在工程应用中,我们得到一组数据,两维的,如下所示:
-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
进行逻辑回归分类,
新建一个logRegresTest.py,如下所示:
# -*- coding: utf-8 -*-
import matplotlib.pyplot as plt
import numpy as np
import time
'''符号函数'''
def sigmoid(x):
return 1.0 / (1 + np.exp(-x))
'''
逻辑回归训练
'''
def train_logRegres(train_x, train_y, opts):
startTime = time.time()
numSamples, numFeatures = np.shape(train_x)
alpha = opts['alpha'] #步长
maxIter = opts['maxIter']#迭代次数
#权重
weights = np.ones((numFeatures, 1)) #初始化参数为1
for k in range(maxIter):
if opts['optimizeType'] == 'gradDescent': # 梯度下降算法
output = sigmoid(train_x * weights)
error = train_y - output
weights = weights + alpha * train_x.transpose() * error
elif opts['optimizeType'] == 'stocGradDescent': # 随机梯度下降
for i in range(numSamples):
output = sigmoid(train_x[i, :] * weights)
error = train_y[i, 0] - output
weights = weights + alpha * train_x[i, :].transpose() * error
elif opts['optimizeType'] == 'smoothStocGradDescent': # 平稳随机梯度下降
dataIndex = range(numSamples)
for i in range(numSamples):
alpha = 4.0 / (1.0 + k + i) + 0.01
randIndex = int(np.random.uniform(0, len(dataIndex)))
output = sigmoid(train_x[randIndex, :] * weights)
error = train_y[randIndex, 0] - output
weights = weights + alpha * train_x[randIndex, :].transpose() * error
del(dataIndex[randIndex]) # during one interation, delete the optimized sample
else:
raise NameError('Not support optimize method type!')
print 'Congratulations, training complete! Took %fs!' % (time.time() - startTime)
print(weights)
return weights
'''逻辑回归测试'''
def test_LogRegres(weights, test_x, test_y):
numSamples, numFeatures = np.shape(test_x)
matchCount = 0
for i in xrange(numSamples):
predict = sigmoid(test_x[i, :] * weights)[0, 0] > 0.5
if predict == bool(test_y[i, 0]):
matchCount += 1
accuracy = float(matchCount) / numSamples
return accuracy
'''显示'''
def showLogRegres(weights, train_x, train_y):
# notice: train_x and train_y is mat datatype
numSamples, numFeatures = np.shape(train_x)
if numFeatures != 3:
print "Sorry! I can not draw because the dimension of your data is not 2!"
return 1
# draw all samples
for i in xrange(numSamples):
if int(train_y[i, 0]) == 0:
plt.plot(train_x[i, 1], train_x[i, 2], 'or')
elif int(train_y[i, 0]) == 1:
plt.plot(train_x[i, 1], train_x[i, 2], 'ob')
# draw the classify line
min_x = min(train_x[:, 1])[0, 0]
max_x = max(train_x[:, 1])[0, 0]
weights = weights.getA() # convert mat to array
y_min_x = float(-weights[0] - weights[1] * min_x) / weights[2]
y_max_x = float(-weights[0] - weights[1] * max_x) / weights[2]
plt.plot([min_x, max_x], [y_min_x, y_max_x], '-g')
plt.xlabel('X1'); plt.ylabel('X2')
plt.show()
建立logRegresmain函数,如下:
# -*- coding: utf-8 -*- import numpy as np from LogRegresTest import * '''加载数据''' def loadFile(): train_x =[] train_y =[] fileIn = open('data/data.txt') for line in fileIn.readlines(): lineArr = line.strip().split() train_x.append([1.0, float(lineArr[0]), float(lineArr[1])])#y=w0+x1*w1+x2*w2,(3个维度) train_y.append(float(lineArr[2])) return np.mat(train_x), np.mat(train_y).transpose() '''逻辑回归测试''' def logRegresMain(): print "step 1: loading data..." train_x, train_y = loadFile() test_x = train_x; test_y = train_y print "step 2: training..." alpha = 0.01 maxIter = 200 #gradDescent ,stocGradDescent ,smoothStocGradDescent optimizeType = 'gradDescent'#调用的方法 opts = {'alpha': alpha, 'maxIter': maxIter, 'optimizeType': optimizeType} optimalWeights = train_logRegres(train_x, train_y, opts) ## step 3: testing print "step 3: testing..." accuracy = test_LogRegres(optimalWeights, test_x, test_y) ## step 4: show the result print "step 4: show the result..." print 'The classify accuracy is: %.3f%%' % (accuracy * 100) showLogRegres(optimalWeights, train_x, train_y) if __name__=='__main__': logRegresMain()本代码支持gradDescent ,stocGradDescent ,smoothStocGradDescent
这三种优化算法,在步长为0.01,迭代次数为200的情况下,stocGradDescent的分类效果最好。