def colicTest():
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 = logRegres.stocGradAscent1(np.array(trainingSet),
trainingLabels, 500)
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(logRegres.classifyVector(np.array(lineArr),
trainWeights)) != int(currLine[21]):
errorCount += 1
errorRate = float(errorCount) / numTestVec
print 'the error rate of this test is: %f' % errorRate
return errorRate
def colicTest():
frTrain = open('horseColicTraining.txt')
frTest = open('horseColicTest.txt')
trainingSet = []
trainingLabels = []
# 训练回归模型
for line in frTrain.readlines():
currLine = line.strip().split('\t') #每行按\t分割
print('currLine:')
print(currLine) #每一行进行读取数据
lineArr = []
for i in range(21):
lineArr.append(float(currLine[i]))
print('lineArr:')
print(lineArr)
trainingSet.append(lineArr)
trainingLabels.append(float(currLine[21]))
trainWeights = logRegres.stocGradAscent1(array(trainingSet),
trainingLabels, 1000)
errorCount = 0
numTestVec = 0.0
#测试回归模型
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(logRegres.classifyVector(array(lineArr), trainWeights)) != int(
currLine[21]):
errorCount += 1
errorRate = (float(errorCount) / numTestVec)
print("the error rate of this test is: %f" % errorRate)
return errorRate
def colicTest():
trainingSet,trainingLabels = dln.loadDataSet('horseColicTraining.txt') #载入训练数据
trainWeights = lgr.stocGradAscent1(array(trainingSet), trainingLabels, 1000) #训练得到模型参数：改进的随机梯度上升算法
testSet,testLabels = dln.loadDataSet('horseColicTest.txt') #载入训练数据
errorCount = 0; numTestVec = 0.0
m,n = shape(testSet)
for i in range(m):
numTestVec += 1.0
if int(lgr.classifyVector(array(testSet[i]), trainWeights))!= int(testLabels[i]):
errorCount += 1
errorRate = (float(errorCount)/numTestVec)
print "the error rate of this test is: %f" % errorRate
return errorRate
def LRFeature(train_in, train_out, test_in):
n_train = np.shape(train_in)[0]
n_test = np.shape(test_in)[0]
# ---------对于LR的特殊处理
addones_train = np.ones((n_train, 1))
train_in = np.c_[addones_train, train_in] # 给训练集数据加1列1
addones_test = np.ones((n_test, 1))
test_in = np.c_[addones_test, test_in] # 给测试集加一列1
train_in, train_out = RandomOverSampler().fit_sample(train_in,
train_out) #过采样
trainWeights = LR.stocGradAscent1(train_in, train_out, 500) #梯度下降算法，训练500次
len_test = np.shape(test_in)[0] #测试集样本个数
test_predict = []
for i in range(len_test):
test_predict_tmp = LR.classifyVector(
test_in[i, :], trainWeights) #一个样本一个样本的算，样本中各特征乘以对应的权重
test_predict.append(test_predict_tmp)
test_predict = np.array(test_predict) #得到最终的预测结果
return test_predict
# for train,test in skf.split(dataMat,labelMat):
#==============================================================================
print("%s %s" % (train, test))
train_in = dataMat[train]
test_in = dataMat[test]
train_out = labelMat[train]
test_out = labelMat[test]
train_in, train_out = RandomOverSampler().fit_sample(train_in, train_out)
trainWeights = LR.stocGradAscent1(train_in, train_out, 500)
len_train = np.shape(train_in)[0]
len_test = np.shape(test_in)[0]
test_predict = []
proba_test = []
for i in range(len_test):
test_predict_tmp = LR.classifyVector(test_in[i, :], trainWeights)
test_predict.append(test_predict_tmp)
proba_test_tmp = LR.classifyProb(test_in[i, :], trainWeights)
proba_test.append(proba_test_tmp)
train_predict = []
proba_train = []
for i in range(len_train):
train_predict_tmp = LR.classifyVector(train_in[i, :], trainWeights)
train_predict.append(train_predict_tmp)
proba_train_tmp = LR.classifyProb(train_in[i, :], trainWeights)
proba_train.append(proba_train_tmp)
test1, test2 = ann.evaluatemodel(train_out, train_predict,
proba_train) #test model with trainset
evaluate_train.extend(test1)