机器学习实战之Logistics回归实现

from math import *
import numpy as np

#%%
"回归梯度上升优化算法"
def loadDataSet():   # 文件读取
    dataMat = []
    labelMat = []
    fr = open(r'C:\Users\xuning\PycharmProjects\machine learning\Logistics Regression\testSet.txt','r')
    for line in fr.readlines():
        lineArr = line.strip().split()
        dataMat.append([1.0, float(lineArr[0]), float(lineArr[1])])
        labelMat.append(int(lineArr[2]))
    return dataMat, labelMat
#%%
def sigmoid(inX):  # sigmoid函数
    return 1.0 / (1 + np.exp(-inX))

#%%
def gradAscent(dataMatIn, classLabels):  # 行：训练样本，列：不同特征；类别标签
    dataMatrix = np.mat(dataMatIn)  # 转换为矩阵
    labelsMat = np.mat(classLabels).transpose()  # 标签矩阵的转置
    m, n = np.shape(dataMatrix)  # dataMatrix的行和列
    alpha = 0.01  # 向目标移动的步长
    maxCycles = 500  # 变量迭代次数
    weights = np.ones((n, 1))  # 初始化回归系数
    for k in range(maxCycles):  # 开始迭代
        h = sigmoid(dataMatrix * weights)  # 预测值
        error = (labelsMat - h)  # 差值
        weights = weights + alpha * dataMatrix.transpose() * error  # 更新权重
    return weights  # 返回回归系数

#%%
dataArr, labelsMat = loadDataSet()
gradAscent(dataArr, labelsMat) 
matrix([[12.78439308],
        [ 1.11820761],
        [-1.7408268 ]])

"画出数据集和Logistics回归最佳拟合直线的函数"
def plotBestFit(wei):
    import matplotlib.pyplot as plt
    weights = wei.getA()  # 矩阵转换为数组
    dataMat, labelMat = loadDataSet()  # 特征矩阵和标签矩阵
    dataArr = np.array(dataMat)
    n = np.shape(dataArr)[0]
    xcord1 = []; ycord1 = []
    xcord2 = []; ycord2 = []
    for i in range(n):
        if int(labelMat[i]) == 1:  # 根据标签的不同求坐标
            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')
    ax.scatter(xcord2, ycord2, s=30, c='green')
    x = np.arange(-3.0, 3.0, 0.1)
    y = (-weights[0]-weights[1]*x)/weights[2]  # 最佳拟合直线
    ax.plot(x, y)
    plt.xlabel('X1'); plt.ylabel('X2')
    plt.show()

# %%
plotBestFit(weights)

# %%
plotBestFit(weights)

 def stocGradAscent0(dataMatrix, classLabels):  # 随机梯度下降法
    m, n = np.shape(dataMatrix)
    alpha = 0.01 
    weights = np.ones(n)
    for i in range(m):
        h = sigmoid(sum(dataMatrix[i]*weights))
        error = classLabels[i] - h
        weights = weights + alpha * error * dataMatrix[i]
    return weights
#%%
dataArr, labelsMat = loadDataSet()
#%%
weights = stocGradAscent0(np.array(dataArr), labelsMat)
#%%
plotBestFit(np.mat(weights).reshape(3, 1))

# %%
 def stocGradAscent0(dataMatrix, classLabels, numIter = 300):  # 改进的随机梯度下降法
    m, n = np.shape(dataMatrix)
    weights = np.ones(n)
    dataIndex = list(range(m))
    for j in range(numIter):  # 迭代次数
        for i in range(m):
            alpha = 0.01 + 4/(1.0+j+i) 
            randIndex = int(np.random.uniform(0, len(dataIndex)))  # 随机选取样本
            h = sigmoid(sum(dataMatrix[randIndex]*weights))
            error = classLabels[randIndex] - h
            weights = weights + alpha * error * dataMatrix[randIndex]
    return weights

dataArr, labelsMat = loadDataSet()
#%%
weights = stocGradAscent0(np.array(dataArr), labelsMat)
#%%
plotBestFit(np.mat(weights).reshape(3, 1))
# %% 

"Logistics回归分类函数"
def classifyVector(inX, weights):  
    prob = sigmoid(sum(inX*weights))
    if prob > 0.5:
        return 1.0
    else:
        return 0.0

# %%
def coliTest():  # 文件读取以及模型训练
    import os
    path = os.path.realpath(os.curdir)  # 获取当前目录的绝对路径
    path1 = os.path.join(path, "horseColicTraining.txt")  # 加上文件名
    path2 = os.path.join(path,"horseColicTest.txt")
    frTrain = open(path1)
    frTest = open(path2)
    trainingSet = []; trainingLabels = []
    for line in frTrain.readlines():
        currLine = line.strip().split('\t')
        lineArr = []
        for i in range(21):
            lineArr.append(float(currLine[i]))
        trainingSet.append(lineArr)
        trainingLabels.append(float(currLine[i]))
    trainWeights = stocGradAscent0(np.array(trainingSet), trainingLabels, 500)
    errorCount = 0; numTestVec = 0.0
    for line in frTest.readlines():
        numTestVec += 1.0
        currLine = line.strip().split('\t')
        lineArr = []
        for i in range(21):
            lineArr.append(float(currLine[i]))
        if int(classifyVector(np.array(lineArr), trainWeights)) != int(currLine[21]):
            errorCount += 1
    errorRate = (float(errorCount)/numTestVec)
    print("the error rate of this test is: %f" % errorRate)
    return errorRate
# %%
    def multiTest():  # 调用coliTest并运行10次
        numTests = 10; errorSum = 0.0
        for k in range(numTests):
            errorSum += coliTest()
        print("after %d iterations the average error rate is %f" % (numTests, errorSum /float(numTests)))
# %%
multiTest()

[43]multiTest()
multiTest()
the error rate of this test is: 0.298507
the error rate of this test is: 0.298507
the error rate of this test is: 0.298507
the error rate of this test is: 0.298507
the error rate of this test is: 0.298507
the error rate of this test is: 0.298507
the error rate of this test is: 0.298507
the error rate of this test is: 0.298507
the error rate of this test is: 0.298507
the error rate of this test is: 0.298507
after 10 iterations the average error rate is 0.298507