修改luj

eda/esmm/Model_pipline/to_database.py

@@ -36,10 +36,10 @@ def native_set_join(lst):
 def main():
 
     # native queue
-    df2 = pd.read_csv('/data/esmm/native.csv')
+    df2 = pd.read_csv(path+'/native.csv')
     df2['cid_id'] = df2['cid_id'].astype(str)
 
-    df1 = pd.read_csv("/data/esmm/native/pred.txt",sep='\t',header=None,names=["ctr","cvr","ctcvr"])
+    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.columns = ["device_id","city_id","native_queue"]
@@ -47,10 +47,10 @@ def main():
 
 
     # nearby queue
-    df2 = pd.read_csv('/data/esmm/nearby.csv')
+    df2 = pd.read_csv(path+'/nearby.csv')
     df2['cid_id'] = df2['cid_id'].astype(str)
 
-    df1 = pd.read_csv("/data/esmm/nearby/pred.txt",sep='\t',header=None,names=["ctr","cvr","ctcvr"])
+    df1 = pd.read_csv(path+"/nearby/pred.txt",sep='\t',header=None,names=["ctr","cvr","ctcvr"])
     df2["ctr"], df2["cvr"], df2["ctcvr"] = df1["ctr"], df1["cvr"], df1["ctcvr"]
     df4 = 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':nearby_set_join}).reset_index(drop=False)
     df4.columns = ["device_id","city_id","nearby_queue"]
@@ -87,5 +87,7 @@ def main():
 
     print("done")
 
+
 if __name__ == '__main__':
+    path = "/home/gmuser/esmm"
     main()
\ No newline at end of file