def __init__(self,
stop_words_file,
related_training_data_file,
awareness_training_data_file,
needs_training,
related_classifier_dump_file,
awareness_classifier_dump_file,
feature_list_file,
classifier_type='nb'):
self.helper = ClassifierHelper()
self.stop_words = self.init_stop_words(stop_words_file)
self.feature_list = []
if needs_training:
self.related_classifier = self.train_classifier(
related_training_data_file, related_classifier_dump_file,
feature_list_file, classifier_type)
self.awareness_classifier = self.train_classifier(
awareness_training_data_file, awareness_classifier_dump_file,
feature_list_file, classifier_type)
else:
with open(related_classifier_dump_file, 'rb') as f:
self.related_classifier = pickle.load(f)
with open(awareness_classifier_dump_file, 'rb') as f:
self.awareness_classifier = pickle.load(f)
with open(feature_list_file, 'r') as f:
for token in f:
self.feature_list.append(token.strip())
def __init__(self, trainingDataFile, classifierDumpFile, datadir):
# Instantiate classifier helper
self.helper = ClassifierHelper('%s/%s' % (datadir, 'feature_list.txt'),
'%s/%s' % (datadir, 'stop_words.txt'))
self.trainingDataFile = trainingDataFile
self.classifierPickled = classifierDumpFile
self.last_trained = None
self.classifier = self._getClassifier()
