机器学习实战——Logistic回归

书籍：《机器学习实战》中文版
IDE：PyCharm Edu 4.02

环境：Adaconda3  python3.6

关键词：sigmoid函数、批梯度上升法、随机梯度上升法

from numpy import *
import matplotlib.pyplot as plt
def loadDataSet():
    dataMat = []
    labelMat = []
    with open('testSet.txt') as fr:
        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
dataMat,labelMat = loadDataSet()
def sigmoid(inX):
    return 1.0/(1+exp(-inX))
# 批梯度上升算法（计算量大）
def gradAscent(dataMatIn,classLabels):
    #convert to NumPy matrix
    dataMatrix = mat(dataMatIn)                      # 100 by 3
    labelMat = mat(classLabels).transpose()          # 100 by 1
    m,n = shape(dataMatrix)
    alpha = 0.001
    maxCycles = 500    #迭代次数
    weights = ones((n,1))    #矩阵 3 by 1
    for k in range(maxCycles):
        h = sigmoid(dataMatrix*weights)         # 两个矩阵类型 *表示矩阵乘法
        error = labelMat-h
        weights = weights + alpha * dataMatrix.transpose() * error  #批梯度下降法公式
    return weights
weights1 = gradAscent(dataMat,labelMat)
#print(weights1)   # print(weights1.getA())
# 画出数据集和logistic回归最佳拟合直线
def plotBestFit(weights):
    dataArr = array(dataMat)   #二维时，array()与mat()函数效果相同
    n = shape(dataArr)[0]      #行数
    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)                         # 数组（60，）
    #根据sigmoid(z)函数，0是两个分类的分界处
    #z=w0x0+w1x1+w2x2  令z=0，x0=1解出x1与x2的关系
    y = (-weights[0]-weights[1]*x)/weights[2]         # 矩阵（1,60）
    #  原文 ax.plot(x,y)
    ax.plot(x,y.transpose())
    plt.xlabel('X1');plt.ylabel('X2')
    plt.show()
#原文 plotBestFit(weights1.getA())
#print(plotBestFit(weights1))
# 随机梯度上升算法
def stocGradAscent0(dataMatrix,classLabels):
    m,n = shape(dataMatrix)
    alpha = 0.01
    weights = ones(n)    # 数组
    for i in range(m):
        h = sigmoid(sum(dataMatrix[i]*weights))   # 元素相乘再求和即w0x0+w1x1+w2x2
        error = classLabels[i] - h
        weights = weights + alpha * error * dataMatrix[i]
    return weights
weights2 = stocGradAscent0(array(dataMat),labelMat)
# print(weights2)
# print(plotBestFit(weights2))
# 改进的随机梯度下降法
# alpha随着迭代次数不断减小
def stocGradAscent1(dataMatrix,classLabels,numIter=150):
    m,n = shape(dataMatrix)
    weights = ones(n)                  # 数组对象
    dataMatrix = array(dataMatrix)    #转换为numpy格式
    for j in range(numIter):
        # 原文 dataIndex = range(m)
        dataIndex = list(range(m))
        for i in range(m):
            # 随机选择一个样本进行权重的更新
            alpha = 4/(1.0+j+i)+0.001           #apha decreases with iteration, does not
            randIndex = int(random.uniform(0,len(dataIndex))) #go to 0 because of the constant
            h = sigmoid(sum(dataMatrix[randIndex]*weights))
            error = classLabels[randIndex] - h
            weights = weights + alpha * error * dataMatrix[randIndex]
            del(dataIndex[randIndex])
    return weights
weights3 = stocGradAscent1(dataMat,labelMat)
print(plotBestFit(weights3))

注解：

1、numpy：矩阵和数组的转换

np.mat(变量)函数 ：将对象转换为matrix

np.变量.getA()：将矩阵转换为数组

例子：批梯度下降法返回一个矩阵weight1s，而plotBestFit(weights)函数接收一个数组，

因此，调用命令为plotBestFit(weights1.getA())。

直接使用 plotBestFit(weights1)报错：x and y must have same first dimension, but have shapes (60,) and (1, 60)

解决方法：将原文的ax.plot(x,y) 改为ax.plot(x,y.transpose())

  

2、区分list、numpy的矩阵及数组

（1）

list对象中间有逗号[1,1,1,1,1]
print(ones(5))                       #数组
print(ones((5,1)))                 #矩阵
[ 1.  1.  1.  1.  1.]
[[ 1.]
 [ 1.]
 [ 1.]
 [ 1.]
 [ 1.]]

（2）

矩阵对象：* 表示矩阵乘法

ndarray对象： * 表示元素乘法；dot(A,B)表示矩阵乘法。

当然，二维的ndarray与matrix相同。

python列表：print([1,2,3]*2)  结果：[1,2,3,1,2,3]

若想从列表得到数乘结果，可以使用列表生成式！

（3）记住随机梯度上升法的推导公式

weights = weights + alpha * error * dataMatrix[randIndex]