How to Split a Dataset into Train and Test Sets in Machine Learning

Program 1

Machine Learning Dataset

import matplotlib.pyplot as plt
import pandas as pd
import numpy as np

df=pd.read_csv("D:\scikit_data\cardata\carprices.csv")
df.head(5)

df=df.rename(columns={'Age(yrs)':'Age'})
df=df.rename(columns={'Sell Price($)':'SellPrice'})

df.head(5)

plt.scatter(df['Mileage'],df['SellPrice'],color='red')

plt.scatter(df['Age'],df['SellPrice'],color='red')

from sklearn.model_selection import train_test_split

x=df[['Mileage','Age']]

y=df[['SellPrice']]
# x_train---> Training data set for Independed variable
# x_test---> Testing data set for Independed variable
# y_train---> Training data set for depended variable
# y_test---> Testing data set for depended variable

x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.3)

len(x_train)

len(y_train)

len(x_test)

len(y_test)

x_train

y_train

x_test

y_test

from sklearn import linear_model

model=linear_model.LinearRegression()
model.fit(x_train,y_train)

model.predict(x_test)

model.score(x_test,y_test)

# Predication by training dataset
y_pred=model.predict(x_train)

plt.scatter(y_train,y_pred,color='red')
plt.xlabel("Actual Price")
plt.ylabel("Predicated Price")
plt.show()

from sklearn.metrics import r2_score

print("R2 Score for Training data:",r2_score(y_train,y_pred))

# Predication by test dataset
y_pred=model.predict(x_test)
#print(y_pred)
plt.scatter(y_test,y_pred,color='blue',marker='+')
plt.xlabel("Actual Price")
plt.ylabel("Predicated Price")
plt.show()
print("R2 Score for Testing data:",r2_score(y_test,y_pred))