def get_info(self, content):
words = util.getWords(content)
temp_tags = bigram_tag.tag(words)
tags = self.re_tag(temp_tags)
normalized = True
while normalized:
normalized = False
for i in range(0, len(tags) - 1):
tagged1 = tags[i]
if i + 1 >= len(tags):
break
tagged2 = tags[i + 1]
key = tagged1[1] + '+' + tagged2[1]
pos = cfg.get(key)
if pos:
tags.pop(i)
tags.pop(i)
re_tagged = tagged1[0] + ' ' + tagged2[0]
tags.insert(i, (re_tagged, pos))
normalized = True
final_context = []
for tag in tags:
if tag[1] == 'NNP' or tag[1] == 'NNI':
final_context.append(tag[0])
return final_context
def get_info(self, content):
words = util.getWords(content)
temp_tags = bigram_tag.tag(words)
tags = self.re_tag(temp_tags)
normalized = True
while normalized:
normalized = False
for i in range(0, len(tags) - 1):
tagged1 = tags[i]
if i+1 >= len(tags):
break
tagged2 = tags[i+1]
key = tagged1[1] + '+' + tagged2[1]
pos = cfg.get(key)
if pos:
tags.pop(i)
tags.pop(i)
re_tagged = tagged1[0] + ' ' + tagged2[0]
tags.insert(i, (re_tagged, pos))
normalized = True
final_context = []
for tag in tags:
if tag[1] == 'NNP' or tag[1] == 'NNI':
final_context.append(tag[0])
return final_context
def remove_stopwords(sentences):
"""
Removes stopwords from the sentence
:param sentences: (list) sentences
:returns: cleaned sentences without any stopwords
"""
sw = set(stopwords.words('english'))
cleaned = []
for sentence in sentences:
words = util.getWords(sentence)
sentence = ' '.join([c for c in words if c not in sw])
cleaned.append(sentence)
return cleaned
def remove_stopwords(sentences):
"""
Removes stopwords from the sentence
:param sentences: (list) sentences
:returns: cleaned sentences without any stopwords
"""
sw = set(stopwords.words('english'))
cleaned = []
for sentence in sentences:
words = util.getWords(sentence)
sentence = ' '.join([c for c in words if c not in sw])
cleaned.append(sentence)
return cleaned
def get_text():
"""
Driver function; Execution starts here
"""
text = raw_input('TEXT: ')
limit = input('LIMIT: ')
words_dict, words = util.getWords(text)
words_sorted = sorted(words, key=len)
words_dict = reduce_general_slang(words_dict, words_sorted, limit)
words_dict = reduce_suffix(words_dict, words_sorted, limit)
words_dict = reduce_prefix(words_dict, words_sorted, limit)
words_dict = reduce_vowels(words_dict, words_sorted, limit)
for word in words:
print words_dict[word][REDUCED],
def testGetWords(w):
return util.getWords(w)
# print(util.getRelations('force'))
