def svmCV(k, filetype, groups, cp, ke):
predictAcc = np.zeros(k)
for i in range(k):
print 'k:', k, 'run:', i
result = dv.createDataVoca(k, i, filetype)
data = result[0]
voca = result[1]
label = result[2]
subsetSize = len(label) / k
testLabel = label[i * subsetSize:(i + 1) * subsetSize]
trainLabel = np.append(label[:i * subsetSize],
label[(i + 1) * subsetSize:],
axis=0)
lenTestLab = len(testLabel)
lenTrainLab = len(trainLabel)
print 'len(testLabel):', lenTestLab
print 'len(trainLabel):', lenTrainLab
mask = np.logical_and((data[:, 0] > i * subsetSize),
(data[:, 0] <= (i + 1) * subsetSize))
tem = np.array([i * subsetSize, 0, 0])
testData = data[mask] - tem
tem1 = np.array([subsetSize, 0, 0])
maskhi = data[:, 0] > (i + 1) * subsetSize
trainDatahi = data[maskhi] - tem1
masklo = data[:, 0] <= i * subsetSize
trainDatalo = data[masklo]
trainData = np.append(trainDatahi, trainDatalo, axis=0)
# generate features for all the reviews
trainFeat = fvec.mulFeatGen(trainData, voca, lenTrainLab)
testFeat = fvec.mulFeatGen(testData, voca, lenTestLab)
clf = svm.SVC(C=cp, kernel=ke, cache_size=1000)
print "we are training our data:"
clf.fit(trainFeat, trainLabel)
print "we are testing our data:"
predictMul = clf.predict(testFeat)
print "we are calculating accuracy:"
predictAcc[i] = fvec.accPredict(testLabel, predictMul)
print "accuracy: " + str(predictAcc[i])
joblib.dump(
clf, '../modelSave/svmModelAll_K' + str(k) + '_Run' + str(i) +
'_' + filetype + '.pkl')
# averageAcc = np.mean(predictAcc)
return predictAcc
def svmCV(k, filetype, groups, cp, ke): predictAcc = np.zeros(k) for i in range(k): print 'k:',k,'run:',i result = dv.createDataVoca(k,i,filetype) data = result[0] voca = result[1] label = result[2] subsetSize = len(label)/k testLabel = label[i*subsetSize:(i+1)*subsetSize] trainLabel = np.append(label[:i*subsetSize],label[(i+1)*subsetSize:], axis=0) lenTestLab = len(testLabel) lenTrainLab = len(trainLabel) print 'len(testLabel):',lenTestLab print 'len(trainLabel):',lenTrainLab mask = np.logical_and((data[:,0]>i*subsetSize), (data[:,0]<=(i+1)*subsetSize)) tem = np.array([i*subsetSize,0,0]) testData = data[mask] - tem tem1 = np.array([subsetSize,0,0]) maskhi = data[:,0]>(i+1)*subsetSize trainDatahi = data[maskhi] - tem1 masklo = data[:,0]<=i*subsetSize trainDatalo = data[masklo] trainData = np.append(trainDatahi, trainDatalo, axis=0) # generate features for all the reviews trainFeat = fvec.mulFeatGen(trainData, voca, lenTrainLab) testFeat = fvec.mulFeatGen(testData, voca, lenTestLab) clf = svm.SVC(C=cp, kernel=ke, cache_size=1000) print "we are training our data:" clf.fit(trainFeat, trainLabel) print "we are testing our data:" predictMul = clf.predict(testFeat) print "we are calculating accuracy:" predictAcc[i] = fvec.accPredict(testLabel,predictMul) print "accuracy: "+str(predictAcc[i]) joblib.dump(clf, '../modelSave/svmModelAll_K'+str(k)+'_Run'+str(i)+'_'+filetype+'.pkl') # averageAcc = np.mean(predictAcc) return predictAcc
def navieBayesMulCV(k, filetype, groups):
predictAcc = np.zeros(k)
for i in range(k):
print 'k:', k, 'run:', i
result = dv.createDataVoca(k, i, filetype)
data = result[0]
voca = result[1]
label = result[2]
subsetSize = len(label) / k
testLabel = label[i * subsetSize:(i + 1) * subsetSize]
trainLabel = np.append(label[:i * subsetSize],
label[(i + 1) * subsetSize:],
axis=0)
print 'len(trainLabel):', len(trainLabel)
print 'len(testLabel):', len(testLabel)
mask = np.logical_and((data[:, 0] > i * subsetSize),
(data[:, 0] <= (i + 1) * subsetSize))
tem = np.array([i * subsetSize, 0, 0])
testData = data[mask] - tem
tem1 = np.array([subsetSize, 0, 0])
maskhi = data[:, 0] > (i + 1) * subsetSize
trainDatahi = data[maskhi] - tem1
masklo = data[:, 0] <= i * subsetSize
trainDatalo = data[masklo]
trainData = np.append(trainDatahi, trainDatalo, axis=0)
print "we are training our data:"
result = navieBayesMulTrain(groups, voca, trainData, trainLabel)
print "we are testing our data:"
predictMul = navieBayesMulTest(groups, voca, testData, testLabel,
result[0], result[1])
print "we are calculating accuracy:"
predictAcc[i] = fvec.accPredict(testLabel, predictMul)
# if i==0:
# print "we are calculating the confusion matrix:"
# kkmatMul = fvec.confMatrix(testLabel,predictMul)
# np.savetxt('mulConfMat_k_'+str(k)+'_run_'+str(i)+'_'+filetype+'.txt', kkmatMul, fmt='%4d')
# averageAcc = np.mean(predictAcc)
return predictAcc
def navieBayesMulCV(k, filetype, groups):
predictAcc = np.zeros(k)
for i in range(k):
print "k:", k, "run:", i
result = dv.createDataVoca(k, i, filetype)
data = result[0]
voca = result[1]
label = result[2]
subsetSize = len(label) / k
testLabel = label[i * subsetSize : (i + 1) * subsetSize]
trainLabel = np.append(label[: i * subsetSize], label[(i + 1) * subsetSize :], axis=0)
print "len(trainLabel):", len(trainLabel)
print "len(testLabel):", len(testLabel)
mask = np.logical_and((data[:, 0] > i * subsetSize), (data[:, 0] <= (i + 1) * subsetSize))
tem = np.array([i * subsetSize, 0, 0])
testData = data[mask] - tem
tem1 = np.array([subsetSize, 0, 0])
maskhi = data[:, 0] > (i + 1) * subsetSize
trainDatahi = data[maskhi] - tem1
masklo = data[:, 0] <= i * subsetSize
trainDatalo = data[masklo]
trainData = np.append(trainDatahi, trainDatalo, axis=0)
print "we are training our data:"
result = navieBayesMulTrain(groups, voca, trainData, trainLabel)
print "we are testing our data:"
predictMul = navieBayesMulTest(groups, voca, testData, testLabel, result[0], result[1])
print "we are calculating accuracy:"
predictAcc[i] = fvec.accPredict(testLabel, predictMul)
# if i==0:
# print "we are calculating the confusion matrix:"
# kkmatMul = fvec.confMatrix(testLabel,predictMul)
# np.savetxt('mulConfMat_k_'+str(k)+'_run_'+str(i)+'_'+filetype+'.txt', kkmatMul, fmt='%4d')
# averageAcc = np.mean(predictAcc)
return predictAcc
import numpy as np
import featureVector as fvec
predictMulFeatRemove = np.load("predictMulFeatRemove.npy")
testLabel = np.loadtxt("../data/test.label", delimiter=' ', dtype=int)
Acc = fvec.accPredict(testLabel,predictMulFeatRemove)
import numpy as np
import featureVector as fvec
import matplotlib.pyplot as pl
predictBer = np.load("predictBer.npy")
predictMul = np.load("predictMul.npy")
predictMulAlp = np.load("predictMulAlp.npy")
predictMulFeatRemove = np.load("predictMulFeatRemove.npy")
testLabel = np.loadtxt("../data/test.label", delimiter=' ', dtype=int)
berAcc = fvec.accPredict(testLabel,predictBer)
mulAcc = fvec.accPredict(testLabel,predictMul)
alpRan = predictMulAlp.shape[0]
mulAlpAcc = np.zeros(alpRan)
for index,item in enumerate(predictMulAlp):
mulAlpAcc[index] = fvec.accPredict(testLabel,item)
print "berAcc = " + str(berAcc) + "; mulAcc = " + str(mulAcc)
print "mulAlpAcc = " + str(mulAlpAcc)
# Confusion matrix
kkmatBer = fvec.confMatrix(testLabel,predictBer)
kkmatMul = fvec.confMatrix(testLabel,predictMul)
np.savetxt("berConfMat.txt", kkmatBer, fmt='%4d')
np.savetxt("mulConfMat.txt", kkmatMul, fmt='%4d')
