Commit 33647ec9 authored by 张彦钊's avatar 张彦钊

把esmm的训练集改成精准曝光训练集

parent a95245e6
...@@ -104,15 +104,15 @@ def feature_engineer(): ...@@ -104,15 +104,15 @@ def feature_engineer():
unique_values = [] unique_values = []
db = pymysql.connect(host='172.16.40.158', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='jerry_test') 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)) 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') 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)) 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') 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)) 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') db = pymysql.connect(host='172.16.40.158', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='jerry_test')
...@@ -162,7 +162,7 @@ def feature_engineer(): ...@@ -162,7 +162,7 @@ def feature_engineer():
# unique_values.append("video") # unique_values.append("video")
db = pymysql.connect(host='172.16.40.158', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='jerry_test') 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] validate_date = con_sql(db, sql)[0].values.tolist()[0]
print("validate_date:" + validate_date) print("validate_date:" + validate_date)
temp = datetime.datetime.strptime(validate_date, "%Y-%m-%d") temp = datetime.datetime.strptime(validate_date, "%Y-%m-%d")
...@@ -170,7 +170,7 @@ def feature_engineer(): ...@@ -170,7 +170,7 @@ def feature_engineer():
print(start) print(start)
db = pymysql.connect(host='172.16.40.158', port=4000, user='root', passwd='3SYz54LS9#^9sBvC') 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_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 eagle.src_zhengxing_api_doctor doctor on service.doctor_id = doctor.id " \
"where e.stat_date >= '{}'".format(start) "where e.stat_date >= '{}'".format(start)
...@@ -196,7 +196,7 @@ def feature_engineer(): ...@@ -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," \ "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," \ "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 " \
"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_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.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 " \ "left join jerry_test.device_app_list dl on e.device_id = dl.device_id " \
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment