def processMethod3(userid, featureCondition=1, classificationCondition=1, offsetFeatureOn=False):
""" User-i Device-j hack in User-i Device-k Model: iphone6plus hack iphone5
Returns
-------
float : error rate
"""
# rawDataiPhone6Plus = loadUserData(userid, 1, datatype=1) # moment data
# rawDataiPhone5 = loadUserData(userid, 2, datatype=1) # moment data
# trainingData = splitMomentDataByFeature(rawDataiPhone5, featureCondition=featureCondition)
# trainingLabel = rawDataiPhone5[:, 4]
# testData = splitMomentDataByFeature(rawDataiPhone6Plus, featureCondition=featureCondition)
# testLabel = rawDataiPhone6Plus[:, 4]
iPhone6Plus = 1
iPhone5 = 2
trainingData, trainingLabel = splitMomentDataByFeatureAndLabel(userid, iPhone5, featureCondition, classificationCondition, offsetFeatureOn=offsetFeatureOn)
testData, testLabel = splitMomentDataByFeatureAndLabel(userid, iPhone6Plus, featureCondition, classificationCondition, offsetFeatureOn=offsetFeatureOn)
# use same test size with method1
trainingDataIP5, testDataIP5, trainingLabelIP5, testLabelIP5 = train_test_split(trainingData, trainingLabel, test_size=my_test_size, random_state=my_random_state)
trainingDataIP6, testDataIP6, trainingLabelIP6, testLabelIP6 = train_test_split( testData, testLabel, test_size=my_test_size, random_state=my_random_state)
return classify(trainingDataIP5, trainingLabelIP5, testDataIP6, testLabelIP6, kernel=my_kernel, max_iter=my_max_iteration)
def processMethod4(userid, device, featureCondition=1, classificationCondition=1, offsetFeatureOn=False):
""" User-i Device-j hack in User-k Device-j Model
Returns
-------
float : error rate
"""
trainingData, trainingLabel = splitMomentDataByFeatureAndLabel(userid, device, featureCondition, classificationCondition, offsetFeatureOn=offsetFeatureOn)
trainingData, testData, trainingLabel, testLabel = train_test_split(trainingData, trainingLabel, test_size=my_test_size, random_state=my_random_state) # use same test size with method1
clfModel = classifyModel(trainingData, trainingLabel, kernel=my_kernel, max_iter=my_max_iteration)
hackErrorRateTextList = []
hackErrorRateList = []
for testUser in xrange(1, 17):
if testUser != userid :
testData, testLabel = splitMomentDataByFeatureAndLabel(testUser, device, featureCondition, classificationCondition, offsetFeatureOn=offsetFeatureOn)
trainingData, testData, trainingLabel, testLabel = train_test_split(testData, testLabel, test_size=my_test_size, random_state=my_random_state) # use same test size with method1
error_rate = testingWithModel(testData, testLabel, clfModel)
line = 'user ' + str(testUser) + ' hack ' + str(userid) + ', error rate: ' + str(error_rate) + '\n'
hackErrorRateList.append(error_rate)
hackErrorRateTextList.append(line)
return hackErrorRateTextList, hackErrorRateList
def identificationDataLabeling(userid, device, featureCondition, classificationCondition, offsetFeatureOn=False):
data = {}
label = {}
for user in xrange(1,17):
data[user], label[user] = splitMomentDataByFeatureAndLabel(user, device, featureCondition, classificationCondition, offsetFeatureOn=offsetFeatureOn)
if user == userid:
# current user label is 1
label[user] = [1 for value in label[user]]
else:
label[user] = [0 for value in label[user]]
for user in xrange(1,17):
if user != userid:
data[userid] = np.vstack((data[userid], data[user]))
label[userid] = np.hstack((label[userid], label[user]))
return data[userid], label[userid]
def processMethod1(userid, device, featureCondition=1, classificationCondition=1, offsetFeatureOn=False):
"""
User-i Device-j hack in User-i Device-j Model (cross validation)
i=1,2,...,16
j=1,2
Returns
-------
float : error rate
"""
data, label = splitMomentDataByFeatureAndLabel(userid, device, featureCondition, classificationCondition, offsetFeatureOn=offsetFeatureOn)
# rawData = loadUserData(userid, device, datatype)
# data = splitMomentDataByFeature(rawData, featureCondition=featureCondition)
# label = rawData[:, 4]
# if featureCondition==0:
# pass
trainingData, testData, trainingLabel, testLabel = train_test_split(data, label, test_size=my_test_size, random_state=my_random_state)
return classify(trainingData, trainingLabel, testData, testLabel, kernel=my_kernel, max_iter=my_max_iteration)
def identificationMoment(userid, device, featureCondition, classificationCondition, offsetFeatureOn=False):
data = {}
label = {}
for user in xrange(1,17):
data[user], label[user] = splitMomentDataByFeatureAndLabel(user, device, featureCondition, classificationCondition, offsetFeatureOn=offsetFeatureOn)
if user == userid:
label[user] = [1 for value in label[user]]
else:
label[user] = [0 for value in label[user]]
for user in xrange(1,17):
if user != userid:
data[userid] = np.vstack((data[userid], data[user]))
label[userid] = np.hstack((label[userid], label[user]))
trainingData, testData, trainingLabel, testLabel = train_test_split(data[userid], label[userid], test_size=my_test_size, random_state=my_random_state)
# print trainingData, trainingLabel
# plot3DLabel(trainingData, trainingLabel)
print 'preload finished.'
err = classify(trainingData, trainingLabel, testData, testLabel, kernel=my_kernel, max_iter=my_max_iteration)
print 'clssify finished.'
return err
import numpy
from sknn.mlp import Classifier, Layer
from sklearn.cross_validation import train_test_split
userid = 1
device = 1
featureCondition = 16
classificationCondition = 1
offsetFeatureOn = False
my_test_size = 0.3
my_random_state = 42
data, label = splitMomentDataByFeatureAndLabel(userid,
device,
featureCondition,
classificationCondition,
offsetFeatureOn=offsetFeatureOn)
data = data.astype(float)
label = label.astype(int)
trainingData, testData, trainingLabel, testLabel = train_test_split(
data, label, test_size=my_test_size, random_state=my_random_state)
nn = Classifier(
layers=[Layer("Softmax", units=100, pieces=2),
Layer("Softmax")],
learning_rate=0.001,
n_iter=10000)
nn.fit(trainingData, trainingLabel)
def plotROC(userid, device, featureCondition, classificationCondition, offset=False, noisyOn=True, noisyNum=11):
# userid = 1
# device = 1
# featureCondition = 10
# classificationCondition = 3
# offset = False
# noisyOn = True
#np.set_printoptions(threshold='nan')
# fileName = '../result/img/roc/clf'+str(classificationCondition)+'/featureCondition' + str(featureCondition) + '/device' + str(device) + '/user' + str(userid) + '.png'
fileName = 'result.png'
if os.path.exists(fileName)==True:
print 'finish ' + fileName
return
# import data to play with
data, label = splitMomentDataByFeatureAndLabel(userid, device, featureCondition, classificationCondition, offsetFeatureOn=offset)
# binarize the output
classes = list()
if classificationCondition==1:
classes=['0','1']
elif classificationCondition==2:
classes=['2','3']
elif classificationCondition==3:
classes=['0','1','2','3']
else: # classificationCondition==4
classes=['0','1']
label = label_binarize(label, classes=classes)
n_classes = label.shape[1]
# add noisy feature to make problem harder
if noisyOn==True:
random_state = np.random.RandomState(my_random_state)
n_samples, n_features = data.shape
data = np.c_[data, random_state.randn(n_samples, noisyNum * n_features)]
#shuffle and split traning and test sets
trainingData, testData, trainingLabel, testLabel = train_test_split(data, label, test_size=0.5, random_state=my_random_state)
# learn to predict each class against the other
classifier = OneVsRestClassifier(svm.SVC(kernel=my_kernel, probability=True, random_state=my_random_state, max_iter=my_max_iteration))
label_score = classifier.fit(trainingData, trainingLabel).decision_function(testData)
print 'decision success.'
# Compute ROC curve and ROC area for each class
fpr = dict()
tpr = dict()
roc_auc = dict()
for i in range(n_classes):
fpr[i], tpr[i], _ =roc_curve(testLabel[:, i], label_score[:, i])
roc_auc[i] = auc(fpr[i], tpr[i])
# # Compute micro-average ROC curve and ROC area
# print testLabel
# print label_score
# fpr["micro"], tpr["micro"], _ = roc_curve(testLabel.ravel(), label_score.ravel())
# roc_auc["micro"] = auc(fpr["micro"], tpr["micro"])
# # Compute macro-average ROC curve and ROC area
# # First aggregate all false positive rates
# all_fpr = np.unique(np.concatenate([fpr[i] for i in range(n_classes)]))
# # Then interpolate all ROC curves at this points
# mean_tpr = np.zeros_like(all_fpr)
# for i in range(n_classes):
# mean_tpr += interp(all_fpr, fpr[i], tpr[i])
# # Finally average it and compute AUC
# mean_tpr /= n_classes
# fpr["macro"] = all_fpr
# tpr["macro"] = mean_tpr
# roc_auc["macro"] = auc(fpr["macro"], tpr["macro"])
# Plot all ROC curves
plt.figure()
# plt.plot(fpr["micro"], tpr["micro"],
# label='micro-average ROC curve (area = {0:0.2f})'
# ''.format(roc_auc["micro"]),
# linewidth=2)
# plt.plot(fpr["macro"], tpr["macro"],
# label='macro-average ROC curve (area = {0:0.2f})'
# ''.format(roc_auc["macro"]),
# linewidth=2)
for i in range(n_classes):
strLabel = 'ROC curve of class {0} (area = {1:0.2f})'''.format(i, roc_auc[i])
plt.plot(fpr[i], tpr[i], label=strLabel, lw=3)
plt.plot([0, 1], [0, 1], 'k--')
plt.xlim([0.0, 1.0])
plt.ylim([0.0, 1.0])
plt.xlabel('False Positive Rate')
plt.ylabel('True Positive Rate')
plt.title('Receiver operating characteristic')
plt.legend(loc="lower right")
# fileName = '../result/img/roc/clf'+str(classificationCondition)+'/featureCondition' + str(featureCondition) + '/device' + str(device) + '/user' + str(userid) + '.png'
plt.savefig(fileName, dpi=72)
print 'finish ' + fileName
plt.close('all')
from loaddata import loadUserData
from loaddata import splitMomentDataByFeature
from loaddata import splitMomentDataByLabel
from loaddata import splitMomentDataByFeatureAndLabel
userid=1
device=1
featureCondition=3
classificationCondition=1
offsetFeatureOn=True
batch_size = 45
my_test_size = 0.3
my_random_state = 42
data, label = splitMomentDataByFeatureAndLabel(userid, device, featureCondition, classificationCondition, offsetFeatureOn=offsetFeatureOn)
trainingData, testData, trainingLabel, testLabel = train_test_split(data, label, test_size=my_test_size, random_state=my_random_state)
def plot3DLabel(data, label, trainLabel):
print data.shape
print label
fig = plt.figure()
ax = fig.add_subplot(211, projection='3d')
x = [float(value)/736 for value in data[:,0]]
y = [float(value)/414 for value in data[:,1]]
z = [float(value) for value in data[:,2]]
label = [1 if value=='1' else 0 for value in label]
ax.scatter(x,y,z,c=label, marker='o')
ax.set_xlabel('X')
ax.set_ylabel('Y')
