get data

word_vector/word_to_vec.py

@@ -2,12 +2,17 @@ import os
 import time
 
 from gensim.models import word2vec
+from gm_rpcd.all import bind
 
 base_dir = os.getcwd()
 print("base_dir: " + base_dir)
 model_dir = os.path.join(base_dir, "_models")
 data_dir = os.path.join(base_dir, "_data")
 
+model_output_name = "w2v_model"
+model_path = os.path.join(model_dir, model_output_name)
+WORD2VEC_MODEL = word2vec.Word2Vec.load(model_path)
+
 
 class W2vSentences:
     def __init__(self, f_name):
@@ -29,17 +34,17 @@ def w2v_train(f_name, model_output_name):
     w2v_model.save(model_path)
 
 
+@bind("strategy_embedding/word_vector/word_similarity")
+def word_similarity():
+    pass
+
+
 if __name__ == "__main__":
     begin_time = time.time()
 
-    model_output_name = "w2v_model"
     # w2v_train("dispose_problem.txt", model_output_name)
 
-    model_path = os.path.join(model_dir, model_output_name)
-
-    w2v_model = word2vec.Word2Vec.load(model_path)
-
     for i in ["双眼皮", "隆鼻"]:
-        print(w2v_model.wv.most_similar(i))
+        print(WORD2VEC_MODEL.wv.most_similar(i))
 
     print("total cost: {:.2f}mins".format((time.time() - begin_time) / 60))