add content level

doc_similarity/answer_similarity.py

@@ -34,6 +34,7 @@ def write_result():
     bc = BertClient("172.16.44.82", check_length=False)
 
     count = 0
+    content_level_dict = {}
     embedding_dict = {}
     for item in get_answer_info_from_es(["id", "answer", "content_level"]):
         count += 1
@@ -41,7 +42,8 @@ def write_result():
             id = int(item["_id"])
             soup = BeautifulSoup(item["_source"]["answer"], "html.parser")
             content = soup.get_text()
-            # content_level = str(item["_source"]["content_level"])
+            content_level = str(item["_source"]["content_level"])
+            content_level_dict[id] = content_level
             # print(count, id, content)
             embedding_dict[id] = bc.encode([content]).tolist()[0]
         except Exception as e:
@@ -72,7 +74,7 @@ def write_result():
             if i <= 1.0 and tmp_id != id:
                 res.append(str(tmp_id))
         if res:
-            data = "{}:{}".format(str(id), ",".join(res))
+            data = "{}:{}:{}".format(content_level_dict.get(id, -1), str(id), ",".join(res))
             print(data)