Updating Clustering Code

parent d1c23906
......@@ -73,7 +73,7 @@ class TopicCluster:
idf_df = pd.DataFrame(
X.toarray(), columns=idf_vectorizer.get_feature_names())
# idf_df
#updated clustering code
# use_idf=True is default, but I'll leave it in
idf_vectorizer = TfidfVectorizer(
stop_words='english', tokenizer=stemming_tokenizer, use_idf=True, norm='l2')
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment