# Predict how much tip will get per our clients age
# Using a simple linear regression model
dataset = read.csv('tip.csv')

library(caTools)
# choose random number for the see
set.seed(100)
# Split the dataset between test and train set
split = sample.split(dataset$Tip, SplitRatio = 2/3)
training_set = subset(dataset, split == TRUE)
test_set = subset(dataset, split == FALSE)

regressor = lm(formula = Tip ~ Age,
               data = training_set)

# I'll be using ggplot2 to visualize the data
# installing `ggplot2`
install.packages('ggplot2')
# load library
library(ggplot2)

# First we should generate a graph using our train set
# this will give us the slope for our train set which later we can compare it
# with our test set
ggplot() +
  geom_point(aes(x = training_set$Age,
                 y = training_set$Tip),
             colour = 'red') +
  geom_line(aes(x = training_set$Age,
                y = predict(regressor, newdata = training_set)),
            colour = 'blue') +
  ggtitle('Tip vs Client Age (Training set)') +
  xlab('Client Age') +
  ylab('Tip')

ggplot() +
  geom_point(aes(x = test_set$Age,
                 y = test_set$Tip),
             colour = 'green') +
  geom_line(aes(x = training_set$Age,
                y = predict(regressor, newdata = training_set)),
            colour = 'red') +
  ggtitle('Tip vs Client Age (Test Set)') +
  xlab('Client Age') +
  ylab('Tip')