posts/raggruppamento-testuale-con-tf-idf

clustering_1.py

# importiamo le librerie necessarie da sklearn
from sklearn.datasets import fetch_20newsgroups
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.cluster import KMeans
from sklearn.decomposition import PCA

# importiamo le altre librerie necessarie
import pandas as pd
import numpy as np

# librerie per la manipolazione del testo
import re
import string
import nltk
from nltk.corpus import stopwords

# importiamo le librerie di visualizzazione
import matplotlib.pyplot as plt


categories = [
 'comp.graphics',
 'comp.os.ms-windows.misc',
 'rec.sport.baseball',
 'rec.sport.hockey',
 'alt.atheism',
 'soc.religion.christian',
]
dataset = fetch_20newsgroups(subset='train', categories=categories, shuffle=True, remove=('headers', 'footers', 'quotes'))