arthur/ArtStudies
1
0
Fork 0
mirror of https://github.com/ArthurDanjou/ArtStudies.git synced 2026-03-16 03:11:46 +01:00
Code Issues Packages Projects Releases Wiki Activity

Ajout de l'implémentation de Bagging et Boosting pour l'analyse des données de Boston, avec des visualisations et des évaluations de performance.

Browse Source
This commit is contained in:
Arthur Danjou
2026-02-16 11:29:46 +01:00
parent 14390f51e9
commit dc743105f3
2 changed files with 118 additions and 79 deletions
Download Patch File Download Diff File Expand all files Collapse all files

118
M2/Machine Learning 2/Bagging & Boosting.Rmd Normal file
View File

@@ -0,0 +1,118 @@
```{r}
library(randomForest)
library(MASS)
library(tree)
data(Boston)
```
## Sampling
```{r}
set.seed(123)
appr <- sample(seq_len(nrow(Boston)), nrow(Boston) / 2)
```
## Regression Tree
```{r}
arbre_boston <- tree(medv ~ ., Boston, subset = appr)
summary(arbre_boston)
plot(arbre_boston)
text(arbre_boston, pretty = 0)
```
```{r}
cv_boston <- cv.tree(arbre_boston)
plot(cv_boston$size, cv_boston$dev, type = "b")
```
```{r}
yprev <- predict(arbre_boston, newdata = Boston[-appr, ])
boston_test <- Boston[-appr, "medv"]
plot(yprev, boston_test)
abline(0, 1)
mean((yprev - boston_test)^2)
```
## Bagging
```{r}
set.seed(123)
bag_boston <- randomForest(
medv ~ .,
data = Boston,
subset = appr,
mtry = 13,
importance = TRUE
)
bag_boston
yprev_bag <- predict(bag_boston, newdata = Boston[-appr, ])
plot(yprev_bag, boston_test)
abline(0, 1)
mean((yprev_bag - boston_test)^2)
```
## Random Forest
```{r}
set.seed(123)
rf_boston <- randomForest(
medv ~ .,
data = Boston,
subset = appr,
mtry = 6,
importance = TRUE
)
yprev_rf <- predict(rf_boston, newdata = Boston[-appr, ])
mean((yprev_rf - boston_test)^2)
```
## Variable importance
```{r}
importance(rf_boston)
varImpPlot(rf_boston)
```
# Boosting
```{r}
library(gbm)
set.seed(1)
boost_boston <- gbm(
medv ~ .,
data = Boston[appr, ],
distribution = "gaussian",
n.trees = 5000,
interaction.depth = 4
)
summary(boost_boston)
par(mfrow = c(1, 2))
plot(boost_boston, i = "rm")
plot(boost_boston, i = "lstat")
```
```{r}
yhat_boost <- predict(boost_boston, newdata = Boston[-appr, ], n.trees = 5000)
mean((yhat_boost - boston_test)^2)
```
```{r}
boost_boston <- gbm(
medv ~ .,
data = Boston[appr, ],
distribution = "gaussian",
n.trees = 5000,
interaction.depth = 4,
shrinkage = 0.2,
verbose = FALSE
)
yhat_boost <- predict(boost_boston, newdata = Boston[-appr, ], n.trees = 5000)
mean((yhat_boost - boston_test)^2)
```

79
M2/Machine Learning 2/Random_forest.Rmd
View File

@@ -1,79 +0,0 @@
```{r}
library(randomForest)
library(MASS)
library(tree)
data(Boston)
```
## Sampling
```{r}
set.seed(123)
appr = sample(1:nrow(Boston), nrow(Boston) / 2)
```
## Regression Tree
```{r}
arbre.boston = tree(medv ~ ., Boston, subset = appr)
summary(arbre.boston)
plot(arbre.boston)
text(arbre.boston, pretty = 0)
```
```{r}
cv.boston = cv.tree(arbre.boston)
plot(cv.boston$size, cv.boston$dev, type = 'b')
```
```{r}
yprev = predict(arbre.boston, newdata = Boston[-appr, ])
boston.test = Boston[-appr, "medv"]
plot(yprev, boston.test)
abline(0, 1)
mean((yprev - boston.test)^2)
```
## Bagging
```{r}
set.seed(123)
bag.boston = randomForest(
medv ~ .,
data = Boston,
subset = appr,
mtry = 13,
importance = TRUE
)
bag.boston
yprev.bag = predict(bag.boston, newdata = Boston[-appr, ])
plot(yprev.bag, boston.test)
abline(0, 1)
mean((yprev.bag - boston.test)^2)
```
## Random Forest
```{r}
set.seed(123)
rf.boston = randomForest(
medv ~ .,
data = Boston,
subset = appr,
mtry = 6,
importance = TRUE
)
yprev.rf = predict(rf.boston, newdata = Boston[-appr, ])
mean((yprev.rf - boston.test)^2)
```
## Variable importance
```{r}
importance(rf.boston)
varImpPlot(rf.boston)
```