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.
2026-01-14 15:54:13 +01:00 · 2025-11-06 09:26:58 +01:00
parent 8f5f2b417c
commit 03bf0a4db2
10 changed files with 764 additions and 588 deletions
--- a/Visualisation/Exemple
+++ b/Visualisation/Exemple
--- a/Visualisation/tp1/3-td_ggplot2
+++ b/Visualisation/tp1/3-td_ggplot2
@@ -297,7 +297,7 @@ On présente ci-dessous un aperçu des données.
 fold <- getwd()

 # Load data
-# load(paste0(fold, "/M2/Data Visualisation/tp1", "/data/datafreMPTL.RData")) # VSCode # nolint
+# load(paste0(fold, "/M2/Data Visualisation/tp1", "/data/datafreMPTL.RData")) # VSCode
 load(paste0(fold, "/data/datafreMPTL.RData")) # RStudio
 paged_table(dat, options = list(rows.print = 15))
 ```
@@ -505,7 +505,7 @@ df_plot <- dat |>
 p3 <- ggplot(df_plot, aes(x = DrivAge, y = freq)) +
  geom_point() +
  geom_smooth() +
-  labs(x = "Age du conducteur", y = "Frequence")  +
+  labs(x = "Age du conducteur", y = "Frequence") +
  theme_bw()
 p3
 ```
@@ -642,12 +642,16 @@ plot_pairwise_disc <- function(df, var1, var2) {

  df |>
    group_by(varx, vary) |>
-    summarize(exp = sum(Exposure),
-              nb_claims = sum(ClaimNb),
-              freq = sum(ClaimNb) / sum(Exposure), .groups = "drop") |>
+    summarize(
+      exp = sum(Exposure),
+      nb_claims = sum(ClaimNb),
+      freq = sum(ClaimNb) / sum(Exposure), .groups = "drop"
+    ) |>
    ggplot(aes(x = varx, y = freq, colour = vary, group = vary), alpha = 0.3) +
-    geom_point() + geom_line() + theme_bw() +
-    labs(x = var1,  y = "Frequence", colour = var2)
+    geom_point() +
+    geom_line() +
+    theme_bw() +
+    labs(x = var1, y = "Frequence", colour = var2)
 }
 ```

--- a/Visualisation/tp2/4-td_graphiques
+++ b/Visualisation/tp2/4-td_graphiques
@@ -23,8 +23,13 @@ editor_options:

 ```{r setup, include=FALSE}
 ## Global options
-knitr::opts_chunk$set(cache = FALSE, warning = FALSE, message = FALSE, fig.retina = 2)
-options(encoding = 'UTF-8')
+knitr::opts_chunk$set(
+  cache = FALSE,
+  warning = FALSE,
+  message = FALSE,
+  fig.retina = 2
+)
+options(encoding = "UTF-8")
 ```


@@ -33,11 +38,11 @@ options(encoding = 'UTF-8')
 library(lattice)
 library(grid)
 library(ggplot2)
-require(gridExtra)
+require(gridExtra) 
 library(locfit)
 library(scales)
 library(formattable)
-library(RColorBrewer)
+library(RColorBrewer) 
 library(plotly)
 library(dplyr)
 library(tidyr)
@@ -88,7 +93,7 @@ de vie par pays sur la période 1952-1990. Les observations ont lieu tous les 5
 Dans un premier temps, il faut installer le package et le charger. 

 ```{r}
-# install.packages("gapminder")
+# install.packages("gapminder") #nolint
 library(gapminder)
 ```

@@ -140,7 +145,7 @@ pouvez observer entre `gdpPercap` et `lifeExp`.
 :::

 ```{r}
-ggplot(data = gapminder, aes(x = gdpPercap, y = lifeExp)) +
+ggplot(data = gapminder, aes(x = gdpPercap, y = lifeExp)) + 
  geom_point()
 ```

@@ -158,7 +163,7 @@ visualisations permettant de comparer des distributions.

 ```{r}
 ggplot(data = gapminder, aes(x = lifeExp)) + 
-    geom_density()
+  geom_density()
 ```


@@ -171,16 +176,16 @@ Il faut au préalable récupérer un fond de carte (ici de l'année 2016). Nous
 les données `gapminder` de 2007.

 ```{r}
-library(giscoR)
+library(giscoR) 
 library(sf)

 world <- gisco_countries
 world <- subset(world, NAME_ENGL != "Antarctica") # Remove Antartica

 # Merge data
-world_df <- gapminder %>%
+world_df <- gapminder |>
  filter(year == "2007")
-world_df <- world %>%
+world_df <- world |>
  left_join(world_df, by = c("NAME_ENGL" = "country"))

 ggplot(world_df) +
@@ -231,7 +236,7 @@ accidents <- read_csv("data/accidentsVelo.csv",
                                       date = col_date(format = "%Y-%m-%d")))

 # few ajustements 
-accidents <- accidents %>%
+accidents <- accidents |>
  mutate(mois = factor(mois),
         jour = factor(jour),
         dep = factor(dep),
@@ -247,8 +252,8 @@ correct <- paste0("0", str_sub(correct, 1, 1), ":",
 accidents$hrmn[issue] <- correct

 # Extract hour
-accidents <- accidents %>%
-  mutate(hour = paste(date, hrmn, sep = " ")) %>%
+accidents <- accidents |>
+  mutate(hour = paste(date, hrmn, sep = " ")) |>
  mutate(hour = strptime(hour, "%Y-%m-%d %H:%M")$hour)

 # mapping table for french departments
@@ -327,8 +332,8 @@ library(mapview)
 library(sf)

 ## Remove NA
-df_map_dyn <- accidents %>%
-  filter(???) %>%
+df_map_dyn <- accidents |>
+  filter(???) |>
  na.omit()

 # Make map and print it
@@ -354,27 +359,27 @@ Voici un premier code à trou pour vous aider.

 ```{r, eval = F}
 # get french map - level nuts2
-fr <- gisco_get_nuts(resolution = "20", country = ???, nuts_level = ???) %>%
+fr <- gisco_get_nuts(resolution = "20", country = ???, nuts_level = ???) |>
  mutate(res = "20M")

 # Remove white-space to avoid errors.
 library(stringr)
-departements_francais <- departements_francais %>%
+departements_francais <- departements_francais |>
  mutate(dep_name = str_trim(dep_name))

-fr <- fr %>%
+fr <- fr |>
  mutate(NUTS_NAME = str_trim(NUTS_NAME))

 # Merge and remove departements outside metropolitan France
-fr_map <- fr %>%
-  left_join(???) %>%
+fr_map <- fr |>
+  left_join(???) |>
  filter(! dep %in% c("971", ???) )

 # count the number of accidents
 df_acc <-  ???

 # merge statistics with the map
-map_acc <- fr_map %>%
+map_acc <- fr_map |>
  left_join(df_acc, by = c("dep" =  "dep"))

 # map with all accidents
--- a/Models/Code_Lec3.Rmd
+++ b/Models/Code_Lec3.Rmd
@@ -194,11 +194,11 @@ linear.mod$results
 ```{r}
 Ytrain <- cookie.train$sugars
 dfc_train <- data.frame(ytrain = Ytrain, linear.mod = fitted(linear.mod))
-dfc_train %>% rmarkdown::paged_table()
+dfc_train |> rmarkdown::paged_table()
 ```

 ```{r}
-dfc_train %>%
+dfc_train |>
  ggplot(aes(x = ytrain, y = linear.mod)) +
  geom_point(size = 2, color = "#983399") +
  geom_smooth(method = "lm", color = "#389900") +
@@ -211,9 +211,9 @@ dfc_train %>%
 Ytest <- cookie.test$sugars
 dfc_test <- data.frame(ytest = Ytest)
 dfc_test$linear.mod <- predict(linear.mod, newdata = cookie.test)
-# dfc_test%>%rmarkdown::paged_table()
+# dfc_test|>rmarkdown::paged_table()

-dfc_test %>%
+dfc_test |>
  ggplot(aes(x = ytest, y = linear.mod)) +
  geom_point(size = 2, color = "#983399") +
  geom_smooth(method = "lm", color = "#389900") +
@@ -244,7 +244,7 @@ ggplotly(ggplot(Lasso))
 ```

 ```{r}
-Lasso$results %>% rmarkdown::paged_table()
+Lasso$results |> rmarkdown::paged_table()
 ```

 ```{r}
@@ -271,8 +271,8 @@ coef_lasso <- data.frame(
  Variable = rownames(as.matrix(coef(Lasso$finalModel, Lasso$bestTune$lambda))),
  Coefficient = as.matrix(coef(Lasso$finalModel, Lasso$bestTune$lambda))[, 1]
 )
-coef_lasso %>%
-  subset(Coefficient != 0) %>%
+coef_lasso |>
+  subset(Coefficient != 0) |>
  rmarkdown::paged_table()
 ```

@@ -298,7 +298,7 @@ ggplotly(ggplot(ridge))
 ```

 ```{r}
-ridge$results %>% rmarkdown::paged_table()
+ridge$results |> rmarkdown::paged_table()
 ```

 ```{r}
@@ -320,7 +320,7 @@ vip(ridge, num_features = 15)
 ```

 ```{r}
-data.frame(as.matrix(coef(ridge$finalModel, ridge$bestTune$lambda))) %>%
+data.frame(as.matrix(coef(ridge$finalModel, ridge$bestTune$lambda))) |>
  rmarkdown::paged_table()
 ```

@@ -346,7 +346,7 @@ ggplotly(ggplot(ElNet))
 ```

 ```{r}
-ElNet$results %>% rmarkdown::paged_table()
+ElNet$results |> rmarkdown::paged_table()
 ```

 ```{r}
@@ -372,8 +372,8 @@ coef_elnet <- data.frame(
  Variable = rownames(as.matrix(coef(ElNet$finalModel, ElNet$bestTune$lambda))),
  Coefficient = as.matrix(coef(ElNet$finalModel, ElNet$bestTune$lambda))[, 1]
 )
-coef_elnet %>%
-  subset(Coefficient != 0) %>%
+coef_elnet |>
+  subset(Coefficient != 0) |>
  rmarkdown::paged_table()
 ```

@@ -396,7 +396,7 @@ ggplotly(ggplot(pls_mod))
 ```

 ```{r}
-pls_mod$results %>% rmarkdown::paged_table()
+pls_mod$results |> rmarkdown::paged_table()
 ```

 ```{r}
@@ -412,7 +412,7 @@ vip(pls_mod, num_features = 20)
 ```

 ```{r}
-data.frame(Coefficients = as.matrix(coef(pls_mod$finalModel))) %>%
+data.frame(Coefficients = as.matrix(coef(pls_mod$finalModel))) |>
  rmarkdown::paged_table()
 ```

@@ -435,7 +435,7 @@ dTrain$ridge <- fitted(ridge)
 dTrain$ElNet <- fitted(ElNet)
 dTrain$pls <- fitted(pls_mod)
 melt.dTrain <- melt(dTrain, id = "yTrain", variable.name = "model")
-melt.dTrain %>% ggplot() +
+melt.dTrain |> ggplot() +
  aes(x = yTrain, y = value) +
  geom_smooth(method = "lm") +
  geom_point(size = 1, colour = "#983399") +
@@ -446,11 +446,11 @@ melt.dTrain %>% ggplot() +
 ```

 ```{r}
-dTrain %>% rmarkdown::paged_table()
+dTrain |> rmarkdown::paged_table()
 ```

 ```{r}
-melt.dTrain %>% rmarkdown::paged_table()
+melt.dTrain |> rmarkdown::paged_table()
 ```

 ### On the test set
@@ -463,10 +463,10 @@ dTest$Lasso <- predict(Lasso, newdata = cookie.test)
 dTest$ridge <- predict(ridge, newdata = cookie.test)
 dTest$ElNet <- predict(ElNet, newdata = cookie.test)
 dTest$pls <- predict(pls_mod, newdata = cookie.test)
-# dTest%>% rmarkdown::paged_table()
+# dTest|> rmarkdown::paged_table()
 melt.dTest <- melt(dTest, id = "yTest", variable.name = "model")
-# melt.dTest%>% rmarkdown::paged_table()
-melt.dTest %>% ggplot() +
+# melt.dTest|> rmarkdown::paged_table()
+melt.dTest |> ggplot() +
  aes(x = yTest, y = value) +
  geom_smooth(method = "lm") +
  geom_point(size = 1, colour = "#983399") +
@@ -491,8 +491,8 @@ RMSE <- rbind.data.frame(
 )
 names(RMSE) <- c("Train", "Test")
 row.names(RMSE) <- c("Linear", "Lasso", "Ridge", "ElNet", "PLS")
-RMSE %>%
-  kableExtra::kbl() %>%
+RMSE |>
+  kableExtra::kbl() |>
  kableExtra::kable_styling()
 ```