merge_class.py

from sklearn.metrics.pairwise import cosine_similarity

# Get similar classes
distances = cosine_similarity(c_tf_idf, c_tf_idf)
np.fill_diagonal(distances, 0)

# For each class, extract the most similar class
result = pd.DataFrame([(newsgroups.target_names[index], 
                        newsgroups.target_names[distances[index].argmax()])
                       for index in range(len(docs_per_class))],
                      columns=["From", "To"])