def __init__(self, database):
"""
(str) ->
Initialize database and creates two DynamicArray
objects, and trains the model
"""
self.database = database
self.tweet = None
self.emotions = DynamicArray()
self.probabilities = DynamicArray()
self._classifier = self._train_model()
def get_emotions_probability(self):
"""
() -> DynamicArray
Returns an array with emotions of the TWEET
and their probabilities and adds to the array
"""
emotions = DynamicArray()
probabilities = self._classifier.prob_classify(self._tweets_features(self.tweet))
for sample in probabilities.samples():
emotions.append((sample, probabilities.prob(sample)))
self.probabilities.append(emotions)
return emotions
def _creating_set(self):
"""
() -> DynamicArray
Returns an array to train model on it
"""
result_set = DynamicArray()
file = open(self.database, "r", encoding='utf-8')
file.readline()
for line in file:
line = line.split('\t')
first_el = self._tweets_features(line[0])
result_set.append((first_el, line[1]))
return result_set
def available_dates(self):
"""
() -> DynamicArray
Returns a list with the dates on which user wrote tweets
"""
available_dates = DynamicArray()
cur_node = self.data.next
while cur_node is not None:
try:
date = cur_node.data[0].split()
day = "{} {} {}".format(date[1], date[2], date[5])
available_dates.append((cur_node.data[0], day))
cur_node = cur_node.next
except IndexError:
pass
return available_dates
def get_tweet_by_day(self, day):
"""
(str) -> DynamicArray
Returns a list of tweets that have been written
at given DAY
"""
counter = False
for date in self.available_dates:
if date[1] == day:
day = date[0]
counter = True
if not counter:
raise ValueError("This DAY is not available")
days = DynamicArray()
cur_node = self.data.next
while cur_node is not None:
if cur_node.data[0] == day:
days.append(cur_node.data[1])
cur_node = cur_node.next
return days
class EmotionsList:
"""Representing EmotionsList ADT that preserves
emotions and their probabilities"""
def __init__(self, database):
"""
(str) ->
Initialize database and creates two DynamicArray
objects, and trains the model
"""
self.database = database
self.tweet = None
self.emotions = DynamicArray()
self.probabilities = DynamicArray()
self._classifier = self._train_model()
def set_tweet(self, tweet):
"""
(str) ->
Sets tweet which the ADT will analyze
"""
self.tweet = tweet
@staticmethod
def _remove_stop_words(tweet):
"""
(str) -> str
Returns tweet with removed stop words
"""
tokens_without_sw = ""
for word in tweet.split():
if not word.lower() in STOPWORDS:
tokens_without_sw += word.lower() + " "
return tokens_without_sw
def _tweets_features(self, tweet):
"""
(str) -> dict
Additional method.
Creates dictionary with tweet to use it in the
classifying this tweet
"""
tweet = self._remove_stop_words(tweet)
return {'tweet': tweet}
def _creating_set(self):
"""
() -> DynamicArray
Returns an array to train model on it
"""
result_set = DynamicArray()
file = open(self.database, "r", encoding='utf-8')
file.readline()
for line in file:
line = line.split('\t')
first_el = self._tweets_features(line[0])
result_set.append((first_el, line[1]))
return result_set
def _train_model(self):
"""
() -> NaiveBayesClassifier
Trains model with data
"""
train_set = self._creating_set()
return NaiveBayesClassifier.train(train_set)
def get_tweet_emotion(self):
"""
() -> str
Returns a main emotion of the tweet and
adds to the array
"""
label = self._classifier.classify(self._tweets_features(self.tweet))
self.emotions.append(label)
return label
def get_emotions_probability(self):
"""
() -> DynamicArray
Returns an array with emotions of the tweet
and their probabilities and adds to the array
"""
emotions = DynamicArray()
probabilities = self._classifier.prob_classify(
self._tweets_features(self.tweet))
for sample in probabilities.samples():
emotions.append((sample, probabilities.prob(sample)))
self.probabilities.append(emotions)
return emotions