logistic-03

logistic-03.py

## Logistic Regression 
import numpy as np

def sigmoid(x):
    return (1 / (1 + np.exp(-x)))

m = 90
alpha = 0.0001

theta_0 = np.zeros((m,1))
theta_1 = np.zeros((m,1))
theta_2 = np.zeros((m,1))
theta_3 = np.zeros((m,1))
theta_4 = np.zeros((m,1))


epochs = 0
cost_func = []
while(epochs < 10000):
    y = theta_0 + theta_1 * x_1 + theta_2 * x_2 + theta_3 * x_3 + theta_4 * x_4
    y = sigmoid(y)
    
    cost = (- np.dot(np.transpose(y_train),np.log(y)) - np.dot(np.transpose(1-y_train),np.log(1-y)))/m
    
    theta_0_grad = np.dot(np.ones((1,m)),y-y_train)/m
    theta_1_grad = np.dot(np.transpose(x_1),y-y_train)/m
    theta_2_grad = np.dot(np.transpose(x_2),y-y_train)/m
    theta_3_grad = np.dot(np.transpose(x_3),y-y_train)/m
    theta_4_grad = np.dot(np.transpose(x_4),y-y_train)/m
    
    theta_0 = theta_0 - alpha * theta_0_grad
    theta_1 = theta_1 - alpha * theta_1_grad
    theta_2 = theta_2 - alpha * theta_2_grad
    theta_3 = theta_3 - alpha * theta_3_grad
    theta_4 = theta_4 - alpha * theta_4_grad
    
    cost_func.append(cost)
    epochs += 1