Decision Tree Regression


# Importing the dataset

dataset = read.csv('Position_Salaries.csv')
dataset = dataset[2:3]

# Fitting Decision Tree Regression to the dataset
# install.packages('rpart')

library(rpart)
regressor = rpart(formula = Salary ~ .,
                  data = dataset,
                  control = rpart.control(minsplit = 1))

# Predicting a new result with Decision Tree Regression

y_pred = predict(regressor, data.frame(Level = 6.5))

# Visualising the Decision Tree Regression results (higher resolution)
# install.packages('ggplot2')

library(ggplot2)
x_grid = seq(min(dataset$Level), max(dataset$Level), 0.01)
ggplot() +
  geom_point(aes(x = dataset$Level, y = dataset$Salary),
             colour = 'red') +
  geom_line(aes(x = x_grid, y = predict(regressor, newdata = data.frame(Level = x_grid))),
            colour = 'blue') +
  ggtitle('Truth or Bluff (Decision Tree Regression)') +
  xlab('Level') +
  ylab('Salary')


# Plotting the tree
plot(regressor)

text(regressor)


Comments

Post a Comment

Popular posts from this blog

Decision Tree Classification

Image
# Importing the dataset dataset = read.csv('Social_Network_Ads.csv') dataset = dataset[3:5] # 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 = 0.75) training_set = subset(dataset, split == TRUE) test_set = subset(dataset, split == FALSE) # Feature Scaling training_set[-3] = scale(training_set[-3]) test_set[-3] = scale(test_set[-3]) # Fitting Decision Tree Classification to the Training set # install.packages('rpart') library(rpart) classifier = rpart(formula = Purchased ~ .,                    data = training_set) # Predicting the Test set results y_pred = predict(classifier, newdata = test_set[-3], type = 'clas...
Read more

Random Forest Classification

Image
# Importing the dataset dataset = read.csv('Social_Network_Ads.csv') dataset = dataset[3:5] # 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$Purchased, SplitRatio = 0.75) training_set = subset(dataset, split == TRUE) test_set = subset(dataset, split == FALSE) # Feature Scaling training_set[-3] = scale(training_set[-3]) test_set[-3] = scale(test_set[-3]) # Fitting Random Forest Classification to the Training set # install.packages('randomForest') library(randomForest) set.seed(123) classifier = randomForest(x = training_set[-3],                           y = training_set$Purchased,     ...
Read more