机器学习-logistic回归训练数据集

类别：机器学习个人笔记
参考书籍：《统计学习》、《机器学习实战》、周志华大佬的西瓜书
相关数学公式推导见我上传的手写PDF
任务：
学习《机器学习实战》P78页及P79页程序清单5-1和5-2，完成以下问题：

1）导入数据集’testSet.txt’,用logistic回归训练数据集，并画出决策边界。

2）导入数据集’data.txt’,用logistic回归训练数据集，并画出决策边界。

# 导包
from numpy import *
import pandas as pd
import numpy as np
from math import exp
import matplotlib.pyplot as plt

def loadDataSet(fileName):
    dataMat = [];labelMat = []
    fr = open(fileName)
    for line in fr.readlines():
        lineArr = line.strip().split()
        dataMat.append([1.0, float(lineArr[0]),float(lineArr[1])])
        labelMat.append(int(lineArr[2]))
        #print(shape(dataMat),shape(labelMat))
    return dataMat, labelMat

def sigmoid(inX):
    return 1.0/(1+np.exp(-inX))        

def gradAscent(dataMatIn,classLabels):
    dataMatrix = mat(dataMatIn)
    labelMat = mat(classLabels).transpose()
    m,n = shape(dataMatrix)
    alpha = 0.001
    maxCycles = 500  # 最大迭代次数
    weights = ones((n,1))
    for k in range(maxCycles):
        h = sigmoid(dataMatrix * weights)
        error = (labelMat - h)
        weights = weights + alpha * dataMatrix.transpose() * error     
    return weights

def plotBestFit(weights,filename):
    dataMat,labelMat = loadDataSet(filename)
    dataArr = array(dataMat)
    n = shape(dataArr)[0]
    xcord1 = []; ycord1 = []