def extract_aspects(reviews):
"""
INPUT: iterable of strings (pd Series, list)
OUTPUT: list of aspects
Return the aspects from the set of reviews
"""
# import the aspect extraction functions
from extract_aspects import get_sentences, tokenize, pos_tag, aspects_from_tagged_sents
# put all the sentences in all reviews in one stream
sentences = []
for review in reviews:
sentences.extend(get_sentences(review.encode('utf-8', 'ignore')))
tokenized_sentences = [
tokenize(sentence) for sentence in sentences
for sentences in get_sentences(review.encode('utf-8', 'ignore'))
]
# tokenize each sentence
#tokenized_sentences = [tokenize(sentence) for sentence in sentences]
# pos tag each sentence
tagged_sentences = [pos_tag(sentence) for sentence in tokenized_sentences]
# from the pos tagged sentences, get a list of aspects
aspects = aspects_from_tagged_sents(tagged_sentences)
return aspects
def get_sentences_by_aspect(aspect, reviews):
"""
INPUT: string (aspect), iterable of strings (full reviews)
OUTPUT: iterable of strings
Given an aspect and a list of reviews, return a list
sof all sentences that mention that aspect.
"""
# THIS CODE IS TOTALLY COPIED FROM MAIN FILE function 'extract_aspects'
# TODO: REFACTOR THIS IN AN INTELLIGENT WAY.
from extract_aspects import get_sentences, tokenize, pos_tag, aspects_from_tagged_sents
# get
sentences = []
for review in reviews:
sentences.extend(get_sentences(review.encode('utf-8', 'ignore')))
# tokenize each sentence
tokenized_sentences = [
tokenize(sentence) for sentence in sentences
for sentences in get_sentences(review)
]
return [sent for sent in tokenized_sentences if aspect in sent]
def extract_aspects(reviews): """ INPUT: iterable of strings (pd Series, list) OUTPUT: list of aspects Return the aspects from the set of reviews """ # import the aspect extraction functions from extract_aspects import get_sentences, tokenize, pos_tag, aspects_from_tagged_sents # put all the sentences in all reviews in one stream #sentences = [] #for review in reviews: # sentences.extend(get_sentences(review)) tokenized_sentences = [tokenize(sentence) for sentence in sentences for sentences in get_sentences(review)] # tokenize each sentence #tokenized_sentences = [tokenize(sentence) for sentence in sentences] # pos tag each sentence tagged_sentences = [pos_tag(sentence) for sentence in tokenized_sentences] # from the pos tagged sentences, get a list of aspects aspects = aspects_from_tagged_sents(tagged_sentences) return aspects
def aspect_opinions(tweets, aspects):
from extract_aspects import get_sentences, tokenize, pos_tag, aspects_from_tagged_sents
sentences = []
for tweet in tweets:
sentences.extend(get_sentences(tweets[tweet]))
tokenized_sentences = [tokenize(sentence) for sentence in sentences]
aspect_to_tweets = {}
for tweet in tokenized_sentences:
tweet_aspects = extract_aspects(tweet)
relevant_aspects = get_relevant_aspects(tweet_aspects, aspects)
for p_aspect in relevant_aspects:
#value has the relevant aspects. create a dictionary and push the tweets
p_aspects = relevant_aspects[p_aspect]
for aspect in p_aspects:
if aspect in aspect_to_tweets:
aspect_to_tweets[aspect].append(tweet)
else:
aspect_to_tweets[aspect] = []
aspect_to_tweets[aspect].append(tweet)
features = {}
for aspect, tweets in aspect_to_tweets.items():
features[aspect] = [len(tweets), score_aspect(tweets)]
return features
def aspect_opinions(reviews, aspects): from extract_aspects import get_sentences, tokenize, pos_tag, aspects_from_tagged_sents sentences = [] for review in reviews : sentences.extend(get_sentences(review)) tokenized_sentences = [tokenize(sentence) for sentence in sentences] return dict([(aspect, score_aspect(tokenized_sentences, aspect)) for aspect in aspects])
def extract_aspects(reviews):
from extract_aspects import get_sentences, tokenize, pos_tag, aspects_from_tagged_sents
sentences = []
for review in reviews:
sentences.extend(get_sentences(review))
tokenized_sentences = [tokenize(sentence) for sentence in sentences]
tagged_sentences = [pos_tag(sentence) for sentence in tokenized_sentences]
aspects = all_aspects_from_tagged_sents(tagged_sentences)
return aspects
def get_sentences_by_aspect(aspect, reviews): """ INPUT: string (aspect), iterable of strings (full reviews) OUTPUT: iterable of strings Given an aspect and a list of reviews, return a list sof all sentences that mention that aspect. """ # THIS CODE IS TOTALLY COPIED FROM MAIN FILE function 'extract_aspects' # TODO: REFACTOR THIS IN AN INTELLIGENT WAY. from extract_aspects import get_sentences, tokenize, pos_tag, aspects_from_tagged_sents # get #sentences = [] #for review in reviews: # sentences.extend(get_sentences(review)) # tokenize each sentence tokenized_sentences = [tokenize(sentence) for sentence in sentences for sentences in get_sentences(review)] return [sent for sent in tokenized_sentences if aspect in sent]
def aspect_opinions(reviews, aspects, relevant_features):
from extract_aspects import get_sentences, tokenize, pos_tag, aspects_from_tagged_sents
sentences = []
for review in reviews :
sentences.extend(get_sentences(review))
tokenized_sentences = [tokenize(sentence) for sentence in sentences]
scores = [(aspect[1], score_aspect(tokenized_sentences, aspect[0])) for aspect in aspects.items()]
aspect_scores = {}
for score in scores :
klass = relevant_features[score[0]]
if klass in aspect_scores :
old_count = aspect_scores[klass][0]
old_score = aspect_scores[klass][1]
new_count = old_count + score[1][0]
new_score = ( old_count * old_score + new_count * score[1][1] ) / (old_count + new_count)
aspect_scores[klass] = (new_count, new_score)
else :
aspect_scores[klass] = (score[1][0], score[1][1])
return aspect_scores
