Simple Linear Regression.R

# Simple Linear Regression

# Importing the dataset
dataset = read.csv('Salary_Data.csv')

# Splitting the dataset into the Training set and Test set
library(caTools)
set.seed(123)
split = sample.split(dataset$Salary, SplitRatio = 2/3)
training_set = subset(dataset, split == TRUE)
test_set = subset(dataset, split == FALSE)

# Fitting Simple Linear Regression to the Training Set (Part 2)

regressor = lm(formula = Salary ~ YearsExperience,
                data=training_set)
summary(regressor)


# Predictiing the Test Set Results (Part 3)

y_pred = predict(regressor, newdata = test_set)
y_pred


# Visualization (Part 4)

library(ggplot2)

### Training Set
ggplot() +
  geom_point(aes(x = training_set$YearsExperience, y = training_set$Salary),
             color = 'green') +
  geom_line(aes(x = training_set$YearsExperience, y = predict(regressor, newdata = training_set)),
            color = 'darkred') +
  ggtitle('Salary vs Experience (Training Set)') +
  xlab('Years of Experience') +
  ylab('Salary')

# Visualising the Test set results

ggplot() +
  geom_point(aes(x = test_set$YearsExperience, y = test_set$Salary),
             color = 'maroon') +
  geom_line(aes(x = training_set$YearsExperience, y = predict(regressor, newdata = training_set)),
            color = 'navy') +
  ggtitle('Salary vs Experience (Test Set)') +
  xlab('Years of Experience') +
  ylab('Salary')