Exemples

03_Classification/classif.R

@@ -0,0 +1,135 @@
+# Initialisation ----
+library(tidyverse)
+
+# Données d'exemple
+data(iris)
+
+# Graphique de base
+iris %>%
+  ggplot() +
+  aes(x = Petal.Length, y = Sepal.Length, color = Species) +
+  geom_point()
+
+# Set de training
+set.seed(1000)
+iris %>%
+  sample_n(120) -> train
+
+# Set de test
+iris %>%
+  anti_join(train) -> test
+
+# Graphique de base
+train %>%
+  ggplot() +
+  aes(x = Petal.Length, y = Sepal.Length, color = Species) +
+  geom_point() -> g
+
+# kNN ----
+library(class)
+
+# Application du kNN sur les données de test
+knn(train = train %>% select(Petal.Length, Sepal.Length),
+    test  = test %>% select(Petal.Length, Sepal.Length),
+    cl    = train$Species,
+    k     = 10) -> test$Species_knn
+
+# Graphique avec les résultats
+g +
+  geom_point(data = test,
+             aes(x = Petal.Length, y = Sepal.Length, color = Species_knn),
+             size = 4) +
+  geom_point(data = test,
+             aes(x = Petal.Length, y = Sepal.Length, color = Species),
+             size = 2)
+
+# Résultats
+mean(test$Species == test$Species_knn)
+
+# Nouvelles données
+tibble(Petal.Length = rnorm(10, mean(iris$Petal.Length), var(iris$Petal.Length)),
+       Sepal.Length = rnorm(10, mean(iris$Sepal.Length), var(iris$Sepal.Length))) -> test2
+## Exemples particuliers
+# tibble(Petal.Length = rep(5, 10),
+#        Sepal.Length = seq(5, 7, length.out = 10)) %>%
+# bind_rows(test2) -> test2
+
+# Application du kNN sur nouvelles données
+knn(train = iris %>% select(Petal.Length, Sepal.Length),
+    test  = test2 %>% select(Petal.Length, Sepal.Length),
+    cl    = iris$Species,
+    k     = 5) -> test2$Species
+
+# Graphique avec les résultats
+g +
+  geom_point(data = test2,
+             aes(x = Petal.Length, y = Sepal.Length, color = Species),
+             size = 4)
+
+# Arbres décisionnels ----
+library(rpart)
+
+rpart(Species ~ Petal.Length + Sepal.Length, data = train) -> arbre
+arbre %T>%
+  plot(branch = .5, margin = .5) %>%
+  text(use.n = T, all = T, pretty = T, fancy = T)
+
+predict(arbre, test %>% select(Petal.Length, Sepal.Length), type = "class") -> test$Species_cart
+
+# Graphique avec les résultats
+g +
+  geom_point(data = test,
+             aes(x = Petal.Length, y = Sepal.Length, color = Species_cart),
+             size = 4) +
+  geom_point(data = test,
+             aes(x = Petal.Length, y = Sepal.Length, color = Species),
+             size = 2)
+
+# Résultats
+mean(test$Species == test$Species_cart)
+
+# Régression logistique ----
+# Données
+data(mtcars)
+
+# Graphique de base
+mtcars %>%
+  ggplot() +
+  aes(x = hp, y = mpg, color = am) +
+  geom_point() +
+  scale_color_gradient(low = "#FF0000", high = "#0000FF")
+
+# Sets de training et de test
+set.seed(1000)
+mtcars %>%
+  sample_n(24) -> train
+mtcars %>%
+  anti_join(train) -> test
+
+# Graphique training
+train %>%
+  ggplot() +
+  aes(x = hp, y = mpg, color = am) +
+  geom_point() +
+  scale_color_gradient(low = "#FF0000", high = "#0000FF") -> g
+
+# Modèle
+glm(am ~ hp + mpg, data = train, family = "binomial") -> logi
+
+logi %>% summary
+logi %>% plot
+
+# Prédiction
+predict(logi, test %>% select(hp, mpg), type = "response") -> test$am_logi
+
+# Graphique avec prédiction
+g +
+  geom_point(data = test,
+             aes(x = hp, y = mpg, color = am_logi),
+             size = 4) +
+  geom_point(data = test,
+             aes(x = hp, y = mpg, color = am),
+             size = 2)
+
+# Validation
+library(pROC)