Simple Linear Regression Sample

###Python###

# Importing the libraries

import numpy as np

import matplotlib.pyplot as plt

import pandas as pd

# Importing the dataset

dataset = pd.read_csv('Salary_Data.csv')

X = dataset.iloc[:, :-1].values

y = dataset.iloc[:, 1].values

# Encoding categorical data

# Encoding the Independat Variable

## Method 1

from sklearn.compose import ColumnTransformer

from sklearn.preprocessing import OneHotEncoder

ct = ColumnTransformer(transformers=[('encoder', OneHotEncoder(), [3])], remainder='passthrough')

X = np.array(ct.fit_transform(X))

## Method 2

"""

from sklearn.preprocessing import LabelEncoder, OneHotEncoder

labelencoder_X = LabelEncoder()

x[:, 3] = labelencoder_X.fit_transform(x[:, 3])

onehotencoder = OneHotEncoder(categorical_features = [3])

X = onehotencoder.fit_transform(X).toarray()

"""

# Splitting the dataset into the Training set and Test set
from sklearn.model_selection import train_test_split

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 1/3, random_state = 0)

# Feature Scaling

"""

from sklearn.preprocessing import StandardScaler

sc_X = StandardScaler()

X_Train = sc_X.transform(X_train)

X_test = sc_X.transform(X_test)

"""

from sklearn.linear_model import LinearRegression

regressor = LinearRegression()

regressor.fit(X_train, y_train)

y_pred = regressor.predict(X_test)

plt.scatter(X_train, y_train, color = 'red')

plt.plot(X_train, regressor.predict(X_train), color = 'blue')

plt.title('Salary vs Experinece (Training set)')

plt.xlabel('Years of Experience')

plt.ylabel('Salary')

plt.show()

plt.scatter(X_test, y_test, color = 'green')

plt.plot(X_train, regressor.predict(X_train), color = 'blue')

plt.title('Salary vs Experinece (Test set)')

plt.xlabel('Years of Experience')

plt.ylabel('Salary')

plt.show()

###R    ######

# Importing the dataset

dataset = read.csv('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

# 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)

# Predicting the Test set results

y_pred = predict(regressor, newdata = test_set)

# Visualising 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')

# Visualising the Test set results

library(ggplot2)

ggplot() +

  geom_point(aes(x = test_set$YearsExperience, y = test_set$Salary),

             colour = 'green') +

  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')