机器学习实战之线性回归算法

#!/bin/python
#coding=utf-8
# 实现线性回归

import numpy as np
import random

#自动生成数据集，numPoints是行数
#x是测试数据集，2维的向量，y是label
def genData(numPoints,bias,variance):
    x = np.zeros(shape=(numPoints,2))
    y = np.zeros(shape=(numPoints))
    for i in range(0,numPoints):
        x[i][0]=1
        x[i][1]=i
        #uniform(0,1)生成0到1之间的随机数
        y[i]=(i+bias)+random.uniform(0,1)+variance
    return x,y

#梯度下降算法
def gradientDescent(x,y,theta,alpha,m,numIterations):
    #transpose(x)矩阵的转置
    xTran = np.transpose(x)
    for i in range(numIterations):
        hypothesis = np.dot(x,theta)
        loss = hypothesis - y
        #线性模型中的cost
        cost = np.sum(loss ** 2)/(2 * m)
        gradient = np.dot(xTran,loss) / m
        theta = theta - alpha * gradient
    print ("Iteration %d | cost :%f" %(i,cost))
    return theta

x,y = genData(100, 25, 10)
print "x:"
print x
print "y:"
print y

m, n = np.shape(x)
n_y = np.shape(y)

#print("m:"+str(m)+" n:"+str(n)+" n_y:"+str(n_y))

numIterations = 100000
alpha = 0.0005
theta = np.ones(n)
theta= gradientDescent(x, y, theta, alpha, m, numIterations)
print(theta)

#测试算法
X = [1, 1.3]
y = np.dot(X, np.transpose(theta))
y
print y