import_imb.py

from sklearn.datasets import fetch_20newsgroups
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.naive_bayes import MultinomialNB
from sklearn.pipeline import make_pipeline
from sklearn.metrics import classification_report
from imblearn.under_sampling import RandomUnderSampler
from imblearn.pipeline import make_pipeline as make_pipeline_imb
from collections import Counter

categories = [
    "alt.atheism",
    "talk.religion.misc",
    "comp.graphics",
    "sci.space",
]
newsgroups_train = fetch_20newsgroups(subset="train", categories=categories)
newsgroups_test = fetch_20newsgroups(subset="test", categories=categories)

X_train = newsgroups_train.data
X_test = newsgroups_test.data

y_train = newsgroups_train.target
y_test = newsgroups_test.target