real data to test dist predict

eda/esmm/Model_pipline/dist_predict.py

@@ -304,7 +304,7 @@ if __name__ == "__main__":
         df3 = nearby_data.groupby(by=["uid1", "city1"]).apply(lambda x: x.sort_values(by="ctcvr", ascending=False)) \
             .reset_index(drop=True).groupby(by=["uid1", "city1"]).agg({'cid_id1': set_join}).reset_index(drop=False)
         df3.columns = ["device_id", "city_id", "native_queue"]
-        print("native_device_count", df3.shape)
+        print("nearby_device_count", df3.shape)
 
         # print(nearby_data.head())
         # print(nearby_data.dtypes)
@@ -328,7 +328,7 @@ if __name__ == "__main__":
         df4 = native_data_pd.groupby(by=["uid1", "city1"]).apply(lambda x: x.sort_values(by="ctcvr", ascending=False)) \
             .reset_index(drop=True).groupby(by=["uid1", "city1"]).agg({'cid_id1': set_join}).reset_index(drop=False)
         df4.columns = ["device_id", "city_id", "nearby_queue"]
-        print("nearby_device_count", df4.shape)
+        print("native_device_count", df4.shape)
         # print(native_data_pd.dtypes)
 
 
@@ -376,7 +376,7 @@ if __name__ == "__main__":
         except Exception as e:
             print(e)
 
-        print("耗时(秒)：")
-        print((time.time()-b))
+        print("耗时(min)：")
+        print((time.time()-b)/60)