# Import Dataset df = pd.read_json('https://raw.githubusercontent.com/selva86/datasets/master/newsgroups.json') df = df.loc[df.target_names.isin(['soc.religion.christian', 'rec.sport.hockey', 'talk.politics.mideast', 'rec.motorcycles']) , :] print(df.shape) #> (2361, 3) df.head()