def getConfidenceScores(features_train, labels_train, C):
train_confidence = []
#confidence scores for training data are computed using K-fold cross validation
kfold = KFold(features_train.shape[0], n_folds=10)
for train_index,test_index in kfold:
X_train, X_test = features_train[train_index], features_train[test_index]
y_train, y_test = labels_train[train_index], labels_train[test_index]
#train classifier for the subset of train data
m = SVM.train(X_train,y_train,c=C,k="linear")
#predict confidence for test data and append it to list
conf = m.decision_function(X_test)
for x in conf:
train_confidence.append(x)
return np.array(train_confidence)
def getConfidenceScores(features_train, labels_train, C):
train_confidence = []
#confidence scores for training data are computed using K-fold cross validation
kfold = KFold(features_train.shape[0], n_folds=10)
for train_index,test_index in kfold:
X_train, X_test = features_train[train_index], features_train[test_index]
y_train, y_test = labels_train[train_index], labels_train[test_index]
#train classifier for the subset of train data
m = SVM.train(X_train,y_train,c=C,k="linear")
#predict confidence for test data and append it to list
conf = m.decision_function(X_test)
for x in conf:
train_confidence.append(x)
return np.array(train_confidence)
def main(args):
# Create algorithm objects
lbp = LBP()
detector = FaceDetector()
svm = SVM()
knn = KNearest()
# Get subjects to train the svm on
imgs = [
'/home/arthur/Downloads/lfw_funneled/Gian_Marco/Gian_Marco_0001.jpg',
'/home/arthur/Downloads/lfw_funneled/Micky_Ward/Micky_Ward_0001.jpg',
'/home/arthur/Downloads/lfw_funneled/Ziwang_Xu/Ziwang_Xu_0001.jpg',
'/home/arthur/Downloads/lfw_funneled/Zhu_Rongji/Zhu_Rongji_0001.jpg'
]
# Load the subjects and extract their features
hists, labels = load_subjects(imgs, detector, lbp)
# Transform to np arrays
samples = np.array(hists, dtype=np.float32)
labels = np.array(labels, dtype=np.int)
# Train classifiers
svm.train(samples, labels)
knn.train(samples, labels)
# Check which mode the app is running in (image vs. video)
if args.image is not None:
# Read the image from the file path provided
img = cv2.imread(args.image, 0)
# Check the image exists
if img is not None:
# Run face recognition algorithm
classify_snapshot(img, detector, lbp, knn)
else:
print('The image could not be found...')
return
# Establish connection to camera
cap = cv2.VideoCapture(0)
# Continuously grab the next frame from the camera
while cap.isOpened():
# Capture frame-by-frame
ret, frame = cap.read()
# Start timer for performance logging
start = time.time()
# Convert frame to gray scale for face detector
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
# Detect a face in the frame and crop the image
face_coords = detector.detect(gray)
face = detector.crop_face(gray, face_coords)
# Check we have detected a face
if face is not None:
# Apply LBP operator to get feature descriptor
hist, bins = lbp.run(face, False)
# Convert the LBP descriptor to numpy array for opencv classifiers
test_sample = np.array([hist], dtype=np.float32)
# Get the class of id of the closest neighbour and its distance
dist, class_id = knn.predict(test_sample)
# Draw the face if found
util.draw_face(dist, class_id, frame, face_coords)
# util.segment_face(frame)
# Processing finished
end = time.time()
# Write the fps to the video
util.write_fps(start, end, frame)
# Display the resulting frame
cv2.imshow('frame', frame)
# Check if we should stop the application
if cv2.waitKey(1) & 0xFF == ord('q'):
break
# When everything done, release the capture
cap.release()
cv2.destroyAllWindows()
def classify(messages_train,labels_train,messages_test,process_messages_train,process_messages_test,tokens_train,tokens_test,process_tokens_train,process_tokens_test,pos_tags_train,pos_tags_test,negationList,clusters,slangDictionary,lexicons,mpqa_lexicons):
# 0 - negative messages
# 1 - positives messages
labels_train = [0 if x=="negative" else 1 for x in labels_train]
#compute pos tag bigrams for all messages
pos_bigrams_train = getBigrams(pos_tags_train)
pos_bigrams_test = getBigrams(pos_tags_test)
#compute pos tag trigrams for all messages
pos_trigrams_train = getTrigrams(pos_tags_train)
pos_trigrams_test = getTrigrams(pos_tags_test)
#get the unique pos bigrams and trigrams from training set
unique_pos_tags = getPosTagsSet(pos_tags_train)
unique_bigrams = getBigramsSet(pos_bigrams_train)
unique_trigrams= getTrigramsSet(pos_trigrams_train)
#calculate pos bigrams score for all categories
#both dictionaries will be used for training and testing (cannot create new for testing because we don't know the labels of the new messages)
pos_tags_scores_negative = posTagsScore(unique_pos_tags,0,pos_tags_train,labels_train)
pos_tags_scores_positive = posTagsScore(unique_pos_tags,1,pos_tags_train,labels_train)
#calculate pos bigrams score for all categories
#both dictionaries will be used for training and testing (cannot create new for testing because we don't know the labels of the new messages)
pos_bigrams_scores_negative = posBigramsScore(unique_bigrams,0,pos_bigrams_train,labels_train)
pos_bigrams_scores_positive = posBigramsScore(unique_bigrams,1,pos_bigrams_train,labels_train)
#calculate pos bigrams score for all categories
#both dictionaries will be used for training and testing (cannot create new for testing because we don't know the labels of the new messages)
pos_trigrams_scores_negative = posTrigramsScore(unique_trigrams,0,pos_trigrams_train,labels_train)
pos_trigrams_scores_positive = posTrigramsScore(unique_trigrams,1,pos_trigrams_train,labels_train)
#assign a precision and F1 score to each word of to all mpqa lexicons
mpqaScores = getScores(mpqa_lexicons,process_messages_train,labels_train)
#get features from train messages
features_train = features.getFeatures(messages_train,process_messages_train,tokens_train,process_tokens_train,pos_tags_train,slangDictionary,lexicons,mpqa_lexicons,pos_bigrams_train,pos_trigrams_train,pos_bigrams_scores_negative,pos_bigrams_scores_positive,pos_trigrams_scores_negative,pos_trigrams_scores_positive,pos_tags_scores_negative,pos_tags_scores_positive,mpqaScores,negationList,clusters)
#regularize train features
features_train=regularization.regularize(features_train)
#get features from test messages
features_test = features.getFeatures(messages_test,process_messages_test,tokens_test,process_tokens_test,pos_tags_test,slangDictionary,lexicons,mpqa_lexicons,pos_bigrams_test,pos_trigrams_test,pos_bigrams_scores_negative,pos_bigrams_scores_positive,pos_trigrams_scores_negative,pos_trigrams_scores_positive,pos_tags_scores_negative,pos_tags_scores_positive,mpqaScores,negationList,clusters)
#regularize test features
features_test=regularization.regularize(features_test)
#feature selection
#features_train, features_test = selection.feature_selection(features_train,labels_train,features_test,1150)
#C parameter of SVM
C = 0.001953125
#C = 19.3392161013
#train classifier and return trained model
#model = LogisticRegression.train(features_train,labels_train)
model = SVM.train(features_train,labels_train,c=C,k="linear")
#predict labels
#prediction = LogisticRegression.predict(features_test,model)
prediction = SVM.predict(features_test,model)
return prediction
def main(f):
print "System training started"
#load training dataset
dataset_train = f
ids, labels_train, messages_train = tsvreader.opentsv(dataset_train)
print "Train data loaded"
#labels for subjectivity detection (2 categories)
temp_labels_train = [0 if x == "neutral" else 1 for x in labels_train]
#labels for polarity detection (3 categories)
labels_train = [
0 if x == "neutral" else -1 if x == "negative" else 1
for x in labels_train
]
#convert labels to numpy arrays
temp_labels_train = np.array(temp_labels_train)
labels_train = np.array(labels_train)
#load word clusters
clusters = loadClusters()
print "Clusters loaded"
#load Lexicons
negationList, slangDictionary, lexicons, mpqa_lexicons = loadLexicons()
print "Lexicons loaded"
#tokenize all messages
tokens_train = tokenize(messages_train)
print "Messages tokenized"
#compute pos tags for all messages
pos_tags_train = arktagger.pos_tag_list(messages_train)
print "Pos tags computed"
#compute pos tag bigrams
pos_bigrams_train = getBigrams(pos_tags_train)
#compute pos tag trigrams
pos_trigrams_train = getTrigrams(pos_tags_train)
#get the unique pos bigrams from training set
unique_pos_tags = getPosTagsSet(pos_tags_train)
unique_bigrams = getBigramsSet(pos_bigrams_train)
unique_trigrams = getTrigramsSet(pos_trigrams_train)
#compute POS tag scores
pos_tags_scores_neutral = posTagsScore(unique_pos_tags, 0, pos_tags_train,
labels_train)
pos_tags_scores_positive = posTagsScore(unique_pos_tags, 1, pos_tags_train,
labels_train)
pos_tags_scores_negative = posTagsScore(unique_pos_tags, -1,
pos_tags_train, labels_train)
pos_bigrams_scores_neutral = posBigramsScore(unique_bigrams, 0,
pos_bigrams_train,
labels_train)
pos_bigrams_scores_positive = posBigramsScore(unique_bigrams, 1,
pos_bigrams_train,
labels_train)
pos_bigrams_scores_negative = posBigramsScore(unique_bigrams, -1,
pos_bigrams_train,
labels_train)
pos_trigrams_scores_neutral = posTrigramsScore(unique_trigrams, 0,
pos_trigrams_train,
labels_train)
pos_trigrams_scores_positive = posTrigramsScore(unique_trigrams, 1,
pos_trigrams_train,
labels_train)
pos_trigrams_scores_negative = posTrigramsScore(unique_trigrams, -1,
pos_trigrams_train,
labels_train)
#compute mpqa scores
mpqaScores = getScores(mpqa_lexicons,
messages_train,
labels_train,
neutral=True)
#save scores and other resources for future use
savePosScores(pos_tags_scores_neutral, pos_tags_scores_positive,
pos_tags_scores_negative, pos_bigrams_scores_neutral,
pos_bigrams_scores_positive, pos_bigrams_scores_negative,
pos_trigrams_scores_neutral, pos_trigrams_scores_positive,
pos_trigrams_scores_negative, mpqaScores)
#save lexicons
saveLexicons(negationList, slangDictionary, lexicons, mpqa_lexicons)
#save clusters
saveClusters(clusters)
#load Glove embeddings
d = 200
glove = GloveDictionary.Glove(d)
#save Glove embeddings for future use
saveGlove(glove)
#Subjectivity Detection Features
#SD1 features
features_train_1 = features.getFeatures(
messages_train, tokens_train, pos_tags_train, slangDictionary,
lexicons, mpqa_lexicons, pos_bigrams_train, pos_trigrams_train,
pos_bigrams_scores_negative, pos_bigrams_scores_positive,
pos_trigrams_scores_negative, pos_trigrams_scores_positive,
pos_tags_scores_negative, pos_tags_scores_positive, mpqaScores,
negationList, clusters, pos_bigrams_scores_neutral,
pos_trigrams_scores_neutral, pos_tags_scores_neutral)
#SD2 features
features_train_2 = []
#for message in tokens_train :
for i in range(0, len(messages_train)):
features_train_2.append(glove.findCentroid(tokens_train[i]))
features_train_2 = np.array(features_train_2)
#regularize features
features_train_1 = regularization.regularize(features_train_1)
features_train_2 = regularization.regularizeHorizontally(features_train_2)
#Penalty parameter C of the error term for every SD system
C1 = 0.001953125
C2 = 1.4068830572470667
#get confidence scores
train_confidence_1 = getConfidenceScores(features_train_1,
temp_labels_train, C1)
train_confidence_2 = getConfidenceScores(features_train_2,
temp_labels_train, C2)
#normalize confidence scores
softmax = lambda x: 1 / (1. + math.exp(-x))
train_confidence_1 = [softmax(conf) for conf in train_confidence_1]
train_confidence_2 = [softmax(conf) for conf in train_confidence_2]
train_confidence_1 = np.array(train_confidence_1)
train_confidence_2 = np.array(train_confidence_2)
#train SD classifiers
sd1 = SVM.train(features_train_1, temp_labels_train, c=C1, k="linear")
sd2 = SVM.train(features_train_2, temp_labels_train, c=C2, k="linear")
#Sentiment Polarity Features (append confidence scores to SD features)
#SP1 features
features_train_1 = np.hstack(
(features_train_1,
train_confidence_1.reshape(train_confidence_1.shape[0], 1)))
#SP1 features
features_train_2 = np.hstack(
(features_train_2,
train_confidence_2.reshape(train_confidence_2.shape[0], 1)))
#Penalty parameter C of the error term for every SP system
C1 = 0.003410871889693192
C2 = 7.396183688299606
#train SP classifiers
sp1 = SVM.train(features_train_1, labels_train, c=C1, k="linear")
sp2 = SVM.train(features_train_2, labels_train, c=C2, k="linear")
#save trained models
saveModels(sd1, sd2, sp1, sp2)
print "System training completed!"
def main(f):
print "System training started"
#load training dataset
dataset_train = f
ids,labels_train,messages_train=tsvreader.opentsv(dataset_train)
print "Train data loaded"
#labels for subjectivity detection (2 categories)
temp_labels_train = [0 if x=="neutral" else 1 for x in labels_train]
#labels for polarity detection (3 categories)
labels_train = [0 if x=="neutral" else -1 if x =="negative" else 1 for x in labels_train]
#convert labels to numpy arrays
temp_labels_train=np.array(temp_labels_train)
labels_train=np.array(labels_train)
#load word clusters
clusters = loadClusters()
print "Clusters loaded"
#load Lexicons
negationList, slangDictionary, lexicons, mpqa_lexicons = loadLexicons()
print "Lexicons loaded"
#tokenize all messages
tokens_train = tokenize(messages_train)
print "Messages tokenized"
#compute pos tags for all messages
pos_tags_train = arktagger.pos_tag_list(messages_train)
print "Pos tags computed"
#compute pos tag bigrams
pos_bigrams_train = getBigrams(pos_tags_train)
#compute pos tag trigrams
pos_trigrams_train = getTrigrams(pos_tags_train)
#get the unique pos bigrams from training set
unique_pos_tags = getPosTagsSet(pos_tags_train)
unique_bigrams = getBigramsSet(pos_bigrams_train)
unique_trigrams= getTrigramsSet(pos_trigrams_train)
#compute POS tag scores
pos_tags_scores_neutral = posTagsScore(unique_pos_tags,0,pos_tags_train,labels_train)
pos_tags_scores_positive = posTagsScore(unique_pos_tags,1,pos_tags_train,labels_train)
pos_tags_scores_negative = posTagsScore(unique_pos_tags,-1,pos_tags_train,labels_train)
pos_bigrams_scores_neutral = posBigramsScore(unique_bigrams,0,pos_bigrams_train,labels_train)
pos_bigrams_scores_positive = posBigramsScore(unique_bigrams,1,pos_bigrams_train,labels_train)
pos_bigrams_scores_negative = posBigramsScore(unique_bigrams,-1,pos_bigrams_train,labels_train)
pos_trigrams_scores_neutral = posTrigramsScore(unique_trigrams,0,pos_trigrams_train,labels_train)
pos_trigrams_scores_positive = posTrigramsScore(unique_trigrams,1,pos_trigrams_train,labels_train)
pos_trigrams_scores_negative = posTrigramsScore(unique_trigrams,-1,pos_trigrams_train,labels_train)
#compute mpqa scores
mpqaScores = getScores(mpqa_lexicons,messages_train,labels_train,neutral=True)
#save scores and other resources for future use
savePosScores(pos_tags_scores_neutral, pos_tags_scores_positive,pos_tags_scores_negative,pos_bigrams_scores_neutral,pos_bigrams_scores_positive,pos_bigrams_scores_negative,pos_trigrams_scores_neutral,pos_trigrams_scores_positive,pos_trigrams_scores_negative,mpqaScores)
#save lexicons
saveLexicons(negationList,slangDictionary,lexicons,mpqa_lexicons)
#save clusters
saveClusters(clusters)
#load Glove embeddings
d = 200
glove = GloveDictionary.Glove(d)
#save Glove embeddings for future use
saveGlove(glove)
#Subjectivity Detection Features
#SD1 features
features_train_1 = features.getFeatures(messages_train,tokens_train,pos_tags_train,slangDictionary,lexicons,mpqa_lexicons,pos_bigrams_train,pos_trigrams_train,pos_bigrams_scores_negative,pos_bigrams_scores_positive,pos_trigrams_scores_negative,pos_trigrams_scores_positive,pos_tags_scores_negative,pos_tags_scores_positive,mpqaScores,negationList,clusters,pos_bigrams_scores_neutral,pos_trigrams_scores_neutral,pos_tags_scores_neutral)
#SD2 features
features_train_2 = []
#for message in tokens_train :
for i in range(0,len(messages_train)):
features_train_2.append(glove.findCentroid(tokens_train[i]))
features_train_2 = np.array(features_train_2)
#regularize features
features_train_1 = regularization.regularize(features_train_1)
features_train_2 = regularization.regularizeHorizontally(features_train_2)
#Penalty parameter C of the error term for every SD system
C1=0.001953125
C2=1.4068830572470667
#get confidence scores
train_confidence_1 = getConfidenceScores(features_train_1, temp_labels_train, C1)
train_confidence_2 = getConfidenceScores(features_train_2, temp_labels_train, C2)
#normalize confidence scores
softmax = lambda x: 1 / (1. + math.exp(-x))
train_confidence_1 = [softmax(conf) for conf in train_confidence_1]
train_confidence_2 = [softmax(conf) for conf in train_confidence_2]
train_confidence_1 = np.array(train_confidence_1)
train_confidence_2 = np.array(train_confidence_2)
#train SD classifiers
sd1 = SVM.train(features_train_1,temp_labels_train,c=C1,k="linear")
sd2 = SVM.train(features_train_2,temp_labels_train,c=C2,k="linear")
#Sentiment Polarity Features (append confidence scores to SD features)
#SP1 features
features_train_1 = np.hstack((features_train_1,train_confidence_1.reshape(train_confidence_1.shape[0],1)))
#SP1 features
features_train_2 = np.hstack((features_train_2,train_confidence_2.reshape(train_confidence_2.shape[0],1)))
#Penalty parameter C of the error term for every SP system
C1=0.003410871889693192
C2=7.396183688299606
#train SP classifiers
sp1 = SVM.train(features_train_1,labels_train,c=C1,k="linear")
sp2 = SVM.train(features_train_2,labels_train,c=C2,k="linear")
#save trained models
saveModels(sd1,sd2,sp1,sp2)
print "System training completed!"