get data

eda/smart_rank/tag3_update_user_portrait_offline.py

@@ -6,6 +6,7 @@ from collections import Counter
 
 import redis
 
+import pymysql
 from pyspark import SparkConf
 from pyspark.sql import SparkSession
 from tool import (get_doris_prod, get_jerry_test, get_tag3_user_log, send_email, write_user_portrait,
@@ -52,6 +53,84 @@ def merge_results_by_event(lst):
     return res
 
 
+def _make_score(lst, score):
+    return dict(zip(lst, [score] * len(lst)))
+
+
+def _get_all_by_project(name):
+    first_demands = []
+    second_demands = []
+    first_solutions = []
+    second_solutions = []
+    first_positions = []
+    second_positions = []
+    sql = """select name, tag_type from api_tag_3_0 where id in (
+             select tag_attr.tag_attr_id from api_tag_3_0 as api_tag
+             left join api_tag_attr_tag as tag_attr on tag_attr.tag_id = api_tag.id
+             where api_tag.name = '{}')
+    """.format(name)
+    zhengxing_conn = pymysql.connect(host="172.16.30.141",
+                                     user="work",
+                                     password="BJQaT9VzDcuPBqkd",
+                                     database="zhengxing",
+                                     charset="utf8")
+    zhengxing_cursor = zhengxing_conn.cursor()
+    zhengxing_cursor.execute(sql)
+    sql_tag_results = zhengxing_cursor.fetchall()
+    # TAG_V3_TYPE
+    for name, agg_type in sql_tag_results:
+        if agg_type == 20:
+            second_demands.append(name)
+        elif agg_type == 16:
+            second_solutions.append(name)
+        elif agg_type == 22:
+            second_positions.append(name)
+        elif agg_type == 19:
+            first_demands.append(name)
+        elif agg_type == 18:
+            first_solutions.append(name)
+        elif agg_type == 21:
+            first_positions.append(name)
+    return {
+        "first_demands": first_demands,
+        "second_demands": second_demands,
+        "first_solutions": first_solutions,
+        "second_solutions": second_solutions,
+        "first_positions": first_positions,
+        "second_positions": second_positions,
+        "projects": [name]
+    }
+
+
+def _get_all_by_projects(name_lst):
+    first_demands = []
+    second_demands = []
+    first_solutions = []
+    second_solutions = []
+    first_positions = []
+    second_positions = []
+    projects = name_lst
+    for name in projects:
+        all = _get_all_by_project(name)
+        first_demands.extend(all.get("first_demands", []))
+        second_demands.extend(all.get("second_demands", []))
+        first_solutions.extend(all.get("first_solutions", []))
+        second_solutions.extend(all.get("second_solutions", []))
+        first_positions.extend(all.get("first_positions", []))
+        second_positions.extend(all.get("second_positions", []))
+    if first_demands or second_demands or first_solutions or second_solutions or first_positions or second_positions or projects:
+        return {
+            "first_demands": _make_score(first_demands, 2),
+            "second_demands": _make_score(second_demands, 2),
+            "first_solutions": _make_score(first_solutions, 2),
+            "second_solutions": _make_score(second_solutions, 2),
+            "first_positions": _make_score(first_positions, 2),
+            "second_positions": _make_score(second_positions, 2),
+            "projects": _make_score(projects, 2)
+        }
+    return None
+
+
 def update_tag3_user_portrait_by_event(cl_id):
     user_df = get_tag3_user_log(cl_id)
     if not user_df.empty:
@@ -158,7 +237,8 @@ def update_tag3_user_portrait(cl_id):
                 projects_score[k] = v
 
         if (len(first_demands_score) == 0) and (len(first_solutions_score) == 0) and (len(first_positions_list) == 0):
-            pass
+            res = _get_all_by_projects(list(projects_score.keys()))
+            print(res)
 
         res = {
             "first_demands": first_demands_score,