def trainPosNeg(self):
positive = "./positive"
negative = "./negative"
pos_files = ptr(positive, '.*')
neg_files = ptr(negative, '.*')
pos_all_words = [pos_files.raw(fileid).split(" ")
for fileid in pos_files.fileids()]
neg_all_words = [neg_files.raw(fileid).split(" ")
for fileid in neg_files.fileids()]
pos_splited_words = [(self.getBigrams(words), 'positive')
for words in pos_all_words]
neg_splited_words = [(self.getBigrams(words), 'negative')
for words in neg_all_words]
pos_neg_trainfeats = pos_splited_words[:] + neg_splited_words[:]
classifier = SklearnClassifier(LinearSVC())
classifier.train(pos_neg_trainfeats)
return classifier
def trainSubObj(self):
subjective = "./subjective"
objective = "./objective"
sub_files = ptr(subjective, '.*')
obj_files = ptr(objective, '.*')
sub_all_words = [sub_files.raw(fileid).split(" ")
for fileid in sub_files.fileids()]
obj_all_words = [obj_files.raw(fileid).split(" ")
for fileid in obj_files.fileids()]
sub_splited_words = [(self.getBigrams(words), 'subjective')
for words in sub_all_words]
obj_splited_words = [(self.getBigrams(words), 'objective')
for words in obj_all_words]
sub_obj_trainfeats = sub_splited_words[:] + obj_splited_words[:]
# SVM with a Linear Kernel and default parameters
classifier = SklearnClassifier(LinearSVC())
classifier.train(sub_obj_trainfeats)
return classifier