Add doc2vec ngram builder script

peter-volkov · Mar 22, 2017 · af4e141 · af4e141
1 parent e98355a
commit af4e141
Show file tree

Hide file tree

Showing 2 changed files with 7 additions and 0 deletions.
diff --git a/ngram_vector_building/doc2vec/doc2vec.txt.7z b/ngram_vector_building/doc2vec/doc2vec.txt.7z
diff --git a/ngram_vector_building/doc2vec/sec2vec.py b/ngram_vector_building/doc2vec/sec2vec.py
@@ -0,0 +1,7 @@
+import gensim 
+import sys
+
+if __name__ == '__main__':
+    documents = gensim.models.doc2vec.TaggedLineDocument(sys.argv[1])
+    model = gensim.models.doc2vec.Doc2Vec(documents, size=250, window=5, min_count=5, workers=32)
+    model.wv.save_word2vec_format('doc2vec.txt')