Commit ed372240 authored by 张彦钊's avatar 张彦钊

增加特征

parent f1521636
...@@ -37,7 +37,7 @@ def get_data(): ...@@ -37,7 +37,7 @@ def get_data():
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 e.y,e.z,e.stat_date,e.ucity_id,feat.level2_ids,e.ccity_name,u.device_type,u.manufacturer," \ sql = "select e.y,e.z,e.stat_date,e.ucity_id,feat.level2_ids,e.ccity_name,u.device_type,u.manufacturer," \
"u.channel,c.top,e.device_id,cut.time,dl.app_list,e.diary_service_id,feat.level3_ids,feat.level2," \ "u.channel,c.top,e.device_id,cut.time,dl.app_list,e.diary_service_id,feat.level3_ids,feat.level2," \
"wiki.tag,question.tag,search.tag,order_tag.tag " \ "wiki.tag,question.tag,search.tag,budan.tag,order_tag.tag,sixin.tag,cart.tag " \
"from {} e left join user_feature u on e.device_id = u.device_id " \ "from {} e left join user_feature u on e.device_id = u.device_id " \
"left join cid_type_top c on e.device_id = c.device_id " \ "left join cid_type_top c on e.device_id = c.device_id " \
"left join cid_time_cut cut on e.cid_id = cut.cid " \ "left join cid_time_cut cut on e.cid_id = cut.cid " \
...@@ -46,17 +46,14 @@ def get_data(): ...@@ -46,17 +46,14 @@ def get_data():
"left join wiki_tag wiki on e.device_id = wiki.device_id " \ "left join wiki_tag wiki on e.device_id = wiki.device_id " \
"left join question_tag question on e.device_id = question.device_id " \ "left join question_tag question on e.device_id = question.device_id " \
"left join search_tag search on e.device_id = search.device_id " \ "left join search_tag search on e.device_id = search.device_id " \
"left join budan_tag budan on e.device_id = budan.device_id " \
"left join order_tag on e.device_id = order_tag.device_id " \ "left join order_tag on e.device_id = order_tag.device_id " \
"left join sixin_tag sixin on e.device_id = sixin.device_id " \
"left join cart_tag cart on e.device_id = cart.device_id " \
"where e.stat_date >= '{}'".format(train_data_set, start) "where e.stat_date >= '{}'".format(train_data_set, start)
# "left join budan_tag budan on e.device_id = budan.device_id " \
# , , sixin.tag, cart.tag
# " " \
# "left join sixin_tag sixin on e.device_id = sixin.device_id " \
# "left join cart_tag cart on e.device_id = cart.device_id "
df = con_sql(db, sql) df = con_sql(db, sql)
# print(df.shape) print(df.shape)
df = df.rename(columns={0: "y", 1: "z", 2: "stat_date", 3: "ucity_id", 4: "clevel2_id", 5: "ccity_name", df = df.rename(columns={0: "y", 1: "z", 2: "stat_date", 3: "ucity_id", 4: "clevel2_id", 5: "ccity_name",
6: "device_type", 7: "manufacturer", 8: "channel", 9: "top", 10: "device_id", 6: "device_type", 7: "manufacturer", 8: "channel", 9: "top", 10: "device_id",
11: "time", 12: "app_list", 13: "service_id", 14: "level3_ids", 15: "level2", 11: "time", 12: "app_list", 13: "service_id", 14: "level3_ids", 15: "level2",
......
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