LinearRegression/LinearRegression.py at master · YearInCode/LinearRegression · GitHub

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
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
from sklearn.datasets import make_regression
import matplotlib.pyplot as plt
import numpy as np

X, y= make_regression(n_samples=100, n_features=1, noise=0.4, bias=50)


def plotLine(theta0, theta1, X, y):
    max_x = np.max(X) + 100
    min_x = np.min(X) - 100


    xplot = np.linspace(min_x, max_x, 1000)
    yplot = theta0 + theta1 * xplot


    plt.plot(xplot, yplot, color='#58b970', label='Regression Line')

    plt.scatter(X,y)
    plt.axis([-10, 10, 0, 200])
    plt.show()


def hypothesis(theta0, theta1, x):
    return theta0 + (theta1*x)

def cost(theta0, theta1, X, y):
    costValue = 0
    for (xi, yi) in zip(X, y):
        costValue += 0.5 * ((hypothesis(theta0, theta1, xi) - yi)**2)
    return costValue


def derivatives(theta0, theta1, X, y):
    dtheta0 = 0
    dtheta1 = 0
    for (xi, yi) in zip(X, y):
        dtheta0 += hypothesis(theta0, theta1, xi) - yi
        dtheta1 += (hypothesis(theta0, theta1, xi) - yi)*xi

    dtheta0 /= len(X)
    dtheta1 /= len(X)

    return dtheta0, dtheta1

def updateParameters(theta0, theta1, X, y, alpha):
    dtheta0, dtheta1 = derivatives(theta0, theta1, X, y)
    theta0 = theta0 - (alpha * dtheta0)
    theta1 = theta1 - (alpha * dtheta1)

    return theta0, theta1


def LinearRegression(X, y):
    theta0 = np.random.rand()
    theta1 = np.random.rand()

    for i in range(0, 1000):
        if i % 100 == 0:
            plotLine(theta0, theta1, X, y)
        # print(cost(theta0, theta1, X, y))
        theta0, theta1 = updateParameters(theta0, theta1, X, y, 0.005)


LinearRegression(X, y)