Created
December 7, 2020 14:59
-
-
Save do-me/cd2555047e8e134f9fb21d56348a238d to your computer and use it in GitHub Desktop.
Topic Modeling with Scikit Learn with Python 3 and Scikit-learn 0.23
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
# adapted code for Python 3 and latest Scikit-learn version 0:23 | |
# based on https://medium.com/mlreview/topic-modeling-with-scikit-learn-e80d33668730 | |
from sklearn.feature_extraction.text import TfidfVectorizer, CountVectorizer | |
from sklearn.decomposition import NMF, LatentDirichletAllocation | |
import numpy as np | |
def display_topics(H, W, feature_names, documents, no_top_words, no_top_documents): | |
for topic_idx, topic in enumerate(H): | |
print("Topic {}".format(topic_idx)) | |
print(" ".join([feature_names[i] for i in topic.argsort()[:-no_top_words - 1:-1]])) | |
top_doc_indices = np.argsort( W[:,topic_idx] )[::-1][0:no_top_documents] | |
for doc_index in top_doc_indices: | |
print(documents[doc_index]) | |
# Single line documents from http://web.eecs.utk.edu/~berry/order/node4.html#SECTION00022000000000000000 | |
documents = [ | |
"Human machine interface for Lab ABC computer applications", | |
"A survey of user opinion of computer system response time", | |
"The EPS user interface management system", | |
"System and human system engineering testing of EPS", | |
"Relation of user-perceived response time to error measurement", | |
"The generation of random, binary, unordered trees", | |
"The intersection graph of paths in trees", | |
"Graph minors IV: Widths of trees and quasi-ordering", | |
"Graph minors: A survey" | |
] | |
# NMF is able to use tf-idf | |
tfidf_vectorizer = TfidfVectorizer(max_df=0.95, min_df=2, stop_words='english') | |
tfidf = tfidf_vectorizer.fit_transform(documents) | |
tfidf_feature_names = tfidf_vectorizer.get_feature_names() | |
# LDA can only use raw term counts for LDA because it is a probabilistic graphical model | |
tf_vectorizer = CountVectorizer(max_df=0.95, min_df=2, stop_words='english') | |
tf = tf_vectorizer.fit_transform(documents) | |
tf_feature_names = tf_vectorizer.get_feature_names() | |
no_topics = 2 | |
# Run NMF | |
nmf_model = NMF(n_components=no_topics, random_state=1, alpha=.1, l1_ratio=.5, init='nndsvd').fit(tfidf) | |
nmf_W = nmf_model.transform(tfidf) | |
nmf_H = nmf_model.components_ | |
# Run LDA | |
lda_model = LatentDirichletAllocation(n_components=no_topics, max_iter=5, learning_method='online', learning_offset=50.,random_state=0).fit(tf) | |
lda_W = lda_model.transform(tf) | |
lda_H = lda_model.components_ | |
no_top_words = 4 | |
no_top_documents = 4 | |
display_topics(nmf_H, nmf_W, tfidf_feature_names, documents, no_top_words, no_top_documents) | |
display_topics(lda_H, lda_W, tf_feature_names, documents, no_top_words, no_top_documents) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment