Explain with a case study of implementing simple linear regression using R.
# Simple Linear Regression
First we will import the dataset
dataset = read.csv('Salary_Data.csv')
Now we split the dataset into the Training set and Test set
# install.packages('caTools')
library(caTools)
set.seed(123)
split = sample.split(dataset$Salary, SplitRatio = 2/3)
training_set = subset(dataset, split == TRUE)
test_set = subset(dataset, split == FALSE)
Now we will perform Feature Scaling
# training_set = scale(training_set)
# test_set = scale(test_set)
Finally we fit the Simple Linear Regression to the Training set
regressor = lm(formula = Salary ~ YearsExperience,
data = training_set)
Now we predict the Test set results
y_pred = predict(regressor, newdata = test_set)
Now we will Visualise the Training set results
library(ggplot2)
ggplot() +
geom_point(aes(x = training_set$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')
Now we Visualise the Test set results
library(ggplot2)
ggplot() +geom_point(aes(x = test_set$YearsExperience, y = test_set$Salary),colour='red')+geom_line(aes(xtraining_set$YearsExperience, y =predict(regressor, newdata = training_set)), colour = 'blue') + ggtitle('Salary vs Experience (Test set)') +xlab('Years of experience') + ylab('Salary')