Linear_Regression_sri, R

Language: Layout:

# Simple Linear Regression

YearsExperience <- c(1.1, 1.3, 1.5, 2, 2.2, 2.9, 3, 3.2, 3.2, 3.7, 3.9, 4, 4, 4.1, 4.5, 4.9, 5.1, 5.3, 5.9, 6, 6.8, 7.1, 7.9, 8.2, 8.7, 9, 9.5, 9.6, 10.3, 10.5)
Salary <- c(39343, 46205, 37731, 43525, 39891, 56642, 60150, 54445, 64445, 57189, 63218, 55794, 56957, 57081, 61111, 67938, 66029, 83088, 81363, 93940, 91738, 98273, 101302, 113812, 109431, 105582, 116969, 112635, 122391, 121872)
dataset <- data.frame(YearsExperience, Salary)

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

#adding missing data

# 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)

#print(training_set)
#print(test_set)

# Feature Scaling
# training_set = scale(training_set)
# test_set = scale(test_set)

# Fitting Simple Linear Regression to the Training set
regressor = lm(formula = Salary ~ YearsExperience,
               data = training_set)

#print(summary(regressor))

# Predicting the Test set results
y_pred = predict(regressor, newdata = test_set)
print(y_pred)

#newvalue = data.frame(YearsExperience=5)
#y_pred = predict(regressor, newvalue)
#print(y_pred)

# Visualising the Training set results
#install.packages("ggplot2")
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')

# Visualising the Test set results
library(ggplot2)
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')

[ + ] Show input
Absolute running time: 1.46 sec, cpu time: 1.62 sec, memory peak: 48 Mb, absolute service time: 1,47 sec