!pip install wordcloud

!pip install --user requests

import requests    # to download files through url

res = requests.get('https://automatetheboringstuff.com/files/rj.txt')
type(res)

# checking for error, 

res.status_code == requests.codes.ok   

len(res.text)   #178,000+ characters long

print(res.text[:0])

print(res.text[:1])

print(res.text[0])

print(res.text[:2])

print(res.text[:3])

print(res.text[:100])

print(res.text[:500])

res.raise_for_status()  
# checking for error
# response.raise_for_status() returns an HTTPError object if an error has occurred during the process.

playFile = open('RomeoAndJuliet.txt', 'wb') 
 # to write binary data instead of text data 
 # to maintain the Unicode encoding of the text. refer to the book

# https://www.geeksforgeeks.org/response-iter_content-python-requests/

for chunk in res.iter_content(200000):
  playFile.write(chunk)

playFile.close()

with open("RomeoAndJuliet.txt", 'r') as fh:  
    filedata = fh.read()

print(type(filedata))
print(len(filedata))
print('---------------')
print(filedata[:500])


#Library to form wordcloud :
from wordcloud import WordCloud, STOPWORDS
stopwords = set(STOPWORDS)

#Library to plot the wordcloud :
import matplotlib.pyplot as plt

#Generating the wordcloud data :
wordcloud = WordCloud(stopwords=stopwords, max_words=100).generate(filedata)

#Plot the wordcloud :
plt.figure(figsize = (10, 10)) 
plt.imshow(wordcloud) 

#To remove the axis value :
plt.axis("off") 
plt.show()

#Add more words to ignore 
stopwords.update(["many","go", "want", "value", "will", "come", "give", "Nurse", "one", "now", "go", "yet", "let"])

#Redo stop words. Limit number of words
wordcloud = WordCloud(stopwords=stopwords, max_words=100, \
                      background_color="white").generate(filedata)

#Plot the wordcloud :
plt.figure(figsize = (10, 10)) 
plt.imshow(wordcloud) 

#To remove the axis value :
plt.axis("off") 
plt.show()

!pip install pillow

pwd

#Import required libraries :
import numpy as np
from PIL import Image

#Here we are going to use a circle image as mask :
#char_mask = np.array(Image.open(""))

# makes the circle using numpy
x, y = np.ogrid[:300, :300]
mask = (x - 150) ** 2 + (y - 150) ** 2 > 130 ** 2
mask = 255 * mask.astype(int)


#Generating wordcloud :
wordcloud = WordCloud(background_color="black",contour_width=0.5, contour_color="yellow", mask=mask).generate(filedata)

#Plot the wordcloud :
plt.figure(figsize = (8,8))
plt.imshow(wordcloud)

#To remove the axis value :
plt.axis("off")
plt.show()