change test file

eda/esmm/Model_pipline/submit.sh

@@ -29,4 +29,6 @@ echo "sort and 2sql"
 ${PYTHON_PATH} ${MODEL_PATH}/to_database.py > "/home/gmuser/esmm/log/insert_$b.log"
 
 echo "delete files"
-
+rm /home/gmuser/esmm/*.csv
+rm /home/gmuser/esmm/native/*
+rm /home/gmuser/esmm/nearby/*
\ No newline at end of file

eda/esmm/Model_pipline/to_database.py

@@ -39,7 +39,8 @@ def main():
 
     df1 = pd.read_csv(path+"/native/pred.txt",sep='\t',header=None,names=["ctr","cvr","ctcvr"])
     df2["ctr"],df2["cvr"],df2["ctcvr"] = df1["ctr"],df1["cvr"],df1["ctcvr"]
-    df3 = df2.groupby(by=["uid","city"]).apply(lambda x: x.sort_values(by="ctcvr",ascending=False)).reset_index(drop=True).groupby(by=["uid","city"]).agg({'cid_id':native_set_join}).reset_index(drop=False)
+    df3 = df2.groupby(by=["uid","city"]).apply(lambda x: x.sort_values(by="ctcvr",ascending=False))\
+        .reset_index(drop=True).groupby(by=["uid","city"]).agg({'cid_id':native_set_join}).reset_index(drop=False)
     df3.columns = ["device_id","city_id","native_queue"]
     print("native_device_count",df3.shape)