194 lines
5.2 KiB
Python
Executable File
194 lines
5.2 KiB
Python
Executable File
#!/usr/bin/env python3
|
||
# -*- coding:UTF-8 -*-
|
||
from sklearn.linear_model import LogisticRegression
|
||
import numpy as np
|
||
import random
|
||
|
||
"""
|
||
函数说明:sigmoid函数
|
||
|
||
Parameters:
|
||
inX - 数据
|
||
Returns:
|
||
sigmoid函数
|
||
Author:
|
||
Jack Cui
|
||
Blog:
|
||
http://blog.csdn.net/c406495762
|
||
Zhihu:
|
||
https://www.zhihu.com/people/Jack--Cui/
|
||
Modify:
|
||
2017-09-05
|
||
"""
|
||
def sigmoid(inX):
|
||
return 1.0 / (1 + np.exp(-inX))
|
||
|
||
"""
|
||
函数说明:改进的随机梯度上升算法
|
||
|
||
Parameters:
|
||
dataMatrix - 数据数组
|
||
classLabels - 数据标签
|
||
numIter - 迭代次数
|
||
Returns:
|
||
weights - 求得的回归系数数组(最优参数)
|
||
Author:
|
||
Jack Cui
|
||
Blog:
|
||
http://blog.csdn.net/c406495762
|
||
Zhihu:
|
||
https://www.zhihu.com/people/Jack--Cui/
|
||
Modify:
|
||
2017-09-05
|
||
"""
|
||
def stocGradAscent1(dataMatrix, classLabels, numIter=150):
|
||
m,n = np.shape(dataMatrix) #返回dataMatrix的大小。m为行数,n为列数。
|
||
weights = np.ones(n) #参数初始化 #存储每次更新的回归系数
|
||
for j in range(numIter):
|
||
dataIndex = list(range(m))
|
||
for i in range(m):
|
||
alpha = 4/(1.0+j+i)+0.01 #降低alpha的大小，每次减小1/(j+i)。
|
||
randIndex = int(random.uniform(0,len(dataIndex))) #随机选取样本
|
||
h = sigmoid(sum(dataMatrix[randIndex]*weights)) #选择随机选取的一个样本，计算h
|
||
error = classLabels[randIndex] - h #计算误差
|
||
weights = weights + alpha * error * dataMatrix[randIndex] #更新回归系数
|
||
del(dataIndex[randIndex]) #删除已经使用的样本
|
||
return weights #返回
|
||
|
||
|
||
"""
|
||
函数说明:梯度上升算法
|
||
|
||
Parameters:
|
||
dataMatIn - 数据集
|
||
classLabels - 数据标签
|
||
Returns:
|
||
weights.getA() - 求得的权重数组(最优参数)
|
||
Author:
|
||
Jack Cui
|
||
Blog:
|
||
http://blog.csdn.net/c406495762
|
||
Zhihu:
|
||
https://www.zhihu.com/people/Jack--Cui/
|
||
Modify:
|
||
2017-08-28
|
||
"""
|
||
def gradAscent(dataMatIn, classLabels):
|
||
dataMatrix = np.mat(dataMatIn) #转换成numpy的mat
|
||
labelMat = np.mat(classLabels).transpose() #转换成numpy的mat,并进行转置
|
||
m, n = np.shape(dataMatrix) #返回dataMatrix的大小。m为行数,n为列数。
|
||
alpha = 0.01 #移动步长,也就是学习速率,控制更新的幅度。
|
||
maxCycles = 500 #最大迭代次数
|
||
weights = np.ones((n,1))
|
||
for k in range(maxCycles):
|
||
h = sigmoid(dataMatrix * weights) #梯度上升矢量化公式
|
||
error = labelMat - h
|
||
weights = weights + alpha * dataMatrix.transpose() * error
|
||
return weights.getA() #将矩阵转换为数组，并返回
|
||
|
||
|
||
|
||
"""
|
||
函数说明:使用Python写的Logistic分类器做预测
|
||
|
||
Parameters:
|
||
无
|
||
Returns:
|
||
无
|
||
Author:
|
||
Jack Cui
|
||
Blog:
|
||
http://blog.csdn.net/c406495762
|
||
Zhihu:
|
||
https://www.zhihu.com/people/Jack--Cui/
|
||
Modify:
|
||
2017-09-05
|
||
"""
|
||
def colicTest():
|
||
frTrain = open('horseColicTraining.txt') #打开训练集
|
||
frTest = open('horseColicTest.txt') #打开测试集
|
||
trainingSet = []; trainingLabels = []
|
||
for line in frTrain.readlines():
|
||
currLine = line.strip().split('\t')
|
||
lineArr = []
|
||
for i in range(len(currLine)-1):
|
||
lineArr.append(float(currLine[i]))
|
||
trainingSet.append(lineArr)
|
||
trainingLabels.append(float(currLine[-1]))
|
||
trainWeights = stocGradAscent1(np.array(trainingSet), trainingLabels,500) #使用改进的随即上升梯度训练
|
||
errorCount = 0; numTestVec = 0.0
|
||
for line in frTest.readlines():
|
||
numTestVec += 1.0
|
||
currLine = line.strip().split('\t')
|
||
lineArr =[]
|
||
for i in range(len(currLine)-1):
|
||
lineArr.append(float(currLine[i]))
|
||
if int(classifyVector(np.array(lineArr), trainWeights))!= int(currLine[-1]):
|
||
errorCount += 1
|
||
errorRate = (float(errorCount)/numTestVec) * 100 #错误率计算
|
||
print("测试集错误率为: %.2f%%" % errorRate)
|
||
|
||
"""
|
||
函数说明:分类函数
|
||
|
||
Parameters:
|
||
inX - 特征向量
|
||
weights - 回归系数
|
||
Returns:
|
||
分类结果
|
||
Author:
|
||
Jack Cui
|
||
Blog:
|
||
http://blog.csdn.net/c406495762
|
||
Zhihu:
|
||
https://www.zhihu.com/people/Jack--Cui/
|
||
Modify:
|
||
2017-09-05
|
||
"""
|
||
def classifyVector(inX, weights):
|
||
prob = sigmoid(sum(inX*weights))
|
||
if prob > 0.5: return 1.0
|
||
else: return 0.0
|
||
|
||
"""
|
||
函数说明:使用Sklearn构建Logistic回归分类器
|
||
|
||
Parameters:
|
||
无
|
||
Returns:
|
||
无
|
||
Author:
|
||
Jack Cui
|
||
Blog:
|
||
http://blog.csdn.net/c406495762
|
||
Zhihu:
|
||
https://www.zhihu.com/people/Jack--Cui/
|
||
Modify:
|
||
2017-09-05
|
||
"""
|
||
def colicSklearn():
|
||
frTrain = open('horseColicTraining.txt') #打开训练集
|
||
frTest = open('horseColicTest.txt') #打开测试集
|
||
trainingSet = []; trainingLabels = []
|
||
testSet = []; testLabels = []
|
||
for line in frTrain.readlines():
|
||
currLine = line.strip().split('\t')
|
||
lineArr = []
|
||
for i in range(len(currLine)-1):
|
||
lineArr.append(float(currLine[i]))
|
||
trainingSet.append(lineArr)
|
||
trainingLabels.append(float(currLine[-1]))
|
||
for line in frTest.readlines():
|
||
currLine = line.strip().split('\t')
|
||
lineArr =[]
|
||
for i in range(len(currLine)-1):
|
||
lineArr.append(float(currLine[i]))
|
||
testSet.append(lineArr)
|
||
testLabels.append(float(currLine[-1]))
|
||
classifier = LogisticRegression(solver = 'sag',max_iter = 5000).fit(trainingSet, trainingLabels)
|
||
test_accurcy = classifier.score(testSet, testLabels) * 100
|
||
print('正确率:%f%%' % test_accurcy)
|
||
|
||
if __name__ == '__main__':
|
||
colicSklearn()
|