Merge branch 'zhao' into 'master'

把esmm的加载曝光训练集改成精准曝光训练集，并减少训练集的数量

See merge request !24

eda/esmm/Model_pipline/feature_engineering.py

@@ -104,15 +104,15 @@ def feature_engineer():
 
     unique_values = []
     db = pymysql.connect(host='172.16.40.158', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='jerry_test')
-    sql = "select distinct stat_date from esmm_train_data_dwell"
+    sql = "select distinct stat_date from esmm_train_data_dwell_precise"
     unique_values.extend(get_unique(db,sql))
 
     db = pymysql.connect(host='172.16.40.158', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='jerry_test')
-    sql = "select distinct ucity_id from esmm_train_data_dwell"
+    sql = "select distinct ucity_id from esmm_train_data_dwell_precise"
     unique_values.extend(get_unique(db, sql))
 
     db = pymysql.connect(host='172.16.40.158', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='jerry_test')
-    sql = "select distinct ccity_name from esmm_train_data_dwell"
+    sql = "select distinct ccity_name from esmm_train_data_dwell_precise"
     unique_values.extend(get_unique(db, sql))
 
     db = pymysql.connect(host='172.16.40.158', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='jerry_test')
@@ -162,15 +162,15 @@ def feature_engineer():
     # unique_values.append("video")
 
     db = pymysql.connect(host='172.16.40.158', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='jerry_test')
-    sql = "select max(stat_date) from esmm_train_data_dwell"
+    sql = "select max(stat_date) from esmm_train_data_dwell_precise"
     validate_date = con_sql(db, sql)[0].values.tolist()[0]
     print("validate_date:" + validate_date)
     temp = datetime.datetime.strptime(validate_date, "%Y-%m-%d")
-    start = (temp - datetime.timedelta(days=100)).strftime("%Y-%m-%d")
+    start = (temp - datetime.timedelta(days=80)).strftime("%Y-%m-%d")
     print(start)
 
     db = pymysql.connect(host='172.16.40.158', port=4000, user='root', passwd='3SYz54LS9#^9sBvC')
-    sql = "select distinct doctor.hospital_id from jerry_test.esmm_train_data_dwell e " \
+    sql = "select distinct doctor.hospital_id from jerry_test.esmm_train_data_dwell_precise e " \
           "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 " \
           "where e.stat_date >= '{}'".format(start)
@@ -196,7 +196,7 @@ def feature_engineer():
           "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 " \
-          "from jerry_test.esmm_train_data_dwell e left join jerry_test.user_feature u on e.device_id = u.device_id " \
+          "from jerry_test.esmm_train_data_dwell_precise 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 " \
           "left join jerry_test.device_app_list dl on e.device_id = dl.device_id " \