# coding=utf-8
from array import array
import matplotlib.pyplot as plt
from numpy import *
from numpy.ma import arange, exp

# 导入数据
def loadDataSet():
    #数据集合
    dataMat = [];
    #标签集合
    labelMat = []

    fr = open('testData.txt')
    # fr = open('testData2.txt')
    #处理输入文件，写入集合
    for line in fr.readlines():
        lineArr = line.strip().split()
        # dataMat.append([1.0, float(lineArr[0]), float(lineArr[1]), float(lineArr[2])])
        dataMat.append([1.0, float(lineArr[0]), float(lineArr[1])])
        # labelMat.append(int(lineArr[3]))
        labelMat.append(int(lineArr[2]))
    return dataMat, labelMat

#用梯度下降法计算回归系数
def gradAscent(dataMatIn, classLabels):
    #转为科学计数法表示
    dataMatrix = mat(dataMatIn)  # convert to NumPy matrix
    labelMat = mat(classLabels).transpose()  # convert to NumPy matrix
    #矩阵维度，m：数据条数，n：单条数据维度
    m, n = shape(dataMatrix)
    #梯度下降变量α
    alpha = 0.0001
    #循环次数
    maxCycles = 500
    #回归系数(密度向量)
    weights = ones((n, 1))
    #遍历计算回归系数
    for k in range(maxCycles):
        #矩阵相称
        h = sigmoid(dataMatrix * weights)
        #向量差
        error = (labelMat - h)
        weights = weights + alpha * dataMatrix.transpose() * error
    return weights

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

def GetResult():
    dataMat, labelMat = loadDataSet()
    weights = gradAscent(dataMat, labelMat)
    print weights
    plotBestFit(weights)

def plotBestFit(weights):
    dataMat, labelMat = loadDataSet()
    dataArr = array(dataMat)
    n = shape(dataArr)[0]
    xcord1 = [];
    ycord1 = []
    xcord2 = [];
    ycord2 = []
    for i in range(n):
        if int(labelMat[i]) == 1:
            xcord1.append(dataArr[i, 1]);
            ycord1.append(dataArr[i, 2])
        else:
            xcord2.append(dataArr[i, 1]);
            ycord2.append(dataArr[i, 2])
    fig = plt.figure()
    ax = fig.add_subplot(111)
    ax.scatter(xcord1, ycord1, s=30, c='red', marker='s')
    ax.scatter(xcord2, ycord2, s=30, c='green')
    x = arange(-3.0, 3.0, 0.1)

    #    y=(0.48*x+4.12414)/(0.616)
    #     y = (-weights[0]-weights[1]*x)/weights[2]

    y = (-(float)(weights[0][0]) - (float)(weights[1][0]) * x) / (float)(weights[2][0])
    ax.plot(x, y)
    plt.xlabel('X1');
    plt.ylabel('X2');
    plt.show()


if __name__ == '__main__':
    GetResult()