update

eda/smart_rank/dist_update_portrait_market.py

@@ -147,73 +147,73 @@ def compute_ai_scan(x):
 
 
 def get_user_tag_score(cl_id, all_word_tags, size=10):
-    # try:
-    db_jerry_test = pymysql.connect(host='172.16.40.158', port=4000, user='root', passwd='3SYz54LS9#^9sBvC',
-                                    db='jerry_test', charset='utf8')
-    cur_jerry_test = db_jerry_test.cursor()
-
-    # 用户的非搜索行为
-    user_df_service_sql = "select time,cl_id,score_type,tag_id,tag_referrer,action from user_new_tag_log " \
-                          "where cl_id ='{}' and action != 'do_search' ".format(cl_id)
-    cur_jerry_test.execute(user_df_service_sql)
-    data = list(cur_jerry_test.fetchall())
-    if data:
-        user_log_df = pd.DataFrame(data)
-        user_log_df.columns = ["time", "cl_id", "score_type", "tag_id", "tag_referrer", "action"]
-    else:
-        user_log_df = pd.DataFrame(columns=["time", "cl_id", "score_type", "tag_id", "tag_referrer", "action"])
-    # 用户的搜索行为
-    user_df_search_sql = "select time,cl_id,score_type,tag_id,tag_referrer,action from user_new_tag_log " \
-                         "where cl_id ='{}' and action = 'do_search'".format(cl_id)
-    cur_jerry_test.execute(user_df_search_sql)
-    data_search = list(cur_jerry_test.fetchall())
-    if data_search:
-        user_df_search = pd.DataFrame(data_search)
-        user_df_search.columns = ["time", "cl_id", "score_type", "tag_id", "tag_referrer", "action"]
-    else:
-        user_df_search = pd.DataFrame(columns=["time", "cl_id", "score_type", "tag_id", "tag_referrer", "action"])
-
-    # 搜索词转成tag
-    for index, row in user_df_search.iterrows():
-        if row['tag_referrer'] in all_word_tags:
-            for search_tag in all_word_tags[row['tag_referrer']]:
-                row['tag_id'] = int(search_tag)
-                user_log_df = user_log_df.append(row, ignore_index=True)
-                break
-    if not user_log_df.empty:
-        user_log_df["days_diff_now"] = round((int(time.time())-user_log_df["time"]) / (24*60*60))
-        user_log_df["score"] = user_log_df.apply(
-            lambda x: compute_henqiang(x.days_diff_now) if x.score_type == "henqiang" else (
-                compute_jiaoqiang(x.days_diff_now) if x.score_type == "jiaoqiang" else (
-                    compute_ai_scan(x.days_diff_now) if x.score_type == "ai_scan" else (
-                        compute_ruoyixiang(x.days_diff_now) if x.score_type == "ruoyixiang" else compute_validate(x.days_diff_now)))), axis=1)
-        finally_score = user_log_df.sort_values(by=["score","time"],ascending=False)
-        finally_score.drop_duplicates(subset="tag_id", inplace=True)
-        finally_score["weight"] = finally_score['score'] / finally_score['score'].sum()
-        finally_score["pay_type"] = finally_score.apply(
-            lambda x: 3 if x.action == "api/order/validate" else (
-                2 if x.action == "api/settlement/alipay_callback" else 1
-            ), axis=1
-        )
-        score_result = finally_score[["tag_id", "cl_id", "score", "weight", "pay_type"]]
-        score_result.rename(columns={"cl_id": "device_id"}, inplace=True)
-
-        # 写tidb
-        delete_sql = "delete from api_market_personas where device_id='{}'".format(cl_id)
-        cur_jerry_test.execute(delete_sql)
-        db_jerry_test.commit()
-
-        for index, row in score_result.iterrows():
-            insert_sql = "insert into api_market_personas values (null, {}, '{}', {}, {}, {})".format(
-                row['tag_id'], row['device_id'], row['score'], row['weight'], row['pay_type'])
-            cur_jerry_test.execute(insert_sql)
+    try:
+        db_jerry_test = pymysql.connect(host='172.16.40.158', port=4000, user='root', passwd='3SYz54LS9#^9sBvC',
+                                        db='jerry_test', charset='utf8')
+        cur_jerry_test = db_jerry_test.cursor()
+
+        # 用户的非搜索行为
+        user_df_service_sql = "select time,cl_id,score_type,tag_id,tag_referrer,action from user_new_tag_log " \
+                              "where cl_id ='{}' and action != 'do_search' ".format(cl_id)
+        cur_jerry_test.execute(user_df_service_sql)
+        data = list(cur_jerry_test.fetchall())
+        if data:
+            user_log_df = pd.DataFrame(data)
+            user_log_df.columns = ["time", "cl_id", "score_type", "tag_id", "tag_referrer", "action"]
+        else:
+            user_log_df = pd.DataFrame(columns=["time", "cl_id", "score_type", "tag_id", "tag_referrer", "action"])
+        # 用户的搜索行为
+        user_df_search_sql = "select time,cl_id,score_type,tag_id,tag_referrer,action from user_new_tag_log " \
+                             "where cl_id ='{}' and action = 'do_search'".format(cl_id)
+        cur_jerry_test.execute(user_df_search_sql)
+        data_search = list(cur_jerry_test.fetchall())
+        if data_search:
+            user_df_search = pd.DataFrame(data_search)
+            user_df_search.columns = ["time", "cl_id", "score_type", "tag_id", "tag_referrer", "action"]
+        else:
+            user_df_search = pd.DataFrame(columns=["time", "cl_id", "score_type", "tag_id", "tag_referrer", "action"])
+
+        # 搜索词转成tag
+        for index, row in user_df_search.iterrows():
+            if row['tag_referrer'] in all_word_tags:
+                for search_tag in all_word_tags[row['tag_referrer']]:
+                    row['tag_id'] = int(search_tag)
+                    user_log_df = user_log_df.append(row, ignore_index=True)
+                    break
+        if not user_log_df.empty:
+            user_log_df["days_diff_now"] = round((int(time.time())-user_log_df["time"]) / (24*60*60))
+            user_log_df["score"] = user_log_df.apply(
+                lambda x: compute_henqiang(x.days_diff_now) if x.score_type == "henqiang" else (
+                    compute_jiaoqiang(x.days_diff_now) if x.score_type == "jiaoqiang" else (
+                        compute_ai_scan(x.days_diff_now) if x.score_type == "ai_scan" else (
+                            compute_ruoyixiang(x.days_diff_now) if x.score_type == "ruoyixiang" else compute_validate(x.days_diff_now)))), axis=1)
+            finally_score = user_log_df.sort_values(by=["score","time"],ascending=False)
+            finally_score.drop_duplicates(subset="tag_id", inplace=True)
+            finally_score["weight"] = finally_score['score'] / finally_score['score'].sum()
+            finally_score["pay_type"] = finally_score.apply(
+                lambda x: 3 if x.action == "api/order/validate" else (
+                    2 if x.action == "api/settlement/alipay_callback" else 1
+                ), axis=1
+            )
+            score_result = finally_score[["tag_id", "cl_id", "score", "weight", "pay_type"]]
+            score_result.rename(columns={"cl_id": "device_id"}, inplace=True)
+
+            # 写tidb
+            delete_sql = "delete from api_market_personas where device_id='{}'".format(cl_id)
+            cur_jerry_test.execute(delete_sql)
             db_jerry_test.commit()
-        db_jerry_test.close()
-        return "sucess"
-    else:
-        return "user log is empty"
-    # except Exception as e:
-    #     return 'pass'
+
+            for index, row in score_result.iterrows():
+                insert_sql = "insert into api_market_personas values (null, {}, '{}', {}, {}, {})".format(
+                    row['tag_id'], row['device_id'], row['score'], row['weight'], row['pay_type'])
+                cur_jerry_test.execute(insert_sql)
+                db_jerry_test.commit()
+            db_jerry_test.close()
+            return "sucess"
+        else:
+            return "user log is empty"
+    except Exception as e:
+        return 'pass'
 
 
 if __name__ == '__main__':

eda/smart_rank/dist_update_user_portrait_service.py

@@ -226,7 +226,6 @@ def get_user_service_portrait(cl_id, all_word_tags, all_tag_tag_type, all_3tag_2
             user_df_search.columns = ["time", "cl_id", "score_type", "tag_id", "tag_referrer", "action"]
         else:
             user_df_search = pd.DataFrame(columns=["time", "cl_id", "score_type", "tag_id", "tag_referrer", "action"])
-        db_jerry_test.close()
 
         # 搜索词转成tag
         # user_df_search_2_tag = pd.DataFrame(columns=list(user_df_service.columns))