逻辑回归（Logistic Regression）

import numpy as np
import random

def genData(numPoints,bias,variance):#实例 偏好 方差
    x = np.zeros(shape=(numPoints,2))#行列
    y = np.zeros(shape=(numPoints))#行
    for i in range(0,numPoints):#0->numPoints-1
        x[i][0]=1
        x[i][1]=i
        y[i]=(i+bias)+random.uniform(0,1)+variance
    return x,y

def gradientDescent(x,y,theta,alpha,m,numIterations):
    xTran = np.transpose(x)
    for i in range(numIterations):
        hypothesis = np.dot(x,theta)
        loss = hypothesis-y
        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 = 1000

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

相关度（皮尔森相关系数）衡量两个值线性相关强度的量

R平方值 反应因变量的全部变异能通过回归关系被自变量解释的比例

转载于:https://www.cnblogs.com/wlc297984368/p/7467620.html