update model

word_vector/word_to_vec.py

@@ -3,8 +3,8 @@ import time
 
 from gensim.models import Word2Vec, word2vec
 from gm_rpcd.all import bind
-from utils.es import es_scan
 from utils.db import get_device_click_tractate_ids
+from utils.es import es_scan
 
 base_dir = os.getcwd()
 print("base_dir: " + base_dir)
@@ -79,7 +79,12 @@ def projects_item2vec(score_limit=5):
 def clicked_tractate_ids_item2vec():
     user_dict = get_device_click_tractate_ids()
     click_ids = list(user_dict.values())
-    print(click_ids)
+    model = Word2Vec(click_ids, hs=0, min_count=3, workers=multiprocessing.cpu_count(), iter=10)
+    print(model)
+    print(len(click_ids))
+    for id in ["88529", "87970", "88364"]:
+        print(model.wv.most_similar(id, topn=5))
+    return model
 
 
 if __name__ == "__main__":