def test_get_sentences_fail():
"""
Test that get_sentences fails
when passed None.
"""
tokenize(None)
def test_get_sentences_fail(): """ Test that get_sentences fails when passed None. """ tokenize(None)
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 opinion_mining.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(reviews)]
]
# 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 test_tokenize():
""""
Tests to make sure that the tokenizer works
"""
sentence = "This is a test SENTENCE"
tokens = tokenize(sentence)
for tok in tokens:
assert tok.islower()
assert len(tokens) == 5
assert isinstance(tokens, list)
def test_tokenize(): """" Tests to make sure that the tokenizer works """ sentence = "This is a test SENTENCE" tokens = tokenize(sentence) for tok in tokens: assert tok.islower() assert len(tokens) == 5 assert isinstance(tokens, list)
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 opinion_mining.extract_aspects import get_sentences, tokenize, pos_tag, aspects_from_tagged_sents
# get
'''
sentences = []
if type(reviews)==str:
sentences.append(reviews)
else:
for review in reviews:
sentences.extend(get_sentences(review))
'''
sentences = get_sentences(reviews)
# tokenize each sentence
tokenized_sentences = [tokenize(sentence) for sentence in sentences]
sent_set = []
for i in aspect:
for j in tokenized_sentences:
if i in j:
if i not in sent_set:
sent_set.append(j)
return sent_set