Merge branch 'master' into patch-2

aws · Oct 29, 2020 · cd987ff · cd987ff
2 parents c2c7bef + bc70715
commit cd987ff
Showing 1 changed file with 1 addition and 1 deletion.
diff --git a/...lying_machine_learning/ntm_20newsgroups_topic_modeling/ntm_20newsgroups_topic_model.ipynb b/...lying_machine_learning/ntm_20newsgroups_topic_modeling/ntm_20newsgroups_topic_model.ipynb
@@ -279,7 +279,7 @@
     "print('Tokenizing and counting, this may take a few minutes...')\n",
     "start_time = time.time()\n",
     "vectorizer = CountVectorizer(input='content', analyzer='word', stop_words='english',\n",
-    "                             tokenizer=LemmaTokenizer(), max_features=vocab_size, max_df=0.95, min_df=2)\n",
+    "                             tokenizer=LemmaTokenizer(), max_features=vocab_size, max_df=0.95, min_df=0.2)\n",
     "vectors = vectorizer.fit_transform(data)\n",
     "vocab_list = vectorizer.get_feature_names()\n",
     "print('vocab size:', len(vocab_list))\n",