def giveKeyword(text):
from bs4 import BeautifulSoup
text = BeautifulSoup(text, "lxml").get_text()
from nltk.tokenize import RegexpTokenizer
tokenizer = RegexpTokenizer(r'\w+')
text = tokenizer.tokenize(text)
#print text
cleanText = "".join([
" " + i if not i.startswith("'") and i not in string.punctuation else i
for i in text
]).strip()
rakeobj = Rake("SmartStoplist.txt")
keywords = rakeobj.run(cleanText)
output = ""
#take top two highest ranked (if there even are two)
for keyword in keywords[0:2]:
output = output + keyword[0] + ","
return output #the highest ranked one...
def rake_extract_concepts(text, exclude, number):
r = Rake('/usr/share/postgresql/10/tsearch_data/english.stop')
concepts = r.run(text, minCharacters=2, maxWords=4, minFrequency=3)
count = 0
for keyword, weight in concepts:
if weight > 1 and count < number and keyword not in exclude:
yield keyword, weight
count += 1
def rake(text, top_n=10):
# Clean the text from non-printable characters.
text = ''.join(word for word in text if word in printable)
# Uses all english stopwords and punctuation from NLTK.
r = Rake(NLTKStopList())
return [keyphrase for (keyphrase, score) in r.run(text)[:top_n]]
class KWGet(Driver):
def setup(self):
path = os.path.join(os.path.dirname(__file__), STOPWORDS)
self._rake = Rake(path)
def _get_keywords(self, text):
buf = b64decode(text)
keywords = self._rake.run(buf)
if PRINT:
print('KWGet: keywords=%s' % str(keywords))
return keywords
@wrapper
def put(self, *args, **kwargs):
text = kwargs.get('content')
if text:
keywords = self._get_keywords(text)
if keywords:
return {'keywords':keywords}
class KWGet(Driver):
def setup(self):
path = os.path.join(os.path.dirname(__file__), STOPWORDS)
self._rake = Rake(path)
def _get_keywords(self, text):
buf = b64decode(text)
keywords = self._rake.run(buf)
if PRINT:
print('KWGet: keywords=%s' % str(keywords))
return keywords
@wrapper
def put(self, *args, **kwargs):
text = kwargs.get('content')
if text:
keywords = self._get_keywords(text)
if keywords:
return {'keywords': keywords}
def giveKeyword(text):
from bs4 import BeautifulSoup
text = BeautifulSoup(text,"lxml").get_text()
from nltk.tokenize import RegexpTokenizer
tokenizer = RegexpTokenizer(r'\w+')
text = tokenizer.tokenize(text)
#print text
cleanText = "".join([" " + i if not i.startswith("'") and i not in string.punctuation else i for i in text]).strip()
rakeobj = Rake("SmartStoplist.txt")
keywords = rakeobj.run(cleanText)
output = ""
#take top two highest ranked (if there even are two)
for keyword in keywords[0:2]:
output = output + keyword[0] + ",";
return output #the highest ranked one...
class Analyzer:
'''analyzes text for sentiment and important terms'''
def __init__(self):
self.filter = Rake('stoplist.txt')
def sentiment(self, text):
'''transform sentiment into trinary value'''
polarity = TextBlob(text).sentiment.polarity
if polarity > 0.2:
sentiment = "1"
elif polarity < -0.2:
sentiment = "-1"
else:
sentiment = "0"
return sentiment
def terms(self, text):
'''get most important terms from text'''
if text:
terms = self.filter.run(text)[0][0]
else:
terms = ''
return terms
def get_doc_keywords(html, articleDom):
'''
Search meta keyword tag for any predefined keywords
Else use RAKE library to extract keywords from document content
Return first five keywords
'''
tree = fromstring(html)
keywords = tree.xpath('//meta[@name="keywords"]/@content')
if keywords:
arr = keywords.split(',')[:5] # return first five keywords
return [x.strip(' ') for x in arr]
else:
# Use RAKE to extract keywords from article contetnt
from RAKE import Rake
import operator
node = fromstring(articleDom)
text = node.text_content()
extractor = Rake(
"RAKE/stoplists/SmartStoplist.txt", 3, 3,
5) # min 3 chars, max 3 words, word appears min 5 times
keywords = [x[0] for x in extractor.run(text)]
keywords = keywords[:5] # get top five
return [x.strip(' ') for x in keywords]
def get_keyword(text):
rake = Rake("SmartStoplist.txt")
if text == "":
return ""
keywords = rake.run(text)
return keywords[0][0]
def generate_titles(file_name,
random=False,
use_rake=False,
use_summa_text_rank=False,
use_text_rank=False):
logger.info("Opening file")
text_file = open(file_name)
logger.info("Reading file")
raw_text = text_file.read().lower()
# Remove Unicode characters.
raw_text = raw_text.decode('unicode_escape').encode('ascii', 'ignore')
#Convert raw text to word tokens
logger.info("Tokenizing")
tokens = nltk.word_tokenize(raw_text.translate(None, string.punctuation))
#Remove stopwords
logger.info("Removing stopwords")
stop_words = set(stopwords.words('english'))
#NOTE: we need to include some more stopwords, as 'english' doesn't contain some stopwords
# related to journal articles (e.g., "et" and "al" in "et al.")
stop_words.update(ADDITIONAL_STOPWORDS)
filtered_text = [word for word in tokens if word not in stop_words]
#Create Corpus object for input text
logger.info("Creating corpus object")
input_text = Corpus(raw_text, tokens, filtered_text)
input_text.stop_words = stop_words
logger.info("Filtered words to use")
logger.info("\t %s" % input_text.filtered_tokens[:5])
#NOTE: stopwords are removed before POS tags assigned, this could
# potentially degrade POS tagging performance - may want to
# switch this order
#Demonstrate functions
logger.info("Getting POS tags")
input_text.pos_tags = pos_tagger(input_text)
logger.info("\t %s" % input_text.pos_tags[:5])
logger.info("Finding all used parts of speech.")
input_text.used_pos = set([tag[1] for tag in input_text.pos_tags])
logger.info(input_text.used_pos)
logger.info("Getting stemmed words")
input_text.stemmed_words = stem_tokens(input_text)
logger.info("\t %s" % input_text.stemmed_words[:5])
# split the stemmed words into ~equal-sized groups
logger.info("Splitting the stemmed words into groups")
#logger.info("There are %s words in this group" % len(input_text.stemmed_words))
num_splits = 2
input_text.splits = split_tokens(input_text, num_splits)
#for s in input_text.splits:
# logger.info("%s %s\n\n" % (s,len(s)))
logger.info("Getting word frequency and proximity")
cutoff = 0.125
if len(input_text.filtered_tokens) < 250:
cutoff = 0.35 #33
input_text.word_freq_proximity = stems_frequency_proximity(
input_text, cutoff)
#logger.info("\t %s" % (input_text.word_freq_proximity[u'becom'],))
logger.info("Mapping filtered words and their stemmed forms")
input_text.filtered_word_and_bases, input_text.filtered_bases_and_words = stems_and_bases(
input_text)
#logger.info("\t %s" % input_text.filtered_word_and_bases[u'becom'])
logger.info("Mapping POS tags and words")
input_text.pos_tag_and_words = pos_tags_and_words(input_text)
#logger.info("\t %s" % input_text.pos_tag_and_words['NNS'][:5])
logger.info("------ End Processing ------\n\n")
##########################
if use_rake:
logger.info("------ Begin Rake ------")
"""More information at: https://github.com/fabianvf/python-rake"""
r = Rake(RAKE.SmartStopList()) #stop_words_list)
sorted_keywords = r.run(input_text.raw_text)
logger.info("Sorted keywords: %s" % sorted_keywords[:5])
logger.info("------ End Rake ------\n\n")
if use_summa_text_rank:
logger.info("------ Begin SummaTextRank ------")
"""More information at https://github.com/summanlp/textrank"""
logger.info("Sentence(s) summary: %s" % summarizer.summarize(raw_text))
logger.info("Keywords: %s" % keywords.keywords(raw_text))
logger.info("------ End SummaTextRank ------\n\n")
if use_text_rank:
logger.info("------ Begin TextRank ------")
"""More information at https://github.com/davidadamojr/TextRank"""
logger.info("Sentence(s) summary: %s " %
textrank.extract_sentences(raw_text))
logger.info("Keywords: %s" % textrank.extract_key_phrases(raw_text))
logger.info("------ End TextRank ------\n\n")
##########################
logger.info("------ Begin Weighting ------")
logger.info("Calculating word weights")
input_text.word_weights = get_word_weights(input_text, random)
logger.info("Printing word weights")
weight_thresh = -1
print_words_with_weight_above(weight_thresh, input_text.word_weights,
input_text)
logger.info("------ End Weighting ------\n\n")
##########################
logger.info("------ Begin Building ------")
titles = build_titles(input_text)
logger.info("------ End Building ------\n\n")
##########################
logger.info("Closing file")
text_file.close()
##########################
logger.info("------ Begin Ranking ------")
#NOTE: the scores denote the title rankings relative to one another
# 1 denotes the title with the highest rank and 0 denotes the
# title with the lowest rank (determined by a combination of
# summed word weights and average word weight)
titles_ranked = order_titles(titles, input_text)
logger.info("------ End Ranking ------\n\n")
##########################
return titles_ranked
import csv
from RAKE import Rake
import email
import os
base = os.getcwd() + '/Data_set'
topic_identifier_instance = Rake('Stop_list.txt')
for folder in os.listdir(base + '/Data_set'):
fold = base + '/Data_set/{}'.format(folder)
for file in os.listdir(fold):
mail = email.message_from_file(open(fold + '/{}'.format(file)))
message_string = mail.get_payload()
score_table = topic_identifier_instance.run(message_string)
score_table.insert(0, ('topic', 'word_score'))
print(score_table)
writer = csv.writer(
open(
base + '/Result_data_set' + '/' + folder + '/' + file + '.csv',
'w+'))
for row in score_table:
writer.writerow(row)