LogisticRegression

import numpy as np
import random
def genData(numPoints,bias,variance):
    x = np.ones(shape=(numPoints,2)) #zeros(shape=(a,b)) == zeros((a,b))
    y = np.zeros((numPoints))
    for i in range(numPoints):
        x[i][1] = i
        y[i] = (i+bias)+random.uniform(0,1)*variance #构建以(i+bias)为主的矩阵，搞不懂为什么要加入variance，与矩阵y究竟什么关系
    return x,y
'''
x,y：矩阵
theta:一组向量和x相乘的值
alpha:梯度下降时的参数，即每一步下降多少
m:实例的个数
numIterations:迭代计算的次数，可以理解为梯度下降多少步
'''

def gradientDescent(x,y,theta,alpha,m,numIterations):
    xTrans = x.T
    for i in range(numIterations):
        hypothesis = np.dot(x,theta) #返回数值hypothesis，最终收敛值与初设theta无关
        loss = hypothesis - y
        cost = np.sum(loss**2)/(2*m)
        print ('Iteration %d | Cost:%f'%(i,cost))
        gradient = np.dot(xTrans,loss)/m
        theta = theta - alpha*gradient
    return theta
x,y = genData(100,25,10)
m,n =np.shape(x)
n_y = np.shape(y)
numIterations = 100000
alpha = 0.0005
theta = 100*np.ones(n)
theta = gradientDescent(x,y,theta,alpha,m,numIterations)
print (theta)

转载于:https://my.oschina.net/u/3786144/blog/1802929