mlai-demo

import os
fpath = os.getcwd(); fpath

mlai-demo

from google.colab import files

uploaded = files.upload()

for fn in uploaded.keys():
    print('User uploaded file "{name}" with length {length} bytes'.format(
      name=fn, length=len(uploaded[fn])))
  
# Click Files tab - the uploaded file(s) will be there

mlai-demo

import string
from nltk.tokenize import word_tokenize
nltk.download('punkt') #need if using Google Colab
import matplotlib.pyplot as plt
%matplotlib inline

with open(fpath + '/Plutarch.txt') as f, open(fpath + '/Plutarch_tokens.txt', 'w') as out_f:
    text = f.read()
    tokens = word_tokenize(text)
    tokens = [w.lower() for w in tokens]

mlai-demo

bigrams = nltk.bigrams(words)
freq_bigrams = nltk.FreqDist(bigrams)

plt.figure(figsize=(13, 7))
freq_bigrams.plot(20)

mlai-demo

from nltk.stem.porter import PorterStemmer
with open(fpath + '/Plutarch_tokens.txt') as f, open(fpath + '/Plutarch_stem.txt', 'w') as out_f:
    text = f.read()
    tokens = word_tokenize(text)
    porter = PorterStemmer()
    stemmed = [porter.stem(word) for word in tokens]
    print(stemmed[:100])
    new_stem_text = ' '.join(stemmed)
    fd_stemmed = nltk.FreqDist(stemmed)
    out_f.write(new_stem_text)

mlai-demo

unique = set(words)
print("The tokenized text is {} words long, has {} unique words and {} letters on average".format
      (len(words), len(unique), round(sum(len(word) for word in words)/len(words),2)))
      

mlai-demo

import pandas as pd
from wordcloud import WordCloud
import matplotlib.pyplot as plt  
from os import path

d = path.dirname(__file__) if "__file__" in locals() else os.getcwd()

text_standard = open(fpath + '/Plutarch_tokens.txt', 'rt').read()

wc = WordCloud(stopwords=stop_words,

mlai-demo

import numpy as np
from PIL import Image

roman_mask = np.array(Image.open(path.join(d, 'roman7.png')))
text_stem = open(fpath + '/Plutarch_stem.txt', 'rt').read()

wc = WordCloud(stopwords=stop_words, 
               max_font_size=200,
               width=5000,
               height=4000,

mlai-demo

import os
import re
fpath = os.getcwd(); fpath

mlai-demo

with open(fpath + '/Plutarch.txt') as f, 
open(fpath + '/Plutarch2.txt', 'w') as out_f:
    text = f.read().lower()
    new_text = re.sub('[^a-z\.\?\!\-\'\:\;]', ' ', text) #keep only wanted characters (alphabet and select punctuation)    new_text = re.sub(' +', ' ', new_text)#remove double empty spaces between words
    new_text = re.sub(' +', ' ', new_text) #remove double space
    new_text = re.sub('\n', ' ', new_text) #remove new line
    items = [w for w in new_text.split(' ') if w.strip() != '' or w == '\n']
    unique_items = set(items)
    print("The text is {} words long, has {} unique items and {} characters on average\n".format
      (len(items), len(unique_items), round(sum(len(word) for word in items)/len(items),2)))