Last active
July 26, 2023 09:48
-
-
Save kururu-abdo/bf36ade2435872a013596345e956021f to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| from wordcloud import WordCloud, STOPWORDS | |
| print ('Wordcloud imported!') | |
| import urllib | |
| # # open the file and read it into a variable alice_novel | |
| alice_novel = urllib.request.urlopen('https://cf-courses-data.s3.us.cloud-object-storage.appdomain.cloud/IBMDeveloperSkillsNetwork-DV0101EN-SkillsNetwork/Data%20Files/alice_novel.txt').read().decode("utf-8") | |
| stopwords = set(STOPWORDS) | |
| # instantiate a word cloud object | |
| alice_wc = WordCloud() | |
| # generate the word cloud | |
| alice_wc.generate(alice_novel) | |
| # display the word cloud | |
| plt.imshow(alice_wc, interpolation='bilinear') | |
| plt.axis('off') | |
| plt.show() | |
| #save mask to alice_mask | |
| alice_mask = np.array(Image.open(urllib.request.urlopen('https://cf-courses-data.s3.us.cloud-object-storage.appdomain.cloud/IBMDeveloperSkillsNetwork-DV0101EN-SkillsNetwork/labs/Module%204/images/alice_mask.png'))) | |
| fig = plt.figure(figsize=(14, 18)) | |
| plt.imshow(alice_mask, cmap=plt.cm.gray, interpolation='bilinear') | |
| plt.axis('off') | |
| plt.show() | |
| # instantiate a word cloud object | |
| alice_wc = WordCloud(background_color='white', max_words=2000, mask=alice_mask, stopwords=stopwords) | |
| # generate the word cloud | |
| alice_wc.generate(alice_novel) | |
| # display the word cloud | |
| fig = plt.figure(figsize=(14, 18)) | |
| plt.imshow(alice_wc, interpolation='bilinear') | |
| plt.axis('off') | |
| plt.show() | |
| #from data frame | |
| total_immigration | |
| max_words = 90 | |
| word_string = '' | |
| for country in df_can.index.values: | |
| # check if country's name is a single-word name | |
| if country.count(" ") == 0: | |
| repeat_num_times = int(df_can.loc[country, 'Total'] / total_immigration * max_words) | |
| word_string = word_string + ((country + ' ') * repeat_num_times) | |
| # display the generated text | |
| word_string | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment