a5_gradient_train.py

def train(X, y, model_parameters, learning_rate=0.1, iterations=100):
    # Make prediction for every data sample
    predictions = [predict(x, model_parameters) for x in X]

    # Calculate initial cost for model - MSE
    lowest_error = mse(predictions, y)
    
    for i in range(iterations):
        # Sum up partial gradients for every data sample, for every parameter in model
        accumulated_grad_w0 = 0
        accumulated_grad_b = 0   
        for x, y_target in zip(X, y):
            accumulated_grad_w0 += (predict(x, model_parameters) - y_target)*x[0]
            accumulated_grad_b += (predict(x, model_parameters) - y_target)
            
        # Calculate mean of gradient
        w_grad = (1.0/len(X)) * accumulated_grad_w0
        b_grad = (1.0/len(X)) * accumulated_grad_b
        
        # Update parameters by small part of averaged gradient
        model_parameters["w"][0] = model_parameters["w"] - learning_rate * w_grad
        model_parameters["b"] = model_parameters["b"] - learning_rate * b_grad