def removestop(text):
text = re.sub(r"[^A-Za-z0-9^,!.\/'+-=]", " ", text)
text = text.lower().split()
stops = ['so', 'his', 't', 'y', 'ours', 'herself', 'your', 'all',
'some', 'they', 'i', 'of', 'didn',
'them', 'when', 'will', 'that', 'its', 'because',
'while', 'those', 'my', 'don', 'again', 'her', 'if',
'further', 'now', 'does', 'against', 'won', 'same',
'a', 'during', 'who', 'here', 'have', 'in', 'being',
'it', 'other', 'once', 'itself', 'hers', 'after', 're',
'just', 'their', 'himself', 'theirs', 'whom', 'then', 'd',
'out', 'm', 'mustn', 'where', 'below', 'about', 'isn',
'shouldn', 'wouldn', 'these', 'me', 'to', 'doesn', 'into',
'the', 'until', 'she', 'am', 'under', 'how', 'yourself',
'couldn', 'ma', 'up', 'than', 'from', 'themselves', 'yourselves',
'off', 'above', 'yours', 'having', 'mightn', 'needn', 'on',
'too', 'there', 'an', 'and', 'down', 'ourselves', 'each',
'hadn', 'ain', 'such', 've', 'did', 'be', 'or', 'aren', 'he',
'should', 'for', 'both', 'doing', 'this', 'through', 'do', 'had',
'own', 'but', 'were', 'over', 'not', 'are', 'few', 'by',
'been', 'most', 'no', 'as', 'was', 'what', 's', 'is', 'you',
'shan', 'between', 'wasn', 'has', 'more', 'him', 'nor',
'can', 'why', 'any', 'at', 'myself', 'very', 'with', 'we',
'which', 'hasn', 'weren', 'haven', 'our', 'll', 'only',
'o', 'before']
text = [w for w in text if not w in stops]
text = " ".join(text)
text = text.replace("."," ").replace(","," ")
return(text)
def transform_review_text(text):
text = text.lower()
text = re.sub('[^a-z ]', '', text)
text_array = [
stemmer.stem(word) for word in text.split() if word not in stopwords
]
return ' '.join(text_array)
def clean_text_round1(text):
'''Make text lowercase, remove punctuation, mentions, hashtags and words containing numbers.'''
# make text lowercase
text = text.lower()
# removing text within brackets
text = re.sub('\[.*?\]', '', text)
# removing text within parentheses
text = re.sub('\(.*?\)', '', text)
# removing numbers
text = re.sub('\w*\d\w*', '', text)
# if there's more than 1 whitespace, then make it just 1
text = re.sub('\s+', ' ', text)
# if there's a new line, then make it a whitespace
text = re.sub('\n', ' ', text)
# removing any quotes
text = re.sub('\"+', '', text)
# removing &
text = re.sub('(\&\;)', '', text)
# removing any usernames
text = re.sub('(@[^\s]+)', '', text)
# removing any hashtags
text = re.sub('(#[^\s]+)', '', text)
# remove `rt` for retweet
text = re.sub('(rt)', '', text)
# string.punctuation is a string of all punctuation marks
# so this gets rid of all punctuation
text = re.sub('[%s]' % re.escape(string.punctuation), '', text)
# getting rid of `httptco`
text = re.sub('(httptco)', '', text)
return text
def predict():
# Prediction text
text = request.args.get('text') if request.args.get('text') else ""
# Split text using non alpha numeric, then remove stopwords
text = ' '.join(
[i for i in re.split('[^a-z0-9]', text.lower()) if i not in stop])
# Number of predictions
predictions = int(
request.args.get('num')) if request.args.get('num') else 3
retval = dict()
slicing_value = -1 * (predictions + 2)
cat_train.insert(0, text)
tfidf = TfidfVectorizer(max_df=0.4,
min_df=2,
stop_words='english',
norm='l1',
use_idf=True).fit_transform(cat_train)
cosine_similarities = linear_kernel(tfidf[0:1], tfidf).flatten()
related_docs_indices = cosine_similarities.argsort()[-2:slicing_value:-1]
for index, x in enumerate(list(related_docs_indices)):
cos_value = list(cosine_similarities)[x]
if cos_value > 0:
retval[category[x - 1]] = str(cos_value)
del cat_train[0]
response = jsonify(retval)
response.headers.add('Access-Control-Allow-Origin', CORS)
#response.headers.add('Access-Control-Allow-Origin', 'https://dashboard.heroku.com/apps/bazarr-web')
return response
def preProcess(text):
text = text.lower()
tokenizer = RegexpTokenizer(r'\w+')
tokens = tokenizer.tokenize(text)
filtered_words = [w for w in tokens if not w in stopwords.words('english') and not w.isdigit()]
print "preprocess:" + " ".join(filtered_words)
return " ".join(filtered_words)
def clean_text_round1(text):
'''Make text lowercase, remove text in square brackets, remove punctuation and remove words containing numbers.'''
text = text.lower()
text = re.sub('\[.*?\]', '', text)
text = re.sub('[%s]' % re.escape(string.punctuation), '', text)
text = re.sub('\w*\d\w*', '', text)
return text
def clean_text(self):
text = re.sub('[^a-zA-z]', ' ', str(self.doc))
text = re.sub('\[.*?\]', ' ', text)
text = re.sub('\d', ' ', text)
text = " ".join(text.split())
text = text.lower()
return text
def clean_lowercase(text):
# remove nan values
if str(text) == 'nan':
text = re.sub('nan', '', str(text))
else:
text = text.lower()
return text
def MyNormalize(text):
tokens = nltk.word_tokenize(text.lower())
tokens = [t for t in tokens if t not in string.punctuation]
toks = [
WNL.lemmatize(t) if t not in exceptions else t for t in tokens
]
return toks
def ProcessText(text):
"""
processes either a string or list of tokenized words
"""
if isinstance((text), (str)):
# remove non-word characters and lower the letters
text = re.sub(r"<[^>]*>", r"", text)
text = re.sub(r"#(\w+)", "", text)
text = re.sub(r"@", "", text)
text = re.sub(r"[^a-zA-Z0-9\s]+", r"", text.lower())
# remove url strings from text
text = RemoveUrl(text)
# remove extra spaces
text = re.sub(r"^ +", r"", text)
text = re.sub(r" +", r" ", text)
return text
if isinstance((text), (list)):
return_list = []
for i in range(len(text)):
# remove non-word characters and lower the letters
temp_text = re.sub(r"<[^>]*>", r"", text[i])
temp_text = re.sub(r"#(\w+)", "", temp_text)
temp_text = re.sub(r"@", "", temp_text)
temp_text = re.sub(r"[^a-zA-Z0-9\s]+", r"", temp_text.lower())
# remove url strings from text
temp_text = RemoveUrl(temp_text)
# remove extra spaces
temp_text = re.sub(r"^ +", r"", temp_text)
temp_text = re.sub(r" +", r" ", temp_text)
return_list.append(temp_text)
return return_list
else:
pass
def textClean(text):
text = re.sub(r"[^A-Za-z0-9^,!.\/'+-=]", " ", text)
text = text.lower().split()
# May change here (remove all the stop words)
stops = set(my_stop_words)
text = [w for w in text if not w in stops]
text = " ".join(text)
return(text)
def clean_text(text):
'''Make text lowercase, remove text in square brackets, remove punctuation and remove words containing numbers.'''
text = text.lower()
text = re.sub('\[.*?\]', '', text)
text = re.sub('[%s]' % re.escape(string.punctuation), '', text)
text = re.sub('\w*\d\w*', '', text)
'''Get rid of some additional punctuation and nonsensical text that was missed the first time around.'''
text = re.sub('[‘’“”…]', '', text)
text = re.sub('\n', '', text)
return text
def generate_spelling_graph(text):
text = text.lower()
text = remove_punct(text)
text = tokenizing(text)
text = remove_stopwords(text)
misspelled = spell.unknown(text)
sizes = [len(text)-len(misspelled), len(misspelled)]
labels = 'correctly spelled words', 'misspelled words'
generate_pie_chart(sizes, labels)
generate_bar_chart(text, misspelled, "Occurance")
def sentimentAFINN(text):
words = pattern_split.split(text.lower())
sentiments = map(lambda word: afinn.get(word, 0), words)
if sentiments:
sentiment = float(sum(sentiments))/math.sqrt(len(sentiments))
else:
sentiment = 0
return sentiment
def initial_clean(text):
"""
Function to clean text-remove punctuations, lowercase text etc.
"""
# remove_digits and special chars
text = re.sub("[^a-zA-Z ]", "", text)
text = text.lower() # lower case text
text = nltk.word_tokenize(text)
return text
def clean_text_round1(text):
'''Make text lowercase, remove text in square brackets, remove punctuation and remove words containing numbers.'''
text = text.lower()
#print('text after changing to lower case:- %s' %(text))
text = re.sub('\[.*?\]', '', text) # removes brackets.
text = re.sub('[%s]' % re.escape(string.punctuation), '',
text) # removes punctuation markes from a string.
text = re.sub(
'\w*\d\w*', '', text
) # \w* means remove numbers from a string \d removes digitis from string.
return text
def clean_text_round1(text):
'''Make text lowercase, remove text in square brackets, remove punctuation and remove words containing numbers.'''
text = text.lower()
text = text.replace('-', ' ')
text = text.replace("’s ", " ").replace("' ", " ")
text = text.replace("s’ ", " ").replace("s' ",
" ") #remove proper possesives
text = re.sub('\[.*?\]', '', text)
text = re.sub('[%s]' % re.escape(string.punctuation), '', text)
text = re.sub('\w*\d\w*', '', text)
return text
def process_text(text):
doc = nlp(text.lower())
result = []
for token in doc:
if token.text in nlp.Defaults.stop_words:
continue
if token.is_punct:
continue
if token.lemma_ == '-PRON-':
continue
result.append(token.lemma_)
return " ".join(result)
def clean_data(text):
""" Clean data part 1: Lower case, """
text = text.lower()
text = re.sub('[%s]' % re.escape(string.punctuation), '', text)
text = re.sub('\w*\d\w*', '', text)
text = re.sub('[‘’“”…]', '', text)
text = re.sub('\n', ' ', text)
text = re.sub('\t', '', text)
text = re.sub('\b', '', text)
text = re.sub('[^a-z ]+', '', text)
text = re.sub('\s\s+', ' ', text)
return text
def process(text, tokenizer=TweetTokenizer(), stopwords=[]):
"""Process the text of a tweet:
- Lowercase
- Tokenize
- Stopword removal
- Digits removal
Return: list of strings
"""
text = text.lower()
tokens = tokenizer.tokenize(text)
return [tok for tok in tokens if tok not in stopwords and not any(i.isdigit() for i in tok) and len(tok)>2 and tok is tok.strip('#') and tok is tok.strip('@') and tok not in (tok for tok in tokens if re.search('http', tok)) ]
def prepare_text(text):
tweet_text = []
try:
tokens = nltk.word_tokenize(text.lower())
clean_tokens = [word for word in tokens if word not in stopwords]
stem_words = [stemmer.stem(token) for token in clean_tokens]
tweet_text.append(" ".join(stem_words))
X_test = tf_vect.transform(tweet_text)
except Exception:
pass
return X_test
def sentimentAFINN(text):
"""
Returns a float for sentiment strength based on the input text.
Positive values are positive valence, negative value are negative valence.
"""
words = pattern_split.split(text.lower())
sentiments = map(lambda word: afinn.get(word, 0), words)
if sentiments:
# How should you weight the individual word sentiments?
# You could do N, sqrt(N) or 1 for example. Here I use sqrt(N)
sentiment = float(sum(sentiments))/math.sqrt(len(sentiments))
else:
sentiment = 0
return sentiment
def preprocessing(text):
if type(text) == pd.Series:
text = [entry.lower() for entry in text]
text = [remove_punct(entry) for entry in text]
text = [tokenizing(entry) for entry in text]
text = [remove_stopwords(entry) for entry in text]
text = [lemmatizing(entry) for entry in text]
text = [" ".join(entry) for entry in text]
elif type(text) == str:
text = text.lower()
text = remove_punct(text)
text = tokenizing(text)
text = remove_stopwords(text)
text = lemmatizing(text)
text = " ".join(text)
return text
def cleaner(
text,
):
filters_regex = r'(?!\')(?:\W|_)'
clean_text = re.sub(
pattern=filters_regex,
repl=' ',
string=text.lower(),
)
clean_text = re.sub(
pattern=r'\s+',
repl=' ',
string=clean_text,
)
return clean_text
def clean_text(text):
'''
Parameters:
ing
Returns:
String
This function does the following process on the text:
convert to lowercase
removes punctuation
removes special characters
'''
'''
New implementation to remove the punctuation and replace with space
Ref: https://stackoverflow.com/questions/42614458/how-to-replace-punctuation-with-whitespace
'''
punc_list = list(string.punctuation)
translator = text.maketrans(dict.fromkeys(punc_list, " "))
cleantext = text.lower().translate(translator)
## clear off numbers and normalize spaces between words
## and lowercase it
cleantext = " ".join(
[s for s in cleantext.split(" ") if s.strip() is not ""]).lower()
## remove any non-printable (non-ascii) characters in the text
printable = set(string.printable)
cleantext = list(filter(lambda x: x in printable, cleantext))
cleantext = "".join(cleantext)
## remove roman numberals from string which
## are not in brackets
toremove = [
' ii ', ' iii ', ' iv ', ' v ', ' vi ', ' vii ', ' viii ', ' ix ',
' x ', '!', '@', '#', '$', '%', '^', '&', '*', '$.'
]
text_array = cleantext.split("\s+")
cleantext = [word.strip() for word in text_array if word not in toremove]
cleantext = " ".join(cleantext)
## clear off all arabic numerals / digits in the text which are attached
## together with text
numbers = [1]
while (len(numbers) != 0):
numbers = re.findall('\d+', cleantext)
for number in numbers:
cleantext = cleantext.replace(number, " ")
cleantext = re.sub(' +', ' ', cleantext)
return cleantext.strip()
def get_parts(text):
nouns = set()
descriptives = set()
text = text.lower().split()
text = [i for i in text if i not in stop]
text = [i for i in text if i not in punctuation]
text = [i for i in text if len(i) > 1]
for word, pos in nltk.pos_tag(
text
): # remove the call to nltk.pos_tag if `sentence` is a list of tuples as described above
if pos in ['NN', "NNP"]: # feel free to add any other noun tags
nouns.add(word)
elif pos in ["JJ", "JJR"]:
descriptives.add(word)
return list(nouns), list(descriptives)
def tokenize_text(text):
text = text.lower()
text = re.sub(r"http\S+", "", text)
text = text.translate(string.punctuation)
words = nltk.word_tokenize(text)
words = [re.sub("[^A-Za-z0-9]", "", word) for word in words]
final_words = []
for word in words:
if not word:
continue
if word in nltk.corpus.stopwords.words("english"):
continue
if word.startswith("@") or word.startswith("#"):
continue
if word.isnumeric():
continue
final_words.append(word)
return final_words
def clean_text(text, remove_stop_words=False):
text = text.lower()
replace_punctuation = str.maketrans(string.punctuation,
' ' * len(string.punctuation))
text = text.translate(replace_punctuation)
text = re.sub(r'\s+', ' ', text)
text = re.sub('[\n\r]', '', text)
if remove_stop_words == True:
text = text.split()
new_text = []
stemmer = PorterStemmer()
for word in text:
if word not in STOPWORDS:
new_text.append(stemmer.stem(word))
text = ' '.join(new_text)
return text
def clean_text(text, country):
text = reduce(lambda a, kv: a.replace(*kv), contractions.items(),
text.lower())
text = text.replace('\t', ' ').replace('\n', ' ').replace('\r', ' ')
text = strip_accents(text)
text = text.translate(
str.maketrans(string.punctuation, ' ' * len(string.punctuation)))
tokens = tk.tokenize(text)
if country == 'USA':
stopwords = usa_stopwords
elif country == 'Canada':
stopwords = canada_stopwords
elif country == 'UK':
stopwords = britain_stopwords
else:
raise ValueError("Country is invalid.")
tokens = [
w for w in tokens
if w not in stopwords and len(w) > 2 and w != ' ' and not w.isdigit()
]
return ' '.join(tokens)
def postTags():
retval = {'tags': []}
text = re.sub('%20', ' ',
request.args.get('text')) if request.args.get('text') else ""
# Remove characters that are not punctuations, numbers and alphabets
text = re.sub('[^a-zA-Z0-9\s.?!-]', '', text)
# Remove extra spaces and tabs
text = re.sub('[\s+]', ' ', text)
print(text)
blob = TextBlob(text.lower())
temp = blob.tags
for i in range(len(temp)):
if temp[i][1] == 'JJ':
k = 1
found = ''
while i + k < len(temp) and k < 2:
if temp[i + k][1] == 'NN' or temp[i + k][1] == 'NNP':
retval['tags'].append(
string.capwords(temp[i][0] + ' ' + temp[i + k][0]))
temp[i + k] = (temp[i + k][0], 'DONE')
break
k += 1
for i in range(len(temp)):
if temp[i][
1] == 'NNP' or temp[i][1] == 'VBN' and temp[i][0] not in stop:
retval['tags'].append(string.capwords(temp[i][0].lemmatize()))
retval['tags'] = list(set(retval['tags']))
response = jsonify(retval)
response.headers.add('Access-Control-Allow-Origin', CORS)
return (response)
def tokenize_and_stem(text):
return stem(text.lower().split(" "))
def normalizeWords(self, text):
return re.compile(r'\W+', re.UNICODE).split(text.lower())
