ML Using R SEction 9 Random Forest

# Import data set
dataset <-  read.csv("G:\\RStudio\\udemy\\ml\\Machine Learning AZ\\Part 2 - Regression\\Section 9 - Random Forest Regression\\Random_Forest_Regression\\Position_Salaries.csv")
# We want to use only columns 2 and 3
dataset <-  dataset[2:3]
head(dataset)

# Polynomial Regression
# taking care of missing values
# Test for missing values
sum(is.na(dataset$Level))

[1] 0

sum(is.na(dataset$Salary))

[1] 0

There is no missing values in the dataset. The while the next step should be to split the dataset, since this dataset is small, we will use the full dataset.

# feature scaling
# in this case for polynomial, not needed for feature scaling. 

# Fitting the  regression model
# add a new column in the dataframe
# install.package("randomforest")
library(randomForest)
set.seed(1234)
regressor <- randomForest(x = dataset[1], y = dataset$Salary, 
                          ntree = 10)
# predicting a new result 
y_pred <-  predict(regressor, data.frame(Level = 6.5))
y_pred

       1 
141733.3 

# Plot
library(ggplot2)

# visualizing regression using higher resolution
x_grid = seq(min(dataset$Level), max(dataset$Level), 0.1 )
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 (Regression Model)") +
  xlab("Levels") +
  ylab("Salary")

# Many more forest
regressor <- randomForest(x = dataset[1], y = dataset$Salary, 
                          ntree = 100)
x_grid = seq(min(dataset$Level), max(dataset$Level), 0.1 )
ggplot() +
  geom_point(aes(x = dataset$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 (Regression Model)") +
  xlab("Levels") +
  ylab("Salary")

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

       1 
160942.5 

# Many more forest at 500
regressor <- randomForest(x = dataset[1], y = dataset$Salary, 
                          ntree = 500)
x_grid = seq(min(dataset$Level), max(dataset$Level), 0.1 )
ggplot() +
  geom_point(aes(x = dataset$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 (Regression Model)") +
  xlab("Levels") +
  ylab("Salary")

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

       1 
162591.5