[R] Decision Tree.ipynb

Kernel: R

Decision Tree

Data preprocessing

# Importing the dataset
dataset = read.csv('Social_Network_Ads.csv')
dataset = dataset[3:5]

head(dataset, 10)

# Encoding the target feature as factor
dataset$Purchased = factor(dataset$Purchased, levels = c(0, 1))

# Splitting the dataset into the Training set and Test set
# install.packages('caTools')
library(caTools)
set.seed(123)
split = sample.split(dataset$Purchased, SplitRatio = 0.80)
training_set = subset(dataset, split == TRUE)
test_set = subset(dataset, split == FALSE)

head(training_set, 10)

head(test_set, 10)

# Feature Scaling*
training_set[-3] = scale(training_set[-3])
test_set[-3] = scale(test_set[-3])

head(training_set, 10)

head(test_set, 10)

Fitting Decision Tree classifier to the Training set

library(rpart)
classifier = rpart(formula = Purchased ~ .,
                        data = training_set)

Predicting the Test set results

y_pred = predict(classifier, newdata = test_set[-3], type = 'class')

head(y_pred, 10)

head(test_set[3], 10)

Making the Confusion Matrix

cm = table(test_set[, 3], y_pred)
cm

   y_pred
     0  1
  0 43  8
  1  6 23

---

classifier made 43 + 23 = 66 correct prediction and 6 + 8 = 14 incoreect predictions.

---

Visualising the Training set results

library(ElemStatLearn)
set = training_set
X1 = seq(min(set[, 1]) - 1, max(set[, 1]) + 1, by = 0.01)
X2 = seq(min(set[, 2]) - 1, max(set[, 2]) + 1, by = 0.01)
grid_set = expand.grid(X1, X2)
colnames(grid_set) = c('Age', 'EstimatedSalary')
y_grid = predict(classifier, newdata = grid_set, type = 'class')
plot(set[, -3],
     main = 'Decision Tree (Training set)',
     xlab = 'Age', ylab = 'Estimated Salary',
     xlim = range(X1), ylim = range(X2))
contour(X1, X2, matrix(as.numeric(y_grid), length(X1), length(X2)), add = TRUE)
points(grid_set, pch = '.', col = ifelse(y_grid == 1, 'springgreen3', 'tomato'))
points(set, pch = 21, bg = ifelse(set[, 3] == 1, 'green4', 'red3'), col='white')
legend("topright", legend = c("0", "1"), pch = 16, col = c('red3', 'green4'))

Visualising the Test set results

library(ElemStatLearn)
set = test_set
X1 = seq(min(set[, 1]) - 1, max(set[, 1]) + 1, by = 0.01)
X2 = seq(min(set[, 2]) - 1, max(set[, 2]) + 1, by = 0.01)
grid_set = expand.grid(X1, X2)
colnames(grid_set) = c('Age', 'EstimatedSalary')
y_grid = predict(classifier, newdata = grid_set, type = 'class')
plot(set[, -3], main = 'Decision Tree (Test set)',
     xlab = 'Age', ylab = 'Estimated Salary',
     xlim = range(X1), ylim = range(X2))
contour(X1, X2, matrix(as.numeric(y_grid), length(X1), length(X2)), add = TRUE)
points(grid_set, pch = '.', col = ifelse(y_grid == 1, 'springgreen3', 'tomato'))
points(set, pch = 21, bg = ifelse(set[, 3] == 1, 'green4', 'red3'), col='white')
legend("topright", legend = c("0", "1"), pch = 16, col = c('red3', 'green4'))

---

Things to remmember while making decison tree classifier:

• Normally it overfits the data. But here in R due to 'rpart' library (a very powerful and famous library), the overfitting is drastically reduced as compare to Decision Tree Model in python.

• There is no need to Scale the features as decision tree does not depends on Euclidean distance. We are using Feature Scaling here just to get a plot with better resolution. If you ammit scaling, then for example the above case the vector size will be about 200+ GB which is not possible to plot.

---

---

If we dont apply feature scaling (i.e. do not run cell 7 all through cell 9), then we can have a look at the decision tree. For this we just need to run 2 lines of code

---

Constructing decision tree

plot(classifier)
text(classifier)