108 lines
2.9 KiB
Python
108 lines
2.9 KiB
Python
|
#!/usr/bin/env python2
|
||
|
|
# -*- coding:utf-8 -*-
|
||
|
|
import numpy as np
|
||
|
|
import matplotlib.pyplot as plt
|
||
|
|
|
||
|
|
|
||
|
|
# 加载数据
|
||
|
|
def loadDataSet():
|
||
|
|
dataMat = []
|
||
|
|
labelMat = []
|
||
|
|
fr = open('testSet.txt')
|
||
|
|
for line in fr.readlines():
|
||
|
|
lineArr = line.strip().split()
|
||
|
|
dataMat.append([1.0, float(lineArr[0]), float(lineArr[1])])
|
||
|
|
labelMat.append(int(lineArr[2]))
|
||
|
|
fr.close()
|
||
|
|
|
||
|
|
return dataMat, labelMat
|
||
|
|
|
||
|
|
|
||
|
|
# sigmoid 激活函数
|
||
|
|
def sigmoid(intX):
|
||
|
|
return 1.0 / (1 + np.exp(-intX))
|
||
|
|
|
||
|
|
|
||
|
|
# 梯度上升算法
|
||
|
|
def gradAscent(dataMatIn, classLabels):
|
||
|
|
dataMatrix = np.mat(dataMatIn)
|
||
|
|
labelMat = np.mat(classLabels).transpose()
|
||
|
|
m, n = np.shape(dataMatrix)
|
||
|
|
alpha = 0.001
|
||
|
|
maxCycles = 500
|
||
|
|
weights = np.ones((n, 1))
|
||
|
|
for k in range(maxCycles):
|
||
|
|
h = sigmoid(dataMatrix * weights)
|
||
|
|
error = labelMat - h
|
||
|
|
weights = weights + alpha * dataMatrix.transpose() * error
|
||
|
|
|
||
|
|
return weights.getA()
|
||
|
|
|
||
|
|
|
||
|
|
def plotBeastFit(weights):
|
||
|
|
dataMat, labelMat = loadDataSet()
|
||
|
|
dataArr = np.array(dataMat)
|
||
|
|
n = np.shape(dataArr)[0]
|
||
|
|
xcord1 = []
|
||
|
|
xcord2 = []
|
||
|
|
ycode1 = []
|
||
|
|
ycode2 = []
|
||
|
|
for i in range(n):
|
||
|
|
if int(labelMat[i]) == 1:
|
||
|
|
xcord1.append(dataArr[i, 1])
|
||
|
|
ycode1.append(dataArr[i, 2])
|
||
|
|
else:
|
||
|
|
xcord2.append(dataArr[i, 1])
|
||
|
|
ycode2.append(dataArr[i, 2])
|
||
|
|
|
||
|
|
fig = plt.figure()
|
||
|
|
ax = fig.add_subplot(111)
|
||
|
|
ax.scatter(xcord1, ycode1, s=20, c='red', marker='s', alpha=0.5)
|
||
|
|
ax.scatter(xcord2, ycode2, s=20, c='green', alpha=0.5)
|
||
|
|
x = np.arange(-3.0, 3.0, 0.1)
|
||
|
|
y = (-weights[0] - weights[1] * x) / weights[2]
|
||
|
|
ax.plot(x, y)
|
||
|
|
plt.title('BestFit')
|
||
|
|
plt.xlabel('X1')
|
||
|
|
plt.ylabel('X2')
|
||
|
|
plt.show()
|
||
|
|
|
||
|
|
|
||
|
|
# 随机梯度上升算法
|
||
|
|
def stocGradAscent0(dataMatrix, classLabels):
|
||
|
|
m, n = np.shape(dataMatrix)
|
||
|
|
alpha = 0.01
|
||
|
|
weights = np.ones(n)
|
||
|
|
for i in range(m):
|
||
|
|
h = sigmoid(sum(dataMatrix[i] * weights))
|
||
|
|
error = classLabels[i] - h
|
||
|
|
weights = weights + alpha * error * dataMatrix[i]
|
||
|
|
|
||
|
|
return weights
|
||
|
|
|
||
|
|
|
||
|
|
# 优化后的梯度上升算法
|
||
|
|
def stocGradAscent1(dataMatrix, classLabels, numIter=150):
|
||
|
|
m, n = np.shape(dataMatrix)
|
||
|
|
weights = np.ones(n)
|
||
|
|
for j in range(numIter):
|
||
|
|
dataIndex = range(m)
|
||
|
|
for i in range(m):
|
||
|
|
# alpha 每次都需要调整
|
||
|
|
alpha = 4 / (1.0 + j + i) + 0.01
|
||
|
|
# 随机选取跟新
|
||
|
|
rangeIndex = int(np.random.uniform(0, len(dataIndex)))
|
||
|
|
h = sigmoid(sum(dataMatrix[rangeIndex] * weights))
|
||
|
|
error = classLabels[rangeIndex] - h
|
||
|
|
weights = weights + alpha * error * dataMatrix[rangeIndex]
|
||
|
|
|
||
|
|
return weights
|
||
|
|
|
||
|
|
|
||
|
|
if __name__ == '__main__':
|
||
|
|
dataMat, labelMat = loadDataSet()
|
||
|
|
# weights = gradAscent(dataMat, labelMat)
|
||
|
|
# weights = stocGradAscent0(np.array(dataMat), labelMat)
|
||
|
|
weights = stocGradAscent1(np.array(dataMat), labelMat)
|
||
|
|
plotBeastFit(weights)
|