In [ ]:
from sklearn.datasets import fetch_20newsgroups
categories = [
'alt.atheism',
'talk.religion.misc',
'comp.graphics',
'sci.space',
]
# Uncomment the following to do the analysis on all the categories
#categories = None
print("Loading 20 newsgroups dataset for categories:")
print(categories)
dataset = fetch_20newsgroups(subset='all', categories=categories,
shuffle=True, random_state=42)
In [ ]:
dataset
In [ ]: