wordfreq | word frequencies , in various natural languages | Natural Language Processing library

def tokenize(lines):
    words = []
    for line in lines:
        line = line.strip()
        start = 0
        while start < len(line):

            while start < len(line) and line[start].isspace():
                start = start +

from collections import Counter
bigLst = [['hello', 'my', 'friend'], ['jim', 'is', 'cool'], ['peter', 'is', 'nice']]
print(Counter([word for lst in bigLst for word in lst]))

Counter({'is': 2, 'hello': 1, 'my': 1, '

from nltk.corpus import indian
from collections import defaultdict

sentence_score=defaultdict(int)
#word=nltk.word_tokenize(text)
for sent in sentences:
    word_count_in_sentence = (len(nltk.word_tokenize(sentence)))
    if word in wordf

from collections import defaultdict
words = ['ab','absa','sbaa','basa','ba']
wordToAnagram= defaultdict(list) 
# word vs list anagram 
# loop below will create {aabs:  ['absa', 'sbaa', 'basa']}
for word in words:
    s = "".join(sorted(wor

>>> df = pd.DataFrame.from_dict(word_freq, orient='index')
>>> df = df.rename(columns={0: 'WordFreq'})
>>> df.index.name = 'Word'
>>> df
         WordFreq
Word
france          2
spain           3
beaches

from collections import Counter


text_list = ['france', 'spain', 'spain beaches', 'france beaches', 'spain best beaches']

counter_dict = Counter([split_word for word in text_list for split_word in word.split()]
#Counter({'france': 2, 'sp

from collections import Counter

def represent(group):
    groupWords = [ expr.split(" ") for expr in group ]
    wordFreq   = Counter(word for words in groupWords for word in words)
    weights    = [ sum(wordFreq[word] for word in words)

>>> WordCloud().process_text('penn penn penn penn penn state state state state uni uni uni college college university states vice president vice president vice president vice president vice president vice president vice president'

import string
from collections import Counter
txt = "Why's it always the nice guys?"

counted = Counter(
    word if not word[-1] in string.punctuation else word[:-1] for word in txt.split()
)
print(counted)

>>> Counter({"Why's":