Refactor code for improved readability and consistency across R Markdown files

- Updated comments and code formatting in `3-td_ggplot2 - enonce.Rmd` for clarity.
- Enhanced code structure in `4-td_graphiques - enonce.Rmd` by organizing options and library calls.
- Replaced pipe operator `%>%` with `|>` in `Code_Lec3.Rmd` for consistency with modern R syntax.
- Cleaned up commented-out code and ensured consistent spacing in ggplot calls.

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

@@ -1,5 +1,5 @@
 ```{r}
-setwd('/Users/arthurdanjou/Workspace/studies/M1/General Linear Models/TP1-bis')
+setwd("/Users/arthurdanjou/Workspace/studies/M1/General Linear Models/TP1-bis")
 
 library(tidyverse)
 options(scipen = 999, digits = 5)
@@ -56,8 +56,8 @@ summary(model)
 coef(model)
 ```
 ```{r}
-data <- data %>%
-  mutate(yhat = beta0 + beta1 * poids) %>%
+data <- data |>
+  mutate(yhat = beta0 + beta1 * poids) |>
   mutate(residuals = cholesterol - yhat)
 
 data
@@ -71,8 +71,8 @@ ggplot(data, aes(x = poids, y = cholesterol)) +
 ```{r}
 mean(data[, "cholesterol"])
 mean(data[, "yhat"])
-mean(data[, "residuals"]) %>% round(10)
-cov(data[, "residuals"], data[, "poids"]) %>% round(10)
+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
@@ -117,10 +117,10 @@ t <- qt(0.975, dof)
 sigma_hat <- sigma(model)
 n <- nrow(data)
 
-data <- data %>%
+data <- data |>
   mutate(error = t *
     sigma_hat *
-    sqrt(1 / n + (poids - mean(poids))^2 / RSS)) %>%
+    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)) +

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

@@ -1,5 +1,5 @@
 ```{r}
-setwd('/Users/arthurdanjou/Workspace/studies/M1/General Linear Models/TP2-bis')
+setwd("/Users/arthurdanjou/Workspace/studies/M1/General Linear Models/TP2-bis")
 
 library(tidyverse)
 library(GGally)
@@ -10,9 +10,9 @@ 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"))) %>%
+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") +
@@ -21,8 +21,8 @@ data %>%
 ```
 ```{r}
 data_wide <- pivot_wider(data, names_from = type, values_from = note)
-data_wide %>%
-  select(-id) %>%
+data_wide |>
+  select(-id) |>
   ggpairs() + theme_bw(14)
 ```
 ```{r}
@@ -67,12 +67,12 @@ 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() %>%
+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)) %>%
+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) +

M1/General Linear Models/TP2/TP2.rmd

@@ -1,5 +1,5 @@
 ```{r}
-setwd('/Users/arthurdanjou/Workspace/studies/M1/General Linear Models/TP2')
+setwd("/Users/arthurdanjou/Workspace/studies/M1/General Linear Models/TP2")
 ```
 
 # Question 1 : Import dataset and check variables
@@ -9,8 +9,8 @@ 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))
+cepages <- cepages |> mutate(across(where(is.character), as.numeric))
+cepages <- cepages |> mutate(across(where(is.integer), as.numeric))
 paged_table(cepages)
 ```
 
@@ -39,7 +39,7 @@ tapply(cepages$pH, list(cepages$Couleur, cepages$Origine), mean)
 library(ggplot2)
 
 ggplot(cepages, aes(x = AcTot, y = pH, color = Couleur)) +
-  geom_point(col = 'red', size = 0.5) +
+  geom_point(col = "red", size = 0.5) +
   geom_smooth(method = "lm", se = F)
 
 ggplot(cepages, aes(y = pH, x = AcTot, colour = Couleur, fill = Couleur)) +
@@ -50,8 +50,8 @@ ggplot(cepages, aes(y = pH, x = AcTot, colour = Couleur, fill = Couleur)) +
 
 ```{r}
 ggplot(cepages, aes(x = AcTot, y = pH, color = Origine)) +
-  geom_smooth(method = 'lm', se = F) +
-  geom_point(col = 'red', size = 0.5)
+  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)

M1/General Linear Models/TP3/TP3.rmd

@@ -1,5 +1,5 @@
 ```{r}
-setwd('/Users/arthurdanjou/Workspace/studies/M1/General Linear Models/TP3')
+setwd("/Users/arthurdanjou/Workspace/studies/M1/General Linear Models/TP3")
 ```
 
 # Question 1 : Import dataset and check variables
@@ -9,8 +9,8 @@ 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))
+ozone <- ozone |> mutate(across(where(is.character), as.numeric))
+ozone <- ozone |> mutate(across(where(is.integer), as.numeric))
 paged_table(ozone)
 ```
 
@@ -25,8 +25,8 @@ summary(model_T12)
 library(ggplot2)
 
 ggplot(ozone, aes(x = T12, y = maxO3)) +
-  geom_smooth(method = 'lm', se = T) +
-  geom_point(col = 'red', size = 0.5) +
+  geom_smooth(method = "lm", se = T) +
+  geom_point(col = "red", size = 0.5) +
   labs(title = "maxO3 ~ T12") +
   theme_minimal()
 ```
@@ -130,5 +130,4 @@ new_obs <- list(
   maxO3v = 85
 )
 predict(model_backward, new_obs, interval = "confidence")
-
 ```

M1/General Linear Models/TP4/TP4.rmd

@@ -1,5 +1,5 @@
 ```{r}
-setwd('/Users/arthurdanjou/Workspace/studies/M1/General Linear Models/TP4')
+setwd("/Users/arthurdanjou/Workspace/studies/M1/General Linear Models/TP4")
 
 set.seed(0911)
 library(ggplot2)
@@ -22,19 +22,19 @@ library(lmtest) # LRtest
 library(survey) # Wald test
 library(vcdExtra) # deviance test
 
-library(rsample)   # for data splitting
+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(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
+ggplot2::theme_set(ggplot2::theme_light()) # Set the graphical theme
 ```
 ```{r}
-car <- read.table('car_income.txt', header = TRUE, sep = ';')
-car %>% rmarkdown::paged_table()
+car <- read.table("car_income.txt", header = TRUE, sep = ";")
+car |> rmarkdown::paged_table()
 summary(car)
 ```
 
@@ -44,7 +44,7 @@ summary(model_purchase)
 ```
 
 ```{r}
-p1 <- car %>%
+p1 <- car |>
   ggplot(aes(y = purchase, x = income + age)) +
   geom_point(alpha = .15) +
   geom_smooth(method = "lm") +
@@ -53,7 +53,7 @@ p1 <- car %>%
   ylab("Probability of Purchase")
 
 
-p2 <- car %>%
+p2 <- car |>
   ggplot(aes(y = purchase, x = income + age)) +
   geom_point(alpha = .15) +
   geom_smooth(method = "glm", method.args = list(family = "binomial")) +
@@ -66,9 +66,9 @@ ggplotly(p2)
 ```
 
 ```{r}
-car <- car %>%
+car <- car |>
   mutate(old = ifelse(car$age > 3, 1, 0))
-car <- car %>%
+car <- car |>
   mutate(rich = ifelse(car$income > 40, 1, 0))
 model_old <- glm(purchase ~ age + income + rich + old, data = car, family = "binomial")
 summary(model_old)
@@ -90,5 +90,5 @@ 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')
+confusionMatrix(data = pima.te$type, reference = pima.te$pred, positive = "Yes")
 ```