【PYTHON】Remove punctuation and numbers and most common words

 #### Remove punctuation and numbers.

import string

translator = str.maketrans('', '', string.punctuation + string.digits)

text = text.translate(translator)

text[:100]

import nltk

nltk.download('stopwords')

from nltk.corpus import stopwords

en_stopwords = stopwords.words('english')

print(en_stopwords[:10])

en_stopwords = set(en_stopwords)

words = text.lower().split()

words[:10]

words = [w for w in words if w not in en_stopwords and len(w) > 3]

words[:10]

bigrams = list([' '.join(bg) for bg in nltk.bigrams(words)])

bigrams[:3]

ug_fdist = nltk.FreqDist(words)

bg_fdist = nltk.FreqDist(bigrams)

ug_fdist.most_common(20)

bg_fdist.most_common(20)

import matplotlib.pyplot as plt

ax = ug_fdist.plot(20)

bg_fdist.plot(20)