davidlenz

from sklearn.datasets import fetch_20newsgroups
import pandas as pd

def twenty_newsgroup_to_csv():
    newsgroups_train = fetch_20newsgroups(subset='train', remove=('headers', 'footers', 'quotes'))

    df = pd.DataFrame([newsgroups_train.data, newsgroups_train.target.tolist()]).T
    df.columns = ['text', 'target']

    targets = pd.DataFrame( newsgroups_train.target_names)