def test_colic(self):
import numpy as np
frTrain = open('horseColicTraining.txt')
frTest = open('horseColicTest.txt')
trainingSet = []
trainingLabels = []
for line in frTrain.readlines():
currLine = line.strip().split('\t')
lineArr = []
for i in range(21):
lineArr.append(float(currLine[i]))
trainingSet.append(lineArr)
trainingLabels.append(float(currLine[21]))
trainWeights = logisticRegression.stocGradAscent1(
np.array(trainingSet), trainingLabels, 1000)
errorCount = 0
numTestVec = 0.0
for line in frTest.readlines():
numTestVec += 1.0
currLine = line.strip().split('\t')
lineArr = []
for i in range(21):
lineArr.append(float(currLine[i]))
if int(
logisticRegression.classifyVector(
np.array(lineArr), trainWeights)) != int(currLine[21]):
errorCount += 1
errorRate = (float(errorCount) / numTestVec)
print("the error rate of this test is: %f" % errorRate)
frTrain.close()
frTest.close()
return errorRate
def test_plotStoc1(self):
dataMat, labelMat = load()
wt = logisticRegression.stocGradAscent1(array(dataMat),
array(labelMat))
logisticRegression.plotBestFit(dataMat, labelMat, wt)
def test_logRegStoc1(self):
dataMat, labelMat = load()
wt = logisticRegression.stocGradAscent1(array(dataMat),
array(labelMat))
print(wt)