Last active
April 23, 2017 18:57
-
-
Save conormm/2ba81bc928760c2dda002fe7a35d5a9b 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
articles = get_articles(the_guardian, breitbart, title_topic="Trump") | |
articles["text"] = articles.text.map(clean_text) | |
articles["text"] = preprocess_articles(articles.text) | |
def get_readability_stats(parsed_articles): | |
stats_list = [] | |
for ix, article in enumerate(parsed_articles): | |
doc = tcy.Doc(article) | |
readability_stats = tcy.text_stats.readability_stats(doc) | |
read_stats_df = pd.DataFrame(readability_stats, index=[ix]) | |
stats_list.append(read_stats_df) | |
return pd.concat(stats_list) | |
readability_stats = get_readability_stats(articles.text) | |
articles = pd.concat([articles.reset_index(drop=True), readability_stats], axis=1) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment