def classify(self, data):
post_probability = {}
for label, probability in self.label_probabilities.iteritems():
words = re.compile('\w+').findall(data.text)
post_probability[label] = reduce(
lambda acc, word: acc + math.log(
self.parameters.probability(word, label), 10), words,
math.log(probability))
return data, max(post_probability.iteritems(),
key=operator.itemgetter(1))[0]
test_dir = sys.argv[1]
loader = ReviewLoader()
# truthful = loader.load(test_dir + "/negative/truthful", 'truthful') \
# + loader.load(test_dir + "/positive/truthful", 'truthful')
# deceptive = loader.load(test_dir + "/negative/deceptive", 'deceptive') \
# + loader.load(test_dir + "/positive/deceptive", 'deceptive')
# positive = loader.load(test_dir + '/positive', 'positive')
# negative = loader.load(test_dir + '/negative', 'negative')
#
# test_data1 = truthful + deceptive
# test_data2 = positive + negative
test_data = loader.load_without_label(test_dir)
model_params = ParameterReader('nbmodel.txt').read(2)
deceptive_model_params = model_params[0]
negative_model_params = model_params[1]
deception_classifier = NaiveClassifier(deceptive_model_params[0],
def sampled_label_probability(self, label):
count = 0
for labelled_data in self.labelled_data.values():
count += len(labelled_data)
return 1.0 * len(self.labelled_data[label]) / count
def sampled_label_probabilities(self):
probabilities = {}
for label in self.labels:
probabilities[label] = self.sampled_label_probability(label)
return probabilities
train_dir = sys.argv[1]
loader = ReviewLoader()
deceptive = loader.load(train_dir + '/positive_polarity/deceptive_from_MTurk', 'deceptive') + \
loader.load(train_dir + '/negative_polarity/deceptive_from_MTurk', 'deceptive')
truthful = loader.load(train_dir + '/negative_polarity/truthful_from_Web', 'truthful') + \
loader.load(train_dir + '/positive_polarity/truthful_from_TripAdvisor', 'truthful')
deception_learner = NaiveLearner(deceptive + truthful)
positive = loader.load(train_dir + '/positive_polarity', 'positive')
negative = loader.load(train_dir + '/negative_polarity', 'negative')
negativity_learner = NaiveLearner(positive + negative)
writer = ParameterWriter('nbmodel.txt')
writer.write(deception_learner.parameters, deception_learner.sampled_label_probabilities())
writer.write(negativity_learner.parameters, negativity_learner.sampled_label_probabilities())
return map(self.classify, self.to_classify)
def classify(self, data):
post_probability = {}
for label, probability in self.label_probabilities.iteritems():
words = re.compile('\w+').findall(data.text)
post_probability[label] = reduce(
lambda acc, word: acc + math.log(self.parameters.probability(word, label), 10), words,
math.log(probability))
return data, max(post_probability.iteritems(), key=operator.itemgetter(1))[0]
test_dir = sys.argv[1]
loader = ReviewLoader()
# truthful = loader.load(test_dir + "/negative/truthful", 'truthful') \
# + loader.load(test_dir + "/positive/truthful", 'truthful')
# deceptive = loader.load(test_dir + "/negative/deceptive", 'deceptive') \
# + loader.load(test_dir + "/positive/deceptive", 'deceptive')
# positive = loader.load(test_dir + '/positive', 'positive')
# negative = loader.load(test_dir + '/negative', 'negative')
#
# test_data1 = truthful + deceptive
# test_data2 = positive + negative
test_data = loader.load_without_label(test_dir)
model_params = ParameterReader('nbmodel.txt').read(2)
deceptive_model_params = model_params[0]
negative_model_params = model_params[1]
deception_classifier = NaiveClassifier(deceptive_model_params[0], deceptive_model_params[1], test_data)
count = 0
for labelled_data in self.labelled_data.values():
count += len(labelled_data)
return 1.0 * len(self.labelled_data[label]) / count
def sampled_label_probabilities(self):
probabilities = {}
for label in self.labels:
probabilities[label] = self.sampled_label_probability(label)
return probabilities
train_dir = sys.argv[1]
loader = ReviewLoader()
deceptive = loader.load(train_dir + '/positive_polarity/deceptive_from_MTurk', 'deceptive') + \
loader.load(train_dir + '/negative_polarity/deceptive_from_MTurk', 'deceptive')
truthful = loader.load(train_dir + '/negative_polarity/truthful_from_Web', 'truthful') + \
loader.load(train_dir + '/positive_polarity/truthful_from_TripAdvisor', 'truthful')
deception_learner = NaiveLearner(deceptive + truthful)
positive = loader.load(train_dir + '/positive_polarity', 'positive')
negative = loader.load(train_dir + '/negative_polarity', 'negative')
negativity_learner = NaiveLearner(positive + negative)
writer = ParameterWriter('nbmodel.txt')
writer.write(deception_learner.parameters,
deception_learner.sampled_label_probabilities())
writer.write(negativity_learner.parameters,
negativity_learner.sampled_label_probabilities())
