Last active
October 30, 2020 05:20
-
-
Save lucinda-lim/478ab20a313e8cf7ed43fd616ec38ae2 to your computer and use it in GitHub Desktop.
This file contains hidden or 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
| def compute_coherence_values(dictionary, corpus, texts, limit, start=2, step=3): | |
| coherence_values = [] | |
| model_list = [] | |
| for num_topics in range(start, limit, step): | |
| model = gensim.models.ldamodel.LdaModel(corpus=corpus, | |
| id2word=id2word, | |
| num_topics=num_topics, | |
| random_state=100, | |
| update_every=1, | |
| chunksize=100, | |
| passes=10, | |
| alpha='auto', | |
| per_word_topics=True) | |
| model_list.append(model) | |
| coherencemodel = CoherenceModel(model=model, texts=texts, dictionary=dictionary, coherence='c_v') | |
| coherence_values.append(coherencemodel.get_coherence()) | |
| return model_list, coherence_values | |
| ## ---------------------------------------------------------------------------------------------- | |
| model_list, coherence_values = compute_coherence_values(dictionary=id2word, corpus=corpus, texts=data_lemmatized, start=2, limit=21, step=1) | |
| ## visualize | |
| limit=21; start=2; step=1; | |
| x = range(start, limit, step) | |
| plt.plot(x, coherence_values) | |
| plt.xlabel("Num Topics") | |
| plt.ylabel("Coherence score") | |
| plt.legend(("coherence_values"), loc='best') | |
| plt.show() | |
| ##print values | |
| for m, cv in zip(x, coherence_values): | |
| print("Num Topics =", m, " has Coherence Value of", round(cv, 4)) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment