change eda

tensnsorflow/eda.py

@@ -17,7 +17,7 @@ def con_sql(db, sql):
 def test(days):
     start = (temp - datetime.timedelta(days)).strftime("%Y-%m-%d")
     print(start)
-    sql = "select (select count(*) from train_data where stat_date = '{}' and y = 0)/(select count(*) " \
+    sql = "select (select count(*) from esmm_train_data where stat_date = '{}' and y = 0)/(select count(*) " \
           "from train_data where stat_date = '{}' and z = 1)".format(start,start)
     db = pymysql.connect(host='10.66.157.22', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='jerry_test')
     exp = con_sql(db, sql)
@@ -31,7 +31,7 @@ def test(days):
 if __name__ == "__main__":
     temp = datetime.datetime.strptime("2019-03-14", "%Y-%m-%d")
     DIRECTORY_PATH = "/home/gmuser/"
-    output_path = DIRECTORY_PATH + "eda.csv"
+    output_path = DIRECTORY_PATH + "esmm_train_eda.csv"
     for i in range(1,41):
         a,b,c = test(i)
         with open(output_path, 'a+') as f:

tensnsorflow/es/feature.py

@@ -115,7 +115,7 @@ def get_predict(date,value_map):
           "from esmm_pre_data 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_level2 cl on e.cid_id = cl.cid " \
-          "left join cid_time_cut cut on e.cid_id = cut.cid"
+          "left join cid_time_cut cut on e.cid_id = cut.cid limit 6"
     df = con_sql(db, sql)
     df = df.rename(columns={0: "y", 1: "z", 2: "label", 3: "ucity_id", 4: "clevel1_id", 5: "ccity_name",
                             6: "device_type", 7: "manufacturer", 8: "channel", 9: "top", 10: "l1",11:"l2",