The print_top_words method from the code below only prints the distribution of the words for each topic:
- Cluster 1: word1 , word2 , ....
- Cluster 2: word3 , word2 , ....
So, instead of printing out the words distribution, I would like to print the documents in each cluster:
- Cluster 1: documents1 , documents2, ....
- Cluster 2: documents5 , documents6, ....
Code:
n_samples = 2000
n_features = 1000
n_topics = 10
n_top_words = 20
def print_top_words(model, feature_names, n_top_words):
for topic_idx, topic in enumerate(model.components_):
print("Topic #%d:" % topic_idx)
print(" ".join([feature_names[i]
for i in topic.argsort()[:-n_top_words - 1:-1]]))
print()
print("Loading dataset...")
t0 = time()
dataset = fetch_20newsgroups(shuffle=True, random_state=1,
remove=('headers', 'footers', 'quotes'))
data_samples = dataset.data[:n_samples]
print("done in %0.3fs." % (time() - t0))
# Use tf (raw term count) features for LDA.
print("Extracting tf features for LDA...")
tf_vectorizer = CountVectorizer(max_df=0.95, min_df=2,
max_features=n_features,
stop_words='english')
t0 = time()
tf = tf_vectorizer.fit_transform(data_samples)
print("done in %0.3fs." % (time() - t0))
print("Fitting LDA models with tf features, "
"n_samples=%d and n_features=%d..."
% (n_samples, n_features))
lda = LatentDirichletAllocation(n_topics=n_topics, max_iter=5,
learning_method='online',
learning_offset=50.,
random_state=0)
t0 = time()
lda.fit(tf)
print("done in %0.3fs." % (time() - t0))
print("\nTopics in LDA model:")
tf_feature_names = tf_vectorizer.get_feature_names()
print_top_words(lda, tf_feature_names, n_top_words)
