CODE IN PYTHON:

Gradient Descent This function will perform gradient descent on the MSE. At the current parameter (Bo, B1, ..., Bm), the gradient is defined by the vector of partial derivatives: = n MSE(B0, B1,...,Bm) abo MSE(B0,31,...,8m) ab1 L=(Bo + B1 211 + ... + Bm l'im yi) Dh=1(B + B1 til + ... + Bm@im Yi)Xi1 This function returns the corresponding gradient as a 1-D numpy array with the partial derivative with respect to Bo as the first value. >>> gradient_descent(dataset, cols=[2,3], betas=[0,0,0]) => array([ -37.87698413, -1756.37222222, -7055.35138889]) # order: (partial derivative of beta_0, beta_2, be ta_3]