Python机器学习笔记5（偏差和方差）

本章代码涵盖了基于Python的解决方案，用于Coursera机器学习课程的第五个编程练习。

import numpy as np
import scipy.io as sio
import scipy.optimize as opt
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns

def load_data():
    """for ex5
    d['X'] shape = (12, 1)
    pandas has trouble taking this 2d ndarray to construct a dataframe, so I ravel
    the results
    """
    d = sio.loadmat('ex5data1.mat')
    return map(np.ravel, [d['X'], d['y'], d['Xval'], d['yval'], d['Xtest'], d['ytest']])

X, y, Xval, yval, Xtest, ytest = load_data()

df = pd.DataFrame({
   'water_level':X, 'flow':y})

sns.lmplot('water_level', 'flow', data=df, fit_reg=False, size=7)
plt.show()

X, Xval, Xtest = [np.insert(x.reshape(x.shape[0], 1), 0, np.ones(x.shape[0]), axis=1) for x in (X, Xval, Xtest)]

代价函数

def cost(theta, X, y):
    """
    X: R(m*n), m records, n features
    y: R(m)
    theta : R(n), linear regression parameters
    """
    m = X.shape[0]

    inner = X @ theta - y  # R(m*1)

    # 1*m @ m*1 = 1*1 in matrix multiplication
    # but you know numpy didn't do transpose in 1d array, so here is just a
    # vector inner product to itselves
    square_sum = inner.T @ inner
    cost = square_sum / (2 * m)

    return cost

theta = np.ones(X.shape[1])
cost(theta, X, y)

303.95152555359761

梯度

def gradient(theta, X, y):
    m = X.shape[0]

    inner = X.T @ (X @ theta - y)  # (m,n).T @ (m, 1) -> (n, 1)

    return inner / m

gradient(theta, X, y)

array([ -15.30301567,  598.16741084])

正则化梯度

def regularized_gradient(theta, X, y, l=1):
    m =