import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
dataset = pd.read_csv('Salary_Data.csv')
X=dataset.iloc[:,-1:].values
y=dataset.iloc[:,1:].values
dataset.head()
YearsExperience Salary
0 1.1 39343.0
1 1.3 46205.0
2 1.5 37731.0
3 2.0 435250
4 2.2 39891.0
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)
from sklearn.linear_model import LinearRegression
regressor = LinearRegression()
regressor.fit(X_train, y_train)
Out[8]:
LinearRegression()
In [9]:
# Predicting the Test set results
y_pred = regressor.predict(X_ test)
plt.scatter(X_test, y_test, color = 'red’)
plt.plot(X_train, regressor.predict(X_train), color = 'blue’)
plt.title('Salary vs Experience (Test set)')
plt.xlabel( Years of Experience')
plt.ylabel( Salary")
plt.show()
.png)
