# generateFile()
## step 1: load data
print "step 1: load data..."
train_x, train_y = loadData()
test_x = train_x; test_y = train_y
## step 2: training...
print "step 2: training..."
opts = {'alpha': 0.01, 'maxIter': 200, 'optimizeType': 'smoothStocGradDescent'}
optimalWeights = trainLogRegres(train_x, train_y, opts)
print 'optimalWeights=',optimalWeights
## step 3: testing
print "step 3: testing..."
accuracy = testLogRegres(optimalWeights, test_x, test_y)
# numSamples, numFeatures = shape(test_x)
# matchCount = 0
# for i in xrange(numSamples):
# predict = sigmoid(test_x[i, :] * optimalWeights)[0, 0] > 0.5
# if predict == bool(test_y[i, 0]):
# matchCount += 1
# accuracy = float(matchCount) / numSamples
print 'accuracy=',accuracy
## 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)
def loadData():
train_x = []
train_y = []
fileIn = open('./testSet.txt')
for line in fileIn.readlines():
lineArr = line.strip().split()
train_x.append([1.0, float(lineArr[0]), float(lineArr[1])])
train_y.append(float(lineArr[2]))
return np.mat(train_x), np.mat(train_y).transpose()
## step 1: load data
print "step 1: load data..."
train_x, train_y = loadData()
test_x = train_x
test_y = train_y
## step 2: training...
print "step 2: training..."
opts = {'alpha': 0.01, 'maxIter': 500, 'optimizeType': 'gradDescent'}
optimalWeights = logRegression.trainLogRegres(train_x, train_y, opts)
## step 3: testing
print "step 3: testing..."
accuracy = logRegression.testLogRegres(optimalWeights, test_x, test_y)
## step 4: show the result
print "step 4: show the result..."
print 'The classify accuracy is: %.3f%%' % (accuracy * 100)
logRegression.showLogRegres(optimalWeights, train_x, train_y)
return mat(train_x), mat(train_y).transpose()
if __name__ == '__main__':
## step 1: load data
print "step 1: load data..."
train_x, train_y = loadData()
test_x = train_x; test_y = train_y
## step 2: training...
print "step 2: training..."
opts = {'alpha': 0.01, 'maxIter': 20, 'optimizeType': 'smoothStocGradDescent'}
optimalWeights = trainLogRegres(train_x, train_y, opts)
print 'optimalWeights=',optimalWeights
## step 3: testing
print "step 3: testing..."
accuracy = testLogRegres(optimalWeights, test_x, test_y)
print 'accuracy=',accuracy
## 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)
'''
梯度下降法，迭代500次
达到精度95%
随机梯度下降法 迭代200次
达到精度97%