Created
October 3, 2022 17:59
-
-
Save andrea-dagostino/06633531f472de3d47e41a523e7b3de2 to your computer and use it in GitHub Desktop.
text_sim_tfidf
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import pandas as pd | |
import numpy as np | |
import nltk | |
from nltk.corpus import stopwords | |
import string | |
from sklearn.feature_extraction.text import TfidfVectorizer | |
from tqdm import tqdm | |
import matplotlib.pyplot as plt | |
import seaborn as sns | |
### | |
Ricordiamo di creare il dataset con lo script presente qui | |
https://www.diariodiunanalista.it/posts/come-scraperare-un-blog-e-raccogliere-i-suoi-articoli | |
### | |
posts = df[df.url.str.contains('post')] | |
posts.reset_index(inplace=True) | |
remove_punctuation_map = dict((ord(char), None) for char in string.punctuation) | |
ita_stopwords = stopwords.words('italian') | |
def preprocess(text): | |
return nltk.word_tokenize(text.lower().translate(remove_punctuation_map)) | |
vectorizer = TfidfVectorizer(tokenizer=preprocess, stop_words=ita_stopwords) | |
def compute_similarity(a, b): | |
tfidf = vectorizer.fit_transform([a, b]) | |
return ((tfidf * tfidf.T).toarray())[0,1] | |
M = np.zeros((posts.shape[0], posts.shape[0])) | |
for i, row in tqdm(posts.iterrows(), total=posts.shape[0], desc='1st level'): | |
for j, next_row in posts.iterrows(): | |
M[i, j] = compute_similarity(row.article, next_row.article) | |
labels = posts.url.str.split('/').str[3:].str[1] | |
similarity_df = pd.DataFrame(M, columns=labels, index=labels) | |
mask = np.triu(np.ones_like(similarity_df)) | |
plt.figure(figsize=(12, 12)) | |
sns.heatmap( | |
similarity_df, | |
square=True, | |
annot=True, | |
robust=True, | |
fmt='.2f', | |
annot_kws={'size': 7, 'fontweight': 'bold'}, | |
yticklabels=similarity_df.columns | |
xticklabels=similarity_df.columns, | |
cmap="YlGnBu", | |
mask=mask | |
) | |
plt.title('Heatmap delle similarità tra testi', fontdict={'fontsize': 24}) | |
plt.show() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment