# Simple Linear Regression

rm(list = ls())

# Data Preprocessing Template

# Importing the dataset
dataset <- read.csv(file.path(getwd(),'Data/Salary_Data.csv'))

# Splitting the dataset into the Training set and Test set
# install.packages('caTools')
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)

# Feature Scaling
# No need to feature scale in Regression
# training_set = scale(training_set)
# test_set = scale(test_set)

# Fittin Linear Regresion to the Training set
regressor <- lm(formula = Salary ~ YearsExperience,
                data = training_set)

# Predicting the Test set results
y_pred <- predict(regressor, newdata = test_set) # we did not use this line!

# Visualizing the Training set results
ggplot() +
  geom_point(aes(x = training_set$YearsExperience, y = training_set$Salary),
             colour = "red") +
  geom_line(aes(x = training_set$YearsExperience,
                y = predict(regressor, newdata = training_set)), colour = "blue") +
  ggtitle("Salary vs Experience (Training Set)") +
  xlab("Years of Experience") +
  ylab("Salary") +
  theme_bw() +
  theme(plot.title = element_text(hjust = 0.5))
# the last line is used to center the title
# if we change 0.5 to 0 or 1, then we go left or right of the plot
# theme_bw() to change the theme of the plot


# Visualizing the Test set results

ggplot() +
  geom_point(aes(x = test_set$YearsExperience, y = test_set$Salary),
             colour = "red") +
  geom_line(aes(x = training_set$YearsExperience,
                y = predict(regressor, newdata = training_set)), colour = "blue") +
  ggtitle("Salary vs Experience (Test Set)") +
  xlab("Years of Experience") +
  ylab("Salary") +
  theme_bw() +
  theme(plot.title = element_text(hjust = 0.5))