gradient descent for more than 1 independent variable

n_gradient_descent.py

import numpy as np

# Theta is the vector representing coefficients (intercept, area, bedrooms)
theta = np.matrix(np.array([0,0,0])) 
alpha = 0.01
iterations = 1000


# define cost function
# takes in theta (current values of coefficients b0, b1, b2), X and y
# returns total cost at current b0, b1, b2

def compute_cost(X, y, theta):
    return np.sum(np.square(np.matmul(X, theta) - y)) / (2 * len(y))


# gradient descent
# takes in current X, y, learning rate alpha, num_iters
# returns cost (notice it uses the cost function defined above)

def gradient_descent_multi(X, y, theta, alpha, iterations):
    theta = np.zeros(X.shape[1])
    m = len(X)
    gdm_df = pd.DataFrame( columns = ['Bets','cost'])

    for i in range(iterations):
        gradient = (1/m) * np.matmul(X.T, np.matmul(X, theta) - y)
        theta = theta - alpha * gradient
        cost = compute_cost(X, y, theta)
        gdm_df.loc[i] = [theta,cost]

    return gdm_df