def classifyEmoticons(text):
# find all emoticons
emoticons = EMOTICON_RE.findall(text)
pos = any([emo in POS_EMOTICONS
for emo in emoticons]) or bool(POS_EMOJIS_RE.search(text))
neg = any([emo in NEG_EMOTICONS
for emo in emoticons]) or bool(NEG_EMOJIS_RE.search(text))
if pos and neg:
return 'N/A'
elif pos and not neg:
return 'pos'
elif neg and not pos:
return 'neg'
elif not pos and not neg:
return None
def emoticonList(corpus):
emolist = []
emocount = []
emoTorF = []
for a in corpus:
ct = [] # store count
TorF = [] # possive or negative
all_emoticons = EMOTICON_RE.findall(a)
ct.append(len(all_emoticons))
if (len(all_emoticons) != 0):
ed = EmoticonDetector()
all_emoticons.sort()
tf = (-1, 1)[ed.is_positive(all_emoticons[0])]
TorF.append(tf)
else:
TorF.append(0)
emolist.append(all_emoticons)
emocount.append(ct)
emoTorF.append(TorF)
return emocount, emoTorF, emolist
def json2csv_preprocess(json_file,
outfile,
fields,
encoding='utf8',
errors='replace',
gzip_compress=False,
skip_retweets=True,
skip_tongue_tweets=True,
skip_ambiguous_tweets=True,
strip_off_emoticons=True,
remove_duplicates=True,
limit=None):
"""
Convert json file to csv file, preprocessing each row to obtain a suitable
dataset for tweets Semantic Analysis.
:param json_file: the original json file containing tweets.
:param outfile: the output csv filename.
:param fields: a list of fields that will be extracted from the json file and
kept in the output csv file.
:param encoding: the encoding of the files.
:param errors: the error handling strategy for the output writer.
:param gzip_compress: if True, create a compressed GZIP file.
:param skip_retweets: if True, remove retweets.
:param skip_tongue_tweets: if True, remove tweets containing ":P" and ":-P"
emoticons.
:param skip_ambiguous_tweets: if True, remove tweets containing both happy
and sad emoticons.
:param strip_off_emoticons: if True, strip off emoticons from all tweets.
:param remove_duplicates: if True, remove tweets appearing more than once.
:param limit: an integer to set the number of tweets to convert. After the
limit is reached the conversion will stop. It can be useful to create
subsets of the original tweets json data.
"""
with codecs.open(json_file, encoding=encoding) as fp:
(writer, outf) = outf_writer_compat(outfile, encoding, errors,
gzip_compress)
# write the list of fields as header
writer.writerow(fields)
if remove_duplicates == True:
tweets_cache = []
i = 0
for line in fp:
tweet = json.loads(line)
row = extract_fields(tweet, fields)
try:
text = row[fields.index('text')]
# Remove retweets
if skip_retweets == True:
if re.search(r'\bRT\b', text):
continue
# Remove tweets containing ":P" and ":-P" emoticons
if skip_tongue_tweets == True:
if re.search(r'\:\-?P\b', text):
continue
# Remove tweets containing both happy and sad emoticons
if skip_ambiguous_tweets == True:
all_emoticons = EMOTICON_RE.findall(text)
if all_emoticons:
if (set(all_emoticons) & HAPPY) and (set(all_emoticons)
& SAD):
continue
# Strip off emoticons from all tweets
if strip_off_emoticons == True:
row[fields.index('text')] = re.sub(
r'(?!\n)\s+', ' ', EMOTICON_RE.sub('', text))
# Remove duplicate tweets
if remove_duplicates == True:
if row[fields.index('text')] in tweets_cache:
continue
else:
tweets_cache.append(row[fields.index('text')])
except ValueError:
pass
writer.writerow(row)
i += 1
if limit and i >= limit:
break
outf.close()
def json2csv_preprocess(json_file, outfile, fields, encoding='utf8', errors='replace',
gzip_compress=False, skip_retweets=True, skip_tongue_tweets=True,
skip_ambiguous_tweets=True, strip_off_emoticons=True, remove_duplicates=True,
limit=None):
"""
Convert json file to csv file, preprocessing each row to obtain a suitable
dataset for tweets Semantic Analysis.
:param json_file: the original json file containing tweets.
:param outfile: the output csv filename.
:param fields: a list of fields that will be extracted from the json file and
kept in the output csv file.
:param encoding: the encoding of the files.
:param errors: the error handling strategy for the output writer.
:param gzip_compress: if True, create a compressed GZIP file.
:param skip_retweets: if True, remove retweets.
:param skip_tongue_tweets: if True, remove tweets containing ":P" and ":-P"
emoticons.
:param skip_ambiguous_tweets: if True, remove tweets containing both happy
and sad emoticons.
:param strip_off_emoticons: if True, strip off emoticons from all tweets.
:param remove_duplicates: if True, remove tweets appearing more than once.
:param limit: an integer to set the number of tweets to convert. After the
limit is reached the conversion will stop. It can be useful to create
subsets of the original tweets json data.
"""
with codecs.open(json_file, encoding=encoding) as fp:
(writer, outf) = outf_writer_compat(outfile, encoding, errors, gzip_compress)
# write the list of fields as header
writer.writerow(fields)
if remove_duplicates == True:
tweets_cache = []
i = 0
for line in fp:
tweet = json.loads(line)
row = extract_fields(tweet, fields)
try:
text = row[fields.index('text')]
# Remove retweets
if skip_retweets == True:
if re.search(r'\bRT\b', text):
continue
# Remove tweets containing ":P" and ":-P" emoticons
if skip_tongue_tweets == True:
if re.search(r'\:\-?P\b', text):
continue
# Remove tweets containing both happy and sad emoticons
if skip_ambiguous_tweets == True:
all_emoticons = EMOTICON_RE.findall(text)
if all_emoticons:
if (set(all_emoticons) & HAPPY) and (set(all_emoticons) & SAD):
continue
# Strip off emoticons from all tweets
if strip_off_emoticons == True:
row[fields.index('text')] = re.sub(r'(?!\n)\s+', ' ', EMOTICON_RE.sub('', text))
# Remove duplicate tweets
if remove_duplicates == True:
if row[fields.index('text')] in tweets_cache:
continue
else:
tweets_cache.append(row[fields.index('text')])
except ValueError:
pass
writer.writerow(row)
i += 1
if limit and i >= limit:
break
outf.close()
i = 0
url_re = re.compile(URLS, re.VERBOSE | re.I | re.UNICODE)
hashtag_re = re.compile('(?:^|\s)[＃#]{1}(\w+)', re.UNICODE)
#mention_re = re.compile('(?:^|\s)[＠@]{1}([^\s#<>[\]|{}]+)', re.UNICODE) # To include more complete names
mention_re = re.compile('(?:^|\s)[＠@]{1}(\w+)', re.UNICODE)
with open(text_file, 'r') as text_reader, open(
words_file, 'w', encoding='utf-8') as words_writer, open(
emo_file, 'w', encoding='utf-8') as emo_writer, open(
hash_file, 'w', encoding='utf-8') as hash_writer, open(
at_file, 'w', encoding='utf-8') as at_writer, open(
link_file, 'w', encoding='utf-8') as link_writer:
for line in text_reader:
line = line.rstrip().lower()
hashs = hashtag_re.findall(line)
ats = mention_re.findall(line)
links = url_re.findall(line)
line = clean(line, hashs, ats, links)
emoticons = emo_re.findall(line)
emojis = [w for w in line if w in emoji.UNICODE_EMOJI]
words = re.findall('[a-záéíóúñ][a-záéíóúñ_-]+',
line) #Revisar para remover ats, hashs y links
words_writer.write(' '.join(w for w in words) + '\n')
emo_writer.write(' '.join(w for w in emoticons + emojis) + '\n')
hash_writer.write(' '.join(w for w in hashs) + '\n')
at_writer.write(' '.join(w for w in ats) + '\n')
link_writer.write(' '.join(w for w in links) + '\n')
i += 1
print(i)