-
Notifications
You must be signed in to change notification settings - Fork 6
/
linear_regression.py
54 lines (44 loc) · 1.53 KB
/
linear_regression.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
# -*- coding: utf-8 -*-
"""
Created on Fri Jul 26 18:04:25 2019
@author: ajayc
"""
# Data Preprocessing Template
# 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
# 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.fit_transform(X_train)
X_test = sc_X.transform(X_test)
sc_y = StandardScaler()
y_train = sc_y.fit_transform(y_train)"""
# Fitting Simple Linear regression in Training Set
from sklearn.linear_model import LinearRegression
regressor = LinearRegression()
regressor.fit(X_train,y_train)
# Predicting salaries of test data
y_pred = regressor.predict(X_test)
# Visualising Training Set Results
plt.scatter(X_train, y_train, color="red")
plt.plot(X_train, regressor.predict(X_train), color = "blue")
plt.title("Salary vs Experience - Training Set")
plt.xlabel("Years of Experience")
plt.ylabel("Salary")
plt.show()
# Visualising Test Set Results
plt.scatter(X_test, y_test, color="red")
plt.plot(X_train, regressor.predict(X_train), color = "blue")
plt.title("Salary vs Experience - Training Set")
plt.xlabel("Years of Experience")
plt.ylabel("Salary")
plt.show()