逻辑回归算法——处理简单数据
代码实现
（1）数据处理； （2）sigmoid函数； （3）梯度上升算法； （4）改进的随机梯度上升算法； （5）绘图
# -*- coding:UTF-8 -*-
import matplotlib.pyplot as plt
import numpy as np
import random
"""
函数说明:加载数据
Parameters:
无
Returns:
dataMat - 数据列表
labelMat - 标签列表
"""
def loadDataSet():
dataMat = [] # 创建数据列表
labelMat = [] # 创建标签列表
fr = open('testSet.txt') # 打开文件
for line in fr.readlines(): # 逐行读取
lineArr = line.strip().split() # 去回车，放入列表
dataMat.append([1.0, float(lineArr[0]), float(lineArr[1])]) # 添加数据
labelMat.append(int(lineArr[2])) # 添加标签
fr.close() # 关闭文件
return dataMat, labelMat # 返回
"""
函数说明:sigmoid函数
Parameters:
inX - 数据
Returns:
sigmoid函数
"""
def sigmoid(inX):
return 1.0 / (1 + np.exp(-inX))
"""
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)
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 = 0.001 #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，返回权重数组
"""
"""
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)
"""
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
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:绘制数据集
Parameters:
weights - 权重参数数组
"""
def plotBestFit(weights):
dataMat, labelMat = loadDataSet() # 加载数据集
dataArr = np.array(dataMat) # 转换成numpy的array数组
n = np.shape(dataMat)[0] # 数据个数
xcord1 = []
ycord1 = [] # 正样本
xcord2 = []
ycord2 = [] # 负样本
for i in range(n): # 根据数据集标签进行分类
if int(labelMat[i]) == 1:
xcord1.append(dataArr[i, 1])
ycord1.append(dataArr[i, 2]) # 1为正样本
else:
xcord2.append(dataArr[i, 1])
ycord2.append(dataArr[i, 2]) # 0为负样本
fig = plt.figure()
ax = fig.add_subplot(111) # 添加subplot
ax.scatter(xcord1, ycord1, s=20, c='red', marker='s', alpha=.5) # 绘制正样本
ax.scatter(xcord2, ycord2, s=20, c='green', alpha=.5) # 绘制负样本
x = np.arange(-3.0, 3.0, 0.1)
y = (-weights[0] - weights[1] * x) / weights[2]
ax.plot(x, y)
plt.title('BestFit') # 绘制title
plt.xlabel('X1')
plt.ylabel('X2') # 绘制label
plt.show()
if __name__ == '__main__':
dataMat, labelMat = loadDataSet()
#weights = gradAscent(dataMat, labelMat)
weights = stocGradAscent1(np.array(dataMat), labelMat)
plotBestFit(weights) 运行结果
数据集（x1,x2,label）
testSet.txt
-0.017612 14.053064 0
-1.395634 4.662541 1
-0.752157 6.538620 0
-1.322371 7.152853 0
0.423363 11.054677 0
0.406704 7.067335 1
0.667394 12.741452 0
-2.460150 6.866805 1
0.569411 9.548755 0
-0.026632 10.427743 0
0.850433 6.920334 1
1.347183 13.175500 0
1.176813 3.167020 1
-1.781871 9.097953 0
-0.566606 5.749003 1
0.931635 1.589505 1
-0.024205 6.151823 1
-0.036453 2.690988 1
-0.196949 0.444165 1
1.014459 5.754399 1
1.985298 3.230619 1
-1.693453 -0.557540 1
-0.576525 11.778922 0
-0.346811 -1.678730 1
-2.124484 2.672471 1
1.217916 9.597015 0
-0.733928 9.098687 0
-3.642001 -1.618087 1
0.315985 3.523953 1
1.416614 9.619232 0
-0.386323 3.989286 1
0.556921 8.294984 1
1.224863 11.587360 0
-1.347803 -2.406051 1
1.196604 4.951851 1
0.275221 9.543647 0
0.470575 9.332488 0
-1.889567 9.542662 0
-1.527893 12.150579 0
-1.185247 11.309318 0
-0.445678 3.297303 1
1.042222 6.105155 1
-0.618787 10.320986 0
1.152083 0.548467 1
0.828534 2.676045 1
-1.237728 10.549033 0
-0.683565 -2.166125 1
0.229456 5.921938 1
-0.959885 11.555336 0
0.492911 10.993324 0
0.184992 8.721488 0
-0.355715 10.325976 0
-0.397822 8.058397 0
0.824839 13.730343 0
1.507278 5.027866 1
0.099671 6.835839 1
-0.344008 10.717485 0
1.785928 7.718645 1
-0.918801 11.560217 0
-0.364009 4.747300 1
-0.841722 4.119083 1
0.490426 1.960539 1
-0.007194 9.075792 0
0.356107 12.447863 0
0.342578 12.281162 0
-0.810823 -1.466018 1
2.530777 6.476801 1
1.296683 11.607559 0
0.475487 12.040035 0
-0.783277 11.009725 0
0.074798 11.023650 0
-1.337472 0.468339 1
-0.102781 13.763651 0
-0.147324 2.874846 1
0.518389 9.887035 0
1.015399 7.571882 0
-1.658086 -0.027255 1
1.319944 2.171228 1
2.056216 5.019981 1
-0.851633 4.375691 1
-1.510047 6.061992 0
-1.076637 -3.181888 1
1.821096 10.283990 0
3.010150 8.401766 1
-1.099458 1.688274 1
-0.834872 -1.733869 1
-0.846637 3.849075 1
1.400102 12.628781 0
1.752842 5.468166 1
0.078557 0.059736 1
0.089392 -0.715300 1
1.825662 12.693808 0
0.197445 9.744638 0
0.126117 0.922311 1
-0.679797 1.220530 1
0.677983 2.556666 1
0.761349 10.693862 0
-2.168791 0.143632 1
1.388610 9.341997 0
0.317029 14.739025 0
查看4道真题和解析
