Example usage

To use pytextprep in a project:

Imports

import re
from pytextprep.extract_ngram import extract_ngram
from pytextprep.extract_hashtags import extract_hashtags
from pytextprep.remove_punct import remove_punct
from pytextprep.generate_cloud import generate_cloud
import pytextprep
import matplotlib.pyplot as plt

Create list of Tweets

tweets_list = [
    "hello literally everyone",
    "hello #America!",
    "Make America Great Again! @DonalTrump", 
    "It's a new day in #America"]

Remove punctuation

cleaned_tweets = remove_punct(tweets_list, skip=["'", "@", "#", '-'])
cleaned_tweets

['hello literally everyone',
 'hello #America',
 'Make America Great Again @DonalTrump',
 "It's a new day in #America"]

Extract ngrams

extract_ngram(cleaned_tweets, n=3)

['hello literally everyone',
 'literally everyone hello',
 'everyone hello #America',
 'hello #America Make',
 '#America Make America',
 'Make America Great',
 'America Great Again',
 'Great Again @DonalTrump',
 "Again @DonalTrump It's",
 "@DonalTrump It's a",
 "It's a new",
 'a new day',
 'new day in',
 'day in #America']

Extract hashtags

extract_hashtags(tweets=tweets_list)

['America', 'America']

Generate word cloud

fig, wc = generate_cloud(tweets_list)
plt.show()

[nltk_data] Downloading package stopwords to /home/docs/nltk_data...
[nltk_data]   Unzipping corpora/stopwords.zip.