words_frequecy_pt.py

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Thu Jan 31 15:41:46 2019

@author: boaretto
"""
from string import digits
from nltk import ngrams, FreqDist
from nltk.corpus import stopwords
from collections import Counter

def words_frequency_pt(text):
    # Clean punctuaction and lower text
    for char in '-.,\n#':
        text=text.replace(char, ' ')
    text = text.lower()

    # Remove digits
    remove_digits = str.maketrans('', '', digits)
    text = text.translate(remove_digits)
    words_list = text.split()

    #Remove stop words
    stop_words = stopwords.words('portuguese')
    stop_words.append('é')
    stop_words.append('ter')
    filtered_text = [w for w in words_list if not w in stop_words] 
    
    return Counter(filtered_text).most_common()