Refactor code for improved readability and consistency across multiple Jupyter notebooks

- Added missing commas in various print statements and function calls for better syntax.
- Reformatted code to enhance clarity, including breaking long lines and aligning parameters.
- Updated function signatures to use float type for sigma parameters instead of int for better precision.
- Cleaned up comments and documentation strings for clarity and consistency.
- Ensured consistent formatting in plotting functions and data handling.

M2/Machine Learning/TP_1/2025_TP_1_M2_ISF.ipynb

@@ -144,7 +144,8 @@
    ],
    "source": [
     "salutation = \"Bonjour, monsieur {}. Comment allez vous en ce {}?\".format(\n",
-    "    \"XX\", \"Mardi 19 septembre\"\n",
+    "    \"XX\",\n",
+    "    \"Mardi 19 septembre\",\n",
     ")\n",
     "print(salutation)"
    ]
@@ -259,7 +260,7 @@
    ],
    "source": [
     "a = 2\n",
-    "if 5 > a:\n",
+    "if a < 5:\n",
     "    print(\"Cinq!\")\n",
     "else:\n",
     "    print(\"a!\")\n",
@@ -2612,11 +2613,10 @@
     "            binaires.append(col)\n",
     "        else:\n",
     "            quantitatives.append(col)\n",
+    "    elif len(data_set[col].dropna().unique()) == 2:\n",
+    "        binaires.append(col)\n",
     "    else:\n",
-    "        if len(data_set[col].dropna().unique()) == 2:\n",
-    "            binaires.append(col)\n",
-    "        else:\n",
-    "            categorielles.append(col)\n",
+    "        categorielles.append(col)\n",
     "\n",
     "print(\"Variables quantitatives :\", quantitatives)\n",
     "print(\"\\nVariables catégorielles :\", categorielles)\n",
@@ -3527,7 +3527,7 @@
    "source": [
     "fig = px.histogram(data_set.sort_values(\"ANNEE_CTR\"), x=\"ANNEE_CTR\")\n",
     "fig.update_xaxes(\n",
-    "    type=\"category\"\n",
+    "    type=\"category\",\n",
     ")  # Cette ligne permet de forcer la variable comme variable catégorielle et non numérique\n",
     "\n",
     "fig.show()"
@@ -18662,7 +18662,7 @@
     "    data_set,\n",
     "    x=\"CONTRAT_ANCIENNETE\",\n",
     "    category_orders={\n",
-    "        \"CONTRAT_ANCIENNETE\": [\"(-1,0]\", \"(0,1]\", \"(1,2]\", \"(2,5]\", \"(5,10]\"]\n",
+    "        \"CONTRAT_ANCIENNETE\": [\"(-1,0]\", \"(0,1]\", \"(1,2]\", \"(2,5]\", \"(5,10]\"],\n",
     "    },\n",
     ")\n",
     "fig.show()"
@@ -48902,7 +48902,7 @@
     "    data_set,\n",
     "    x=\"GROUPE_KM\",\n",
     "    category_orders={\n",
-    "        \"GROUPE_KM\": [\"[0;20000[\", \"[20000;40000[\", \"[40000;60000[\", \"[60000;99999[\"]\n",
+    "        \"GROUPE_KM\": [\"[0;20000[\", \"[20000;40000[\", \"[40000;60000[\", \"[60000;99999[\"],\n",
     "    },\n",
     ")\n",
     "fig.show()"
@@ -64021,7 +64021,7 @@
     "# Ecrivez votre code ici\n",
     "fig = px.histogram(data_set.sort_values(\"ZONE_RISQUE\"), x=\"ZONE_RISQUE\")\n",
     "fig.update_xaxes(\n",
-    "    type=\"category\"\n",
+    "    type=\"category\",\n",
     ")  # Cette ligne permet de forcer la variable comme variable catégorielle et non numérique\n",
     "\n",
     "fig.show()"
@@ -64877,10 +64877,11 @@
    "source": [
     "# Ecrivez votre code ici\n",
     "fig = px.histogram(\n",
-    "    data_set.sort_values(\"AGE_ASSURE_PRINCIPAL\"), x=\"AGE_ASSURE_PRINCIPAL\"\n",
+    "    data_set.sort_values(\"AGE_ASSURE_PRINCIPAL\"),\n",
+    "    x=\"AGE_ASSURE_PRINCIPAL\",\n",
     ")\n",
     "fig.update_xaxes(\n",
-    "    type=\"category\"\n",
+    "    type=\"category\",\n",
     ")  # Cette ligne permet de forcer la variable comme variable catégorielle et non numérique\n",
     "\n",
     "fig.show()"
@@ -79999,7 +80000,7 @@
     "# Ecrivez votre code ici\n",
     "fig = px.histogram(data_set.sort_values(\"GENRE\"), x=\"GENRE\")\n",
     "fig.update_xaxes(\n",
-    "    type=\"category\"\n",
+    "    type=\"category\",\n",
     ")  # Cette ligne permet de forcer la variable comme variable catégorielle et non numérique\n",
     "\n",
     "fig.show()"
@@ -80064,7 +80065,8 @@
     "    [\n",
     "        data_h,\n",
     "        pd.DataFrame(\n",
-    "            [[13, \"M\", 0]], columns=[\"AGE_ASSURE_PRINCIPAL\", \"GENRE\", \"counts\"]\n",
+    "            [[13, \"M\", 0]],\n",
+    "            columns=[\"AGE_ASSURE_PRINCIPAL\", \"GENRE\", \"counts\"],\n",
     "        ),\n",
     "    ],\n",
     "    ignore_index=True,\n",
@@ -82329,17 +82331,17 @@
     "# ANNEE_CONSTRUCTION,VALEUR_DU_BIEN,DEUXIEME_CONDUCTEUR)\n",
     "\n",
     "data_retraitee[\"GROUPE_KM\"] = data_retraitee[\"GROUPE_KM\"].fillna(\n",
-    "    data_retraitee[\"GROUPE_KM\"].mode()[0]\n",
+    "    data_retraitee[\"GROUPE_KM\"].mode()[0],\n",
     ")\n",
     "data_retraitee[\"GENRE\"] = data_retraitee[\"GENRE\"].fillna(\"M\")\n",
     "data_retraitee[\"ANNEE_CONSTRUCTION\"] = data_retraitee[\"ANNEE_CONSTRUCTION\"].fillna(\n",
-    "    data_retraitee[\"ANNEE_CONSTRUCTION\"].median()\n",
+    "    data_retraitee[\"ANNEE_CONSTRUCTION\"].median(),\n",
     ")\n",
     "data_retraitee[\"VALEUR_DU_BIEN\"] = data_retraitee[\"VALEUR_DU_BIEN\"].fillna(\n",
-    "    data_retraitee[\"VALEUR_DU_BIEN\"].mode()[0]\n",
+    "    data_retraitee[\"VALEUR_DU_BIEN\"].mode()[0],\n",
     ")\n",
     "data_retraitee[\"DEUXIEME_CONDUCTEUR\"] = data_retraitee[\"DEUXIEME_CONDUCTEUR\"].fillna(\n",
-    "    False\n",
+    "    False,\n",
     ")"
    ]
   },
@@ -83750,7 +83752,10 @@
    "source": [
     "# Représentation graphique\n",
     "fig = px.line(\n",
-    "    plot_data, x=\"AGE_ASSURE_PRINCIPAL\", y=\"FREQ\", title=\"Sinistralité selon l'âge\"\n",
+    "    plot_data,\n",
+    "    x=\"AGE_ASSURE_PRINCIPAL\",\n",
+    "    y=\"FREQ\",\n",
+    "    title=\"Sinistralité selon l'âge\",\n",
     ")\n",
     "fig.show()"
    ]
@@ -85539,7 +85544,10 @@
     "\n",
     "# Représentation graphique\n",
     "fig = px.scatter(\n",
-    "    plot_data, x=\"ENERGIE\", y=\"FREQ\", title=\"Sinistralité selon le carburant\"\n",
+    "    plot_data,\n",
+    "    x=\"ENERGIE\",\n",
+    "    y=\"FREQ\",\n",
+    "    title=\"Sinistralité selon le carburant\",\n",
     ")\n",
     "fig.show()"
    ]
@@ -86416,7 +86424,10 @@
     "\n",
     "# Représentation graphique\n",
     "fig = px.scatter(\n",
-    "    plot_data, x=\"VALEUR_DU_BIEN\", y=\"CM\", title=\"Coût moyen selon le prix\"\n",
+    "    plot_data,\n",
+    "    x=\"VALEUR_DU_BIEN\",\n",
+    "    y=\"CM\",\n",
+    "    title=\"Coût moyen selon le prix\",\n",
     ")\n",
     "fig.show()"
    ]
@@ -89044,7 +89055,10 @@
     "\n",
     "# Représentation graphique\n",
     "fig = px.scatter(\n",
-    "    plot_data, x=\"GENRE\", y=\"CM\", title=\"Coût moyen selon l'âge de l'assuré\"\n",
+    "    plot_data,\n",
+    "    x=\"GENRE\",\n",
+    "    y=\"CM\",\n",
+    "    title=\"Coût moyen selon l'âge de l'assuré\",\n",
     ")\n",
     "fig.show()"
    ]