change test file

eda/esmm/Model_pipline/feature_engineering.py

@@ -159,6 +159,9 @@ def feature_engineer():
     sql = "select distinct recover_time from knowledge"
     unique_values.extend(get_unique(db, sql))
 
+    cid_star = ["star_0","star_1","star_2","star_3","star_4","star_5","star_3.5"]
+    unique_values.extend(cid_star)
+
     # unique_values.append("video")
 
     db = pymysql.connect(host='172.16.40.158', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='jerry_test')
@@ -195,7 +198,7 @@ def feature_engineer():
           "wiki.tag as tag1,question.tag as tag2,search.tag as tag3,budan.tag as tag4," \
           "ot.tag as tag5,sixin.tag as tag6,cart.tag as tag7,doris.search_tag2,doris.search_tag3," \
           "k.treatment_method,k.price_min,k.price_max,k.treatment_time,k.maintain_time,k.recover_time," \
-          "e.device_id,e.cid_id " \
+          "e.device_id,e.cid_id,concat('star','_',star.content_level) as content_level " \
           "from jerry_test.esmm_train_data_dwell e left join jerry_test.user_feature u on e.device_id = u.device_id " \
           "left join jerry_test.cid_type_top c on e.device_id = c.device_id " \
           "left join jerry_test.cid_time_cut cut on e.cid_id = cut.cid " \
@@ -212,6 +215,7 @@ def feature_engineer():
           "left join eagle.src_zhengxing_api_service service on e.diary_service_id = service.id " \
           "left join eagle.src_zhengxing_api_doctor doctor on service.doctor_id = doctor.id " \
           "left join jerry_test.search_doris doris on e.device_id = doris.device_id and e.stat_date = doris.get_date " \
+          "left join eagle.src_mimas_prod_api_diary star on e.cid_id = star.id " \
           "where e.stat_date >= '{}'".format(start)
 
     df = spark.sql(sql)
@@ -385,7 +389,14 @@ if __name__ == '__main__':
     path = "hdfs:///strategy/esmm/"
     local_path = "/home/gmuser/esmm/"
 
-    validate_date, value_map, app_list_map, leve2_map, leve3_map = feature_engineer()
-    get_predict(validate_date, value_map, app_list_map, leve2_map, leve3_map)
+    sql = "select e.cid_id,concat('star','_',star.content_level) as content_level " \
+          "from jerry_test.esmm_train_data_dwell e " \
+          "left join eagle.src_mimas_prod_api_diary star on e.cid_id = star.id " \
+          "where e.stat_date = '2019-08-13'"
+
+    spark.sql(sql).show()
+
+    # validate_date, value_map, app_list_map, leve2_map, leve3_map = feature_engineer()
+    # get_predict(validate_date, value_map, app_list_map, leve2_map, leve3_map)
 
     spark.stop()