1182,103,862,417,708,"A","E",426,4,6,1670,"A"
+"-Reggie Jackson",419,101,18,65,58,92,20,9528,2510,548,1509,1659,1342,"A","W",0,0,0,487.5,"A"
+"-Ricky Jones",33,6,0,2,4,7,1,33,6,0,2,4,7,"A","W",205,5,4,NA,"A"
+"-Ron Kittle",376,82,21,42,60,35,5,1770,408,115,238,299,157,"A","W",0,0,0,425,"A"
+"-Ray Knight",486,145,11,51,76,40,11,3967,1102,67,410,497,284,"N","E",88,204,16,500,"A"
+"-Randy Kutcher",186,44,7,28,16,11,1,186,44,7,28,16,11,"N","W",99,3,1,NA,"N"
+"-Rudy Law",307,80,1,42,36,29,7,2421,656,18,379,198,184,"A","W",145,2,2,NA,"A"
+"-Rick Leach",246,76,5,35,39,13,6,912,234,12,102,96,80,"A","E",44,0,1,250,"A"
+"-Rick Manning",205,52,8,31,27,17,12,5134,1323,56,643,445,459,"A","E",155,3,2,400,"A"
+"-Rance Mulliniks",348,90,11,50,45,43,10,2288,614,43,295,273,269,"A","E",60,176,6,450,"A"
+"-Ron Oester",523,135,8,52,44,52,9,3368,895,39,377,284,296,"N","W",367,475,19,750,"N"
+"-Rey Quinones",312,68,2,32,22,24,1,312,68,2,32,22,24,"A","E",86,150,15,70,"A"
+"-Rafael Ramirez",496,119,8,57,33,21,7,3358,882,36,365,280,165,"N","W",155,371,29,875,"N"
+"-Ronn Reynolds",126,27,3,8,10,5,4,239,49,3,16,13,14,"N","E",190,2,9,190,"N"
+"-Ron Roenicke",275,68,5,42,42,61,6,961,238,16,128,104,172,"N","E",181,3,2,191,"N"
+"-Ryne Sandberg",627,178,14,68,76,46,6,3146,902,74,494,345,242,"N","E",309,492,5,740,"N"
+"-Rafael Santana",394,86,1,38,28,36,4,1089,267,3,94,71,76,"N","E",203,369,16,250,"N"
+"-Rick Schu",208,57,8,32,25,18,3,653,170,17,98,54,62,"N","E",42,94,13,140,"N"
+"-Ruben Sierra",382,101,16,50,55,22,1,382,101,16,50,55,22,"A","W",200,7,6,97.5,"A"
+"-Roy Smalley",459,113,20,59,57,68,12,5348,1369,155,713,660,735,"A","W",0,0,0,740,"A"
+"-Robby Thompson",549,149,7,73,47,42,1,549,149,7,73,47,42,"N","W",255,450,17,140,"N"
+"-Rob Wilfong",288,63,3,25,33,16,10,2682,667,38,315,259,204,"A","W",135,257,7,341.667,"A"
+"-Reggie Williams",303,84,4,35,32,23,2,312,87,4,39,32,23,"N","W",179,5,3,NA,"N"
+"-Robin Yount",522,163,9,82,46,62,13,7037,2019,153,1043,827,535,"A","E",352,9,1,1000,"A"
+"-Steve Balboni",512,117,29,54,88,43,6,1750,412,100,204,276,155,"A","W",1236,98,18,100,"A"
+"-Scott Bradley",220,66,5,20,28,13,3,290,80,5,27,31,15,"A","W",281,21,3,90,"A"
+"-Sid Bream",522,140,16,73,77,60,4,730,185,22,93,106,86,"N","E",1320,166,17,200,"N"
+"-Steve Buechele",461,112,18,54,54,35,2,680,160,24,76,75,49,"A","W",111,226,11,135,"A"
+"-Shawon Dunston",581,145,17,66,68,21,2,831,210,21,106,86,40,"N","E",320,465,32,155,"N"
+"-Scott Fletcher",530,159,3,82,50,47,6,1619,426,11,218,149,163,"A","W",196,354,15,475,"A"
+"-Steve Garvey",557,142,21,58,81,23,18,8759,2583,271,1138,1299,478,"N","W",1160,53,7,1450,"N"
+"-Steve Jeltz",439,96,0,44,36,65,4,711,148,1,68,56,99,"N","E",229,406,22,150,"N"
+"-Steve Lombardozzi",453,103,8,53,33,52,2,507,123,8,63,39,58,"A","W",289,407,6,105,"A"
+"-Spike Owen",528,122,1,67,45,51,4,1716,403,12,211,146,155,"A","W",209,372,17,350,"A"
+"-Steve Sax",633,210,6,91,56,59,6,3070,872,19,420,230,274,"N","W",367,432,16,90,"N"
+"-Tony Armas",16,2,0,1,0,0,2,28,4,0,1,0,0,"A","E",247,4,8,NA,"A"
+"-Tony Bernazard",562,169,17,88,73,53,8,3181,841,61,450,342,373,"A","E",351,442,17,530,"A"
+"-Tom Brookens",281,76,3,42,25,20,8,2658,657,48,324,300,179,"A","E",106,144,7,341.667,"A"
+"-Tom Brunansky",593,152,23,69,75,53,6,2765,686,133,369,384,321,"A","W",315,10,6,940,"A"
+"-Tony Fernandez",687,213,10,91,65,27,4,1518,448,15,196,137,89,"A","E",294,445,13,350,"A"
+"-Tim Flannery",368,103,3,48,28,54,8,1897,493,9,207,162,198,"N","W",209,246,3,326.667,"N"
+"-Tom Foley",263,70,1,26,23,30,4,888,220,9,83,82,86,"N","E",81,147,4,250,"N"
+"-Tony Gwynn",642,211,14,107,59,52,5,2364,770,27,352,230,193,"N","W",337,19,4,740,"N"
+"-Terry Harper",265,68,8,26,30,29,7,1337,339,32,135,163,128,"N","W",92,5,3,425,"A"
+"-Toby Harrah",289,63,7,36,41,44,17,7402,1954,195,1115,919,1153,"A","W",166,211,7,NA,"A"
+"-Tommy Herr",559,141,2,48,61,73,8,3162,874,16,421,349,359,"N","E",352,414,9,925,"N"
+"-Tim Hulett",520,120,17,53,44,21,4,927,227,22,106,80,52,"A","W",70,144,11,185,"A"
+"-Terry Kennedy",19,4,1,2,3,1,1,19,4,1,2,3,1,"N","W",692,70,8,920,"A"
+"-Tito Landrum",205,43,2,24,17,20,7,854,219,12,105,99,71,"N","E",131,6,1,286.667,"N"
+"-Tim Laudner",193,47,10,21,29,24,6,1136,256,42,129,139,106,"A","W",299,13,5,245,"A"
+"-Tom O'Malley",181,46,1,19,18,17,5,937,238,9,88,95,104,"A","E",37,98,9,NA,"A"
+"-Tom Paciorek",213,61,4,17,22,3,17,4061,1145,83,488,491,244,"A","W",178,45,4,235,"A"
+"-Tony Pena",510,147,10,56,52,53,7,2872,821,63,307,340,174,"N","E",810,99,18,1150,"N"
+"-Terry Pendleton",578,138,1,56,59,34,3,1399,357,7,149,161,87,"N","E",133,371,20,160,"N"
+"-Tony Perez",200,51,2,14,29,25,23,9778,2732,379,1272,1652,925,"N","W",398,29,7,NA,"N"
+"-Tony Phillips",441,113,5,76,52,76,5,1546,397,17,226,149,191,"A","W",160,290,11,425,"A"
+"-Terry Puhl",172,42,3,17,14,15,10,4086,1150,57,579,363,406,"N","W",65,0,0,900,"N"
+"-Tim Raines",580,194,9,91,62,78,8,3372,1028,48,604,314,469,"N","E",270,13,6,NA,"N"
+"-Ted Simmons",127,32,4,14,25,12,19,8396,2402,242,1048,1348,819,"N","W",167,18,6,500,"N"
+"-Tim Teufel",279,69,4,35,31,32,4,1359,355,31,180,148,158,"N","E",133,173,9,277.5,"N"
+"-Tim Wallach",480,112,18,50,71,44,7,3031,771,110,338,406,239,"N","E",94,270,16,750,"N"
+"-Vince Coleman",600,139,0,94,29,60,2,1236,309,1,201,69,110,"N","E",300,12,9,160,"N"
+"-Von Hayes",610,186,19,107,98,74,6,2728,753,69,399,366,286,"N","E",1182,96,13,1300,"N"
+"-Vance Law",360,81,5,37,44,37,7,2268,566,41,279,257,246,"N","E",170,284,3,525,"N"
+"-Wally Backman",387,124,1,67,27,36,7,1775,506,6,272,125,194,"N","E",186,290,17,550,"N"
+"-Wade Boggs",580,207,8,107,71,105,5,2778,978,32,474,322,417,"A","E",121,267,19,1600,"A"
+"-Will Clark",408,117,11,66,41,34,1,408,117,11,66,41,34,"N","W",942,72,11,120,"N"
+"-Wally Joyner",593,172,22,82,100,57,1,593,172,22,82,100,57,"A","W",1222,139,15,165,"A"
+"-Wayne Krenchicki",221,53,2,21,23,22,8,1063,283,15,107,124,106,"N","E",325,58,6,NA,"N"
+"-Willie McGee",497,127,7,65,48,37,5,2703,806,32,379,311,138,"N","E",325,9,3,700,"N"
+"-Willie Randolph",492,136,5,76,50,94,12,5511,1511,39,897,451,875,"A","E",313,381,20,875,"A"
+"-Wayne Tolleson",475,126,3,61,43,52,6,1700,433,7,217,93,146,"A","W",37,113,7,385,"A"
+"-Willie Upshaw",573,144,9,85,60,78,8,3198,857,97,470,420,332,"A","E",1314,131,12,960,"A"
+"-Willie Wilson",631,170,9,77,44,31,11,4908,1457,30,775,357,249,"A","W",408,4,3,1000,"A"

M1/Statistical Learning/data/breast_cancer.csv

@@ -0,0 +1,117 @@
+Age,BMI,Glucose,Insulin,HOMA,Leptin,Adiponectin,Resistin,MCP.1,Classification
+48,23.5,70,2.707,0.467408667,8.8071,9.7024,7.99585,417.114,1
+83,20.69049454,92,3.115,0.706897333,8.8438,5.429285,4.06405,468.786,1
+82,23.12467037,91,4.498,1.009651067,17.9393,22.43204,9.27715,554.697,1
+68,21.36752137,77,3.226,0.612724933,9.8827,7.16956,12.766,928.22,1
+86,21.11111111,92,3.549,0.8053864,6.6994,4.81924,10.57635,773.92,1
+49,22.85445769,92,3.226,0.732086933,6.8317,13.67975,10.3176,530.41,1
+89,22.7,77,4.69,0.890787333,6.964,5.589865,12.9361,1256.083,1
+76,23.8,118,6.47,1.883201333,4.311,13.25132,5.1042,280.694,1
+73,22,97,3.35,0.801543333,4.47,10.358725,6.28445,136.855,1
+75,23,83,4.952,1.013839467,17.127,11.57899,7.0913,318.302,1
+34,21.47,78,3.469,0.6674356,14.57,13.11,6.92,354.6,1
+29,23.01,82,5.663,1.145436133,35.59,26.72,4.58,174.8,1
+25,22.86,82,4.09,0.827270667,20.45,23.67,5.14,313.73,1
+24,18.67,88,6.107,1.33,8.88,36.06,6.85,632.22,1
+38,23.34,75,5.782,1.06967,15.26,17.95,9.35,165.02,1
+44,20.76,86,7.553,1.6,14.09,20.32,7.64,63.61,1
+47,22.03,84,2.869,0.59,26.65,38.04,3.32,191.72,1
+61,32.03895937,85,18.077,3.790144333,30.7729,7.780255,13.68392,444.395,1
+64,34.5297228,95,4.427,1.037393667,21.2117,5.46262,6.70188,252.449,1
+32,36.51263743,87,14.026,3.0099796,49.3727,5.1,17.10223,588.46,1
+36,28.57667585,86,4.345,0.921719333,15.1248,8.6,9.1539,534.224,1
+34,31.97501487,87,4.53,0.972138,28.7502,7.64276,5.62592,572.783,1
+29,32.27078777,84,5.81,1.203832,45.6196,6.209635,24.6033,904.981,1
+35,30.27681661,84,4.376,0.9067072,39.2134,9.048185,16.43706,733.797,1
+54,30.48315806,90,5.537,1.229214,12.331,9.73138,10.19299,1227.91,1
+45,37.03560819,83,6.76,1.383997333,39.9802,4.617125,8.70448,586.173,1
+50,38.57875854,106,6.703,1.752611067,46.6401,4.667645,11.78388,887.16,1
+66,31.44654088,90,9.245,2.05239,45.9624,10.35526,23.3819,1102.11,1
+35,35.2507611,90,6.817,1.513374,50.6094,6.966895,22.03703,667.928,1
+36,34.17489,80,6.59,1.300426667,10.2809,5.065915,15.72187,581.313,1
+66,36.21227888,101,15.533,3.869788067,74.7069,7.53955,22.32024,864.968,1
+53,36.7901662,101,10.175,2.534931667,27.1841,20.03,10.26309,695.754,1
+28,35.85581466,87,8.576,1.8404096,68.5102,4.7942,21.44366,358.624,1
+43,34.42217362,89,23.194,5.091856133,31.2128,8.300955,6.71026,960.246,1
+51,27.68877813,77,3.855,0.732193,20.092,3.19209,10.37518,473.859,1
+67,29.60676726,79,5.819,1.133929133,21.9033,2.19428,4.2075,585.307,1
+66,31.2385898,82,4.181,0.845676933,16.2247,4.267105,3.29175,634.602,1
+69,35.09270153,101,5.646,1.4066068,83.4821,6.796985,82.1,263.499,1
+60,26.34929208,103,5.138,1.305394533,24.2998,2.19428,20.2535,378.996,1
+77,35.58792924,76,3.881,0.727558133,21.7863,8.12555,17.2615,618.272,1
+76,29.2184076,83,5.376,1.1006464,28.562,7.36996,8.04375,698.789,1
+76,27.2,94,14.07,3.262364,35.891,9.34663,8.4156,377.227,1
+75,27.3,85,5.197,1.089637667,10.39,9.000805,7.5767,335.393,1
+69,32.5,93,5.43,1.245642,15.145,11.78796,11.78796,270.142,1
+71,30.3,102,8.34,2.098344,56.502,8.13,4.2989,200.976,1
+66,27.7,90,6.042,1.341324,24.846,7.652055,6.7052,225.88,1
+75,25.7,94,8.079,1.8732508,65.926,3.74122,4.49685,206.802,1
+78,25.3,60,3.508,0.519184,6.633,10.567295,4.6638,209.749,1
+69,29.4,89,10.704,2.3498848,45.272,8.2863,4.53,215.769,1
+85,26.6,96,4.462,1.0566016,7.85,7.9317,9.6135,232.006,1
+76,27.1,110,26.211,7.111918,21.778,4.935635,8.49395,45.843,1
+77,25.9,85,4.58,0.960273333,13.74,9.75326,11.774,488.829,1
+45,21.30394858,102,13.852,3.4851632,7.6476,21.056625,23.03408,552.444,2
+45,20.82999519,74,4.56,0.832352,7.7529,8.237405,28.0323,382.955,2
+49,20.9566075,94,12.305,2.853119333,11.2406,8.412175,23.1177,573.63,2
+34,24.24242424,92,21.699,4.9242264,16.7353,21.823745,12.06534,481.949,2
+42,21.35991456,93,2.999,0.6879706,19.0826,8.462915,17.37615,321.919,2
+68,21.08281329,102,6.2,1.55992,9.6994,8.574655,13.74244,448.799,2
+51,19.13265306,93,4.364,1.0011016,11.0816,5.80762,5.57055,90.6,2
+62,22.65625,92,3.482,0.790181867,9.8648,11.236235,10.69548,703.973,2
+38,22.4996371,95,5.261,1.232827667,8.438,4.77192,15.73606,199.055,2
+69,21.51385851,112,6.683,1.846290133,32.58,4.138025,15.69876,713.239,2
+49,21.36752137,78,2.64,0.507936,6.3339,3.886145,22.94254,737.672,2
+51,22.89281998,103,2.74,0.696142667,8.0163,9.349775,11.55492,359.232,2
+59,22.83287935,98,6.862,1.658774133,14.9037,4.230105,8.2049,355.31,2
+45,23.14049587,116,4.902,1.4026256,17.9973,4.294705,5.2633,518.586,2
+54,24.21875,86,3.73,0.791257333,8.6874,3.70523,10.34455,635.049,2
+64,22.22222222,98,5.7,1.37788,12.1905,4.783985,13.91245,395.976,2
+46,20.83,88,3.42,0.742368,12.87,18.55,13.56,301.21,2
+44,19.56,114,15.89,4.468268,13.08,20.37,4.62,220.66,2
+45,20.26,92,3.44,0.780650667,7.65,16.67,7.84,193.87,2
+44,24.74,106,58.46,15.28534133,18.16,16.1,5.31,244.75,2
+51,18.37,105,6.03,1.56177,9.62,12.76,3.21,513.66,2
+72,23.62,105,4.42,1.14478,21.78,17.86,4.82,195.94,2
+46,22.21,86,36.94,7.836205333,10.16,9.76,5.68,312,2
+43,26.5625,101,10.555,2.629602333,9.8,6.420295,16.1,806.724,2
+55,31.97501487,92,16.635,3.775036,37.2234,11.018455,7.16514,483.377,2
+43,31.25,103,4.328,1.099600533,25.7816,12.71896,38.6531,775.322,2
+86,26.66666667,201,41.611,20.6307338,47.647,5.357135,24.3701,1698.44,2
+41,26.6727633,97,22.033,5.271762467,44.7059,13.494865,27.8325,783.796,2
+59,28.67262608,77,3.188,0.605507467,17.022,16.44048,31.6904,910.489,2
+81,31.64036818,100,9.669,2.38502,38.8066,10.636525,29.5583,426.175,2
+48,32.46191136,99,28.677,7.0029234,46.076,21.57,10.15726,738.034,2
+71,25.51020408,112,10.395,2.871792,19.0653,5.4861,42.7447,799.898,2
+42,29.296875,98,4.172,1.008511467,12.2617,6.695585,53.6717,1041.843,2
+65,29.666548,85,14.649,3.071407,26.5166,7.28287,19.46324,1698.44,2
+48,28.125,90,2.54,0.56388,15.5325,10.22231,16.11032,1698.44,2
+85,27.68877813,196,51.814,25.05034187,70.8824,7.901685,55.2153,1078.359,2
+48,31.25,199,12.162,5.9699204,18.1314,4.104105,53.6308,1698.44,2
+58,29.15451895,139,16.582,5.685415067,22.8884,10.26266,13.97399,923.886,2
+40,30.83653053,128,41.894,13.22733227,31.0385,6.160995,17.55503,638.261,2
+82,31.21748179,100,18.077,4.458993333,31.6453,9.92365,19.94687,994.316,2
+52,30.8012487,87,30.212,6.4834952,29.2739,6.26854,24.24591,764.667,2
+49,32.46191136,134,24.887,8.225983067,42.3914,10.79394,5.768,656.393,2
+60,31.23140988,131,30.13,9.736007333,37.843,8.40443,11.50005,396.021,2
+49,29.77777778,70,8.396,1.449709333,51.3387,10.73174,20.76801,602.486,2
+44,27.88761707,99,9.208,2.2485936,12.6757,5.47817,23.03306,407.206,2
+40,27.63605442,103,2.432,0.617890133,14.3224,6.78387,26.0136,293.123,2
+71,27.91551882,104,18.2,4.668906667,53.4997,1.65602,49.24184,256.001,2
+69,28.44444444,108,8.808,2.3464512,14.7485,5.288025,16.48508,353.568,2
+74,28.65013774,88,3.012,0.6538048,31.1233,7.65222,18.35574,572.401,2
+66,26.5625,89,6.524,1.432235467,14.9084,8.42996,14.91922,269.487,2
+65,30.91557669,97,10.491,2.5101466,44.0217,3.71009,20.4685,396.648,2
+72,29.13631634,83,10.949,2.241625267,26.8081,2.78491,14.76966,232.018,2
+57,34.83814777,95,12.548,2.940414667,33.1612,2.36495,9.9542,655.834,2
+73,37.109375,134,5.636,1.862885867,41.4064,3.335665,6.89235,788.902,2
+45,29.38475666,90,4.713,1.046286,23.8479,6.644245,15.55625,621.273,2
+46,33.18,92,5.75,1.304866667,18.69,9.16,8.89,209.19,2
+68,35.56,131,8.15,2.633536667,17.87,11.9,4.19,198.4,2
+75,30.48,152,7.01,2.628282667,50.53,10.06,11.73,99.45,2
+54,36.05,119,11.91,3.495982,89.27,8.01,5.06,218.28,2
+45,26.85,92,3.33,0.755688,54.68,12.1,10.96,268.23,2
+62,26.84,100,4.53,1.1174,12.45,21.42,7.32,330.16,2
+65,32.05,97,5.73,1.370998,61.48,22.54,10.33,314.05,2
+72,25.59,82,2.82,0.570392,24.96,33.75,3.27,392.46,2
+86,27.18,138,19.91,6.777364,90.28,14.11,4.35,90.09,2