徒手寫代碼之《機器學習實戰》----邏輯迴歸算法(1)（從疝氣病症預測病馬的死亡率項目）

從疝氣病症預測病馬的死亡率

說明:

將 horseColicTraining.txt 和 horseColicTest.txt 放在當前目錄下。

import numpy as np
import matplotlib.pyplot as plt

定義 Sigmoid 函數

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

定義一般的梯度提升算法

def gradAscent(dataMatIn, classLabels):
    #轉換成numpy的mat矩陣
    dataMatrix = np.mat(dataMatIn)   
    #轉換成numpy的mat矩陣並且轉置
    labelMat = np.mat(classLabels).transpose() 
    m, n = np.shape(dataMatrix)
    alpha = 0.001
    #設置最大迭代次數爲500次
    maxCycles = 500
    #權重全部初始化爲1
    weights = np.ones((n, 1))
    for k in range(maxCycles): 
        """
        批量梯度上升法
        """
        h = sigmoid(dataMatrix*weights)     
        error = (labelMat - h)              
        weights = weights + alpha * dataMatrix.transpose()* error 
    return weights

定義隨機梯度上升算法

def stocGradAscent0(dataMatrix, classLabels):
    m, n = np.shape(dataMatrix)
    alpha = 0.01
    weights = np.ones(n)   
    for i in range(m):
        """
        隨機梯度上升法
        """
        h = sigmoid(sum(dataMatrix[i]*weights))
        error = classLabels[i] - h
        weights = weights + alpha * error * dataMatrix[i]
    return weights

定義改進的隨機梯度上升算法

def stocGradAscent1(dataMatrix, classLabels, numIter=150):
    m, n = np.shape(dataMatrix)
    #權重初始化
    weights = np.ones(n)   
    for j in range(numIter):
        dataIndex = list(range(m))
        for i in range(m):
            #隨着迭代次數增加，降低apha值
            alpha = 4/(1.0+j+i)+0.0001   
            #隨機取一個樣本
            randIndex = int(np.random.uniform(0, len(dataIndex)))
            h = sigmoid(sum(dataMatrix[randIndex]*weights))
            error = classLabels[randIndex] - h
            weights = weights + alpha * error * dataMatrix[randIndex]
            del(dataIndex[randIndex])
    return weights

從疝氣病症預測病馬的死亡率

def classifyVector(inX, weights):
    prob = sigmoid(sum(inX*weights))
    if prob > 0.5: 
        return 1.0
    else: 
        return 0.0

def colicTest
    #打開訓練集和測試集
    frTrain = open('./horseColicTraining.txt'); frTest = open('./horseColicTest.txt')
    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[21]))
    #計算迴歸係數的向量
    trainWeights = stocGradAscent1(np.array(trainingSet), trainingLabels, 1000)
    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():
    numTests = 10; errorSum = 0.0
    for k in range(numTests):
        errorSum += colicTest()
    print("after %d iterations the average error rate is: %f" % (numTests, errorSum/float(numTests)))

multiTest()

the error rate of this test is: 0.313433
the error rate of this test is: 0.358209
the error rate of this test is: 0.417910
the error rate of this test is: 0.417910
the error rate of this test is: 0.298507
the error rate of this test is: 0.253731
the error rate of this test is: 0.373134
the error rate of this test is: 0.343284
the error rate of this test is: 0.283582
the error rate of this test is: 0.328358
after 10 iterations the average error rate is: 0.338806