-
Notifications
You must be signed in to change notification settings - Fork 0
/
simple_ln_regression.py
48 lines (35 loc) · 1.08 KB
/
simple_ln_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
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.impute import SimpleImputer
from sklearn.model_selection import train_test_split
dataset = pd.read_csv('data/Salary_Data.csv')
print(dataset)
X = dataset.iloc[:,:-1].values
y = dataset.iloc[:,-1].values
print(X)
print(y)
X_train,X_test, y_train, y_test = train_test_split(X,y,test_size=0.2, random_state=1)
print(X_train)
from sklearn.linear_model import LinearRegression
regressor = LinearRegression()
regressor.fit(X_train, y_train)
print(regressor)
y_pred = regressor.predict(X_test)
print((y_pred))
print(X_test)
#Train
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 Experiece')
plt.ylabel('Salary')
plt.show()
#Test
plt.scatter(X_test,y_test,color='red')
# no need to change below line as the equation is same
plt.plot(X_train,regressor.predict(X_train), color='blue')
plt.title('Salary vs Experience (Test Set)')
plt.xlabel('Years of Experiece')
plt.ylabel('Salary')
plt.show()