get item2vec

strategy_embedding/settings.py

@@ -38,6 +38,7 @@ INSTALLED_APPS = [
     "django_extensions",
     "face_similarity",
     "word_vector",
+    "utils",
 ]
 
 MIDDLEWARE = [

word_vector/word_to_vec.py

@@ -4,7 +4,6 @@ import time
 
 from gensim.models import Word2Vec, word2vec
 from gm_rpcd.all import bind
-from utils.db import get_device_click_tractate_ids
 from utils.es import es_scan
 
 base_dir = os.getcwd()
@@ -76,8 +75,15 @@ def projects_item2vec(score_limit=5):
 
 
 def clicked_tractate_ids_item2vec():
-    user_dict = get_device_click_tractate_ids()
-    click_ids = list(user_dict.values())
+    click_ids = []
+    with open(os.path.join(data_dir, "click_tractate_ids.csv"), "r") as f:
+        data = f.readlines()
+        data = data[:100]
+        for i in data:
+            tmp = i.split("|")
+            # device_id = tmp[0]
+            ids = tmp[1].rstrip("\n").split(",")
+            click_ids.append(ids)
     model = Word2Vec(click_ids, hs=0, min_count=3, workers=multiprocessing.cpu_count(), iter=10)
     print(model)
     print(len(click_ids))
@@ -94,4 +100,6 @@ if __name__ == "__main__":
     for i in ["双眼皮", "隆鼻"]:
         print(word_similarity(i))
 
+    clicked_tractate_ids_item2vec()
+
     print("total cost: {:.2f}mins".format((time.time() - begin_time) / 60))