update

eda/smart_rank/dist_update_user_portrait_service.py

@@ -52,79 +52,80 @@ def get_user_service_portrait(cl_id, all_word_tags, all_tag_tag_type, all_3tag_2
         user_df_service["days_diff_now"] = round((int(time.time()) - user_df_service["time"].astype(float)) / (24 * 60 * 60))
         user_df_service["tag_type"] = user_df_service.apply(lambda x: all_tag_tag_type.get(x["tag_id"]), axis=1)
         user_df_service = user_df_service[user_df_service['tag_type'].isin(['2','3'])]
-        user_log_df_tag2_list = user_df_service[user_df_service['tag_type'] == '2']['tag_id'].unique().tolist()
-        user_df_service["tag2"] = user_df_service.apply(lambda x:
-                                                get_tag2_from_tag3(x.tag_id, all_3tag_2tag, user_log_df_tag2_list)
-                                                if x.tag_type == '3' else x.tag_id, axis=1)
-        user_df_service["tag2_type"] = user_df_service.apply(lambda x: all_tag_tag_type.get(x["tag2"]), axis=1)
-        # 算分及比例
-        user_df_service["tag_score"] = user_df_service.apply(
-            lambda x: compute_henqiang(x.days_diff_now, exponential=0)/get_action_tag_count(user_df_service, x.time) if x.score_type == "henqiang" else (
-                compute_jiaoqiang(x.days_diff_now, exponential=0)/get_action_tag_count(user_df_service, x.time) if x.score_type == "jiaoqiang" else (
-                    compute_ai_scan(x.days_diff_now, exponential=0)/get_action_tag_count(user_df_service, x.time) if x.score_type == "ai_scan" else (
-                    compute_ruoyixiang(x.days_diff_now, exponential=0)/get_action_tag_count(user_df_service, x.time) if x.score_type == "ruoyixiang" else
-                    compute_validate(x.days_diff_now, exponential=0)/get_action_tag_count(user_df_service, x.time)))), axis=1)
-        tag_score_sum = user_df_service.groupby(by=["tag2", "tag2_type"]).agg(
-            {'tag_score': 'sum', 'cl_id': 'first', 'action': 'first'}).reset_index().sort_values(by=["tag_score"],
-                                                                                                 ascending=False)
-        tag_score_sum['weight'] = 100 * tag_score_sum['tag_score'] / tag_score_sum['tag_score'].sum()
-        tag_score_sum["pay_type"] = tag_score_sum.apply(
-            lambda x: 3 if x.action == "api/order/validate" else (
-                2 if x.action == "api/settlement/alipay_callback" else 1
-            ), axis=1
-        )
-        gmkv_tag_score_sum = tag_score_sum[["tag2", "tag_score", "weight"]][:size].to_dict('record')
-        gmkv_tag_score2_sum = tag_score_sum[["tag2", "tag_score"]][:size].to_dict('record')
-        gmkv_tag_score2_sum_dict = {i["tag2"]: i["tag_score"] for i in gmkv_tag_score2_sum}
-
-        # 写redis
-        redis_client = redis.StrictRedis.from_url('redis://:ReDis!GmTx*0aN9@172.16.40.173:6379')
-        cl_id_portrait_key2 = "user:service_portrait_tags2:cl_id:" + str(cl_id)
-        # 如果画像的tag个数小于5，则补充热搜词
-        if len(gmkv_tag_score2_sum_dict) < 5:
-            hot_search_wordskey2 = "user:service_coldstart_tags2"
-            hot_search_words_score = redis_client.hgetall(hot_search_wordskey2)
-            for tag_id in hot_search_words_score:
-                if int(tag_id) in gmkv_tag_score2_sum_dict:
-                    continue
-                else:
-                    gmkv_tag_score2_sum_dict.update({int(tag_id): float(hot_search_words_score[tag_id])})
-                if len(gmkv_tag_score2_sum_dict) > 4:
-                    break
-        redis_client.delete(cl_id_portrait_key2)
-        redis_client.hmset(cl_id_portrait_key2, gmkv_tag_score2_sum_dict)
-        redis_client.expire(cl_id_portrait_key2, time=30 * 24 * 60 * 60)
-
-        # 标签name写redis
-        cl_id_portrait_key3 = "user:service_portrait_tags3:cl_id:" + str(cl_id)
-        gmkv_tag_score3_sum_dict = {all_tags_name[i]: gmkv_tag_score2_sum_dict[i] for i in gmkv_tag_score2_sum_dict}
-        redis_client.delete(cl_id_portrait_key3)
-        redis_client.hmset(cl_id_portrait_key3, gmkv_tag_score3_sum_dict)
-        redis_client.expire(cl_id_portrait_key3, time=30 * 24 * 60 * 60)
-
-        # 写tidb，redis同步
-        stat_date = datetime.datetime.today().strftime('%Y-%m-%d')
-        replace_sql = """replace into user_service_portrait_tags (stat_date, cl_id, tag_list) values("{stat_date}","{cl_id}","{tag_list}")"""\
-            .format(stat_date=stat_date, cl_id=cl_id, tag_list=gmkv_tag_score_sum)
-        cur_jerry_test.execute(replace_sql)
-        db_jerry_test.commit()
-        cur_jerry_test.close()
-        db_jerry_test.close()
-        # # 写tidb 用户分层营销
-        # # todo 不准确，因为聚合后，一个标签会有多个来源，即多个pay_type
-        # score_result = tag_score_sum[["tag2", "cl_id", "tag_score", "weight", "pay_type"]]
-        # score_result.rename(columns={"tag2": "tag_id", "cl_id": "device_id", "tag_score": "score"}, inplace=True)
-        # 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)
-        #     db_jerry_test.commit()
-        # db_jerry_test.close()
-        return cl_id
+        if not user_df_service.empty:
+            user_log_df_tag2_list = user_df_service[user_df_service['tag_type'] == '2']['tag_id'].unique().tolist()
+            user_df_service["tag2"] = user_df_service.apply(lambda x:
+                                                    get_tag2_from_tag3(x.tag_id, all_3tag_2tag, user_log_df_tag2_list)
+                                                    if x.tag_type == '3' else x.tag_id, axis=1)
+            user_df_service["tag2_type"] = user_df_service.apply(lambda x: all_tag_tag_type.get(x["tag2"]), axis=1)
+            # 算分及比例
+            user_df_service["tag_score"] = user_df_service.apply(
+                lambda x: compute_henqiang(x.days_diff_now, exponential=0)/get_action_tag_count(user_df_service, x.time) if x.score_type == "henqiang" else (
+                    compute_jiaoqiang(x.days_diff_now, exponential=0)/get_action_tag_count(user_df_service, x.time) if x.score_type == "jiaoqiang" else (
+                        compute_ai_scan(x.days_diff_now, exponential=0)/get_action_tag_count(user_df_service, x.time) if x.score_type == "ai_scan" else (
+                        compute_ruoyixiang(x.days_diff_now, exponential=0)/get_action_tag_count(user_df_service, x.time) if x.score_type == "ruoyixiang" else
+                        compute_validate(x.days_diff_now, exponential=0)/get_action_tag_count(user_df_service, x.time)))), axis=1)
+            tag_score_sum = user_df_service.groupby(by=["tag2", "tag2_type"]).agg(
+                {'tag_score': 'sum', 'cl_id': 'first', 'action': 'first'}).reset_index().sort_values(by=["tag_score"],
+                                                                                                     ascending=False)
+            tag_score_sum['weight'] = 100 * tag_score_sum['tag_score'] / tag_score_sum['tag_score'].sum()
+            tag_score_sum["pay_type"] = tag_score_sum.apply(
+                lambda x: 3 if x.action == "api/order/validate" else (
+                    2 if x.action == "api/settlement/alipay_callback" else 1
+                ), axis=1
+            )
+            gmkv_tag_score_sum = tag_score_sum[["tag2", "tag_score", "weight"]][:size].to_dict('record')
+            gmkv_tag_score2_sum = tag_score_sum[["tag2", "tag_score"]][:size].to_dict('record')
+            gmkv_tag_score2_sum_dict = {i["tag2"]: i["tag_score"] for i in gmkv_tag_score2_sum}
+
+            # 写redis
+            redis_client = redis.StrictRedis.from_url('redis://:ReDis!GmTx*0aN9@172.16.40.173:6379')
+            cl_id_portrait_key2 = "user:service_portrait_tags2:cl_id:" + str(cl_id)
+            # 如果画像的tag个数小于5，则补充热搜词
+            if len(gmkv_tag_score2_sum_dict) < 5:
+                hot_search_wordskey2 = "user:service_coldstart_tags2"
+                hot_search_words_score = redis_client.hgetall(hot_search_wordskey2)
+                for tag_id in hot_search_words_score:
+                    if int(tag_id) in gmkv_tag_score2_sum_dict:
+                        continue
+                    else:
+                        gmkv_tag_score2_sum_dict.update({int(tag_id): float(hot_search_words_score[tag_id])})
+                    if len(gmkv_tag_score2_sum_dict) > 4:
+                        break
+            redis_client.delete(cl_id_portrait_key2)
+            redis_client.hmset(cl_id_portrait_key2, gmkv_tag_score2_sum_dict)
+            redis_client.expire(cl_id_portrait_key2, time=30 * 24 * 60 * 60)
+
+            # 标签name写redis
+            cl_id_portrait_key3 = "user:service_portrait_tags3:cl_id:" + str(cl_id)
+            gmkv_tag_score3_sum_dict = {all_tags_name[i]: gmkv_tag_score2_sum_dict[i] for i in gmkv_tag_score2_sum_dict}
+            redis_client.delete(cl_id_portrait_key3)
+            redis_client.hmset(cl_id_portrait_key3, gmkv_tag_score3_sum_dict)
+            redis_client.expire(cl_id_portrait_key3, time=30 * 24 * 60 * 60)
+
+            # 写tidb，redis同步
+            stat_date = datetime.datetime.today().strftime('%Y-%m-%d')
+            replace_sql = """replace into user_service_portrait_tags (stat_date, cl_id, tag_list) values("{stat_date}","{cl_id}","{tag_list}")"""\
+                .format(stat_date=stat_date, cl_id=cl_id, tag_list=gmkv_tag_score_sum)
+            cur_jerry_test.execute(replace_sql)
+            db_jerry_test.commit()
+            cur_jerry_test.close()
+            db_jerry_test.close()
+            # # 写tidb 用户分层营销
+            # # todo 不准确，因为聚合后，一个标签会有多个来源，即多个pay_type
+            # score_result = tag_score_sum[["tag2", "cl_id", "tag_score", "weight", "pay_type"]]
+            # score_result.rename(columns={"tag2": "tag_id", "cl_id": "device_id", "tag_score": "score"}, inplace=True)
+            # 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)
+            #     db_jerry_test.commit()
+            # db_jerry_test.close()
+            return cl_id
 
 
 if __name__ == '__main__':