update

new_user_analysis/new_user_project_protratit.py

@@ -113,8 +113,8 @@ for tractate_json in tractate_res_scan:
     # print(tractate_json)
     tractate_list.append(tractate_json["_source"])
     _id = tractate_json["_id"]
-    content_keyword_list = tractate_json["_source"]["content_keyword"]
-    for content_keyword in content_keyword_list:
+    fresh_tractate_tag_list = set(tractate_json["_source"]["fresh_tractate_tag_name"] + tractate_json["_source"]["tags_v3"])
+    for content_keyword in fresh_tractate_tag_list:
         if content_keyword in tractate_dict:
             tractate_dict[content_keyword] += 1
         else:
@@ -131,10 +131,10 @@ es_query_answer = {"query": {
     }
 }
 }
-res = pd.DataFrame(tractate_list)
-res.to_csv("tractate_list.csv",encoding="gb18030")
-send_file_email("", '', sender="litao@igengmei.com", email_group=["litao@igengmei.com"], email_msg_body_str="test",
-                title_str="test", cc_group=["litao@igengmei.com"], file="/srv/apps/meta_base_code/tractate_list.csv")
+# res = pd.DataFrame(tractate_list)
+# res.to_csv("tractate_list.csv",encoding="gb18030")
+# send_file_email("", '', sender="litao@igengmei.com", email_group=["litao@igengmei.com"], email_msg_body_str="test",
+#                 title_str="test", cc_group=["litao@igengmei.com"], file="/srv/apps/meta_base_code/tractate_list.csv")
 
 answer_list = []
 answer_res_scan = scan(client=es, query=json.dumps(es_query_answer), index="gm-dbmw-answer-read", doc_type="answer", scroll='3m')
@@ -142,16 +142,16 @@ answer_dict = {}
 for answer_json in answer_res_scan:
     answer_list.append(answer_json["_source"])
     _id = answer_json["_id"]
-    content_keyword_list = answer_json["_source"]["content_keyword"]
-    for content_keyword in content_keyword_list:
+    fresh_answer_tag_list = set(answer_json["_source"]["fresh_tractate_tag_name"] + answer_json["_source"]["tags_v3"])
+    for content_keyword in fresh_answer_tag_list:
         if content_keyword in answer_dict:
             answer_dict[content_keyword] += 1
         else:
             answer_dict[content_keyword] = 1
-res = pd.DataFrame(answer_list)
-res.to_csv("answer_list.csv",encoding="gb18030")
-send_file_email("", '', sender="litao@igengmei.com", email_group=["litao@igengmei.com"], email_msg_body_str="test",
-                title_str="test", cc_group=["litao@igengmei.com"], file="/srv/apps/meta_base_code/answer_list.csv")
+# res = pd.DataFrame(answer_list)
+# res.to_csv("answer_list.csv",encoding="gb18030")
+# send_file_email("", '', sender="litao@igengmei.com", email_group=["litao@igengmei.com"], email_msg_body_str="test",
+#                 title_str="test", cc_group=["litao@igengmei.com"], file="/srv/apps/meta_base_code/answer_list.csv")
 
 for t in range(2, task_days):
     day_num = 0 - t