Slackbot
11/28/2023, 4:43 PMJosé Morales
11/28/2023, 5:20 PMfutr_exog_list =['s_2', 's_3', 's_4', 's_7', 's_8', 's_9', 's_11',
's_12', 's_13', 's_14', 's_15', 's_17', 's_20', 's_21']
The error you're running into is because since these should be in the future we check that the ds matches what is expected, e.g. if your last training time was 200, the first future ds should be 201, etc. This tutorial was made before we had that validation, so we have to fix it. In the meantime you can offset the start timestamps in the futr_df with the following:
last_train_dates = Y_train_df.groupby('unique_id')['ds'].max().rename('last_train_ds').reset_index()
Y_test_df2 = Y_test_df.merge(last_train_dates, on=['unique_id'])
Y_test_df2['ds'] += Y_test_df2['last_train_ds']
And use futr_df=Y_test_df2
Felix Saretzky
11/28/2023, 5:52 PMJosé Morales
11/28/2023, 5:59 PMNeuralForecast(freq='min', ...)
if the data is captured every minute.Felix Saretzky
11/28/2023, 6:08 PMJosé Morales
11/28/2023, 6:10 PMFelix Saretzky
11/28/2023, 6:13 PMFelix Saretzky
11/28/2023, 6:46 PMJosé Morales
11/28/2023, 7:02 PMfutr_exog_list = ['Sensor1', 'Sensor2', ...]
otherwise you can specify them as historic only through hist_exog_list
Felix Saretzky
11/28/2023, 7:23 PMJosé Morales
11/28/2023, 7:30 PMFelix Saretzky
11/28/2023, 7:35 PMJosé Morales
11/28/2023, 7:36 PMFelix Saretzky
11/28/2023, 7:41 PMFarzad E
12/11/2023, 5:18 PMJosé Morales
12/11/2023, 5:21 PMFarzad E
12/11/2023, 5:32 PMFarzad E
12/11/2023, 5:36 PMpip install git+<https://github.com/Nixtla/neuralforecast.git>
José Morales
12/11/2023, 5:50 PMFelix Saretzky
12/12/2023, 8:21 AMFelix Saretzky
12/12/2023, 8:28 AMJosé Morales
12/12/2023, 4:00 PMFelix Saretzky
12/12/2023, 7:20 PMJosé Morales
12/12/2023, 7:26 PMFelix Saretzky
12/13/2023, 2:16 PMFelix Saretzky
12/13/2023, 2:16 PMFelix Saretzky
12/13/2023, 2:21 PMFarzad E
12/13/2023, 4:21 PMJosé Morales
12/13/2023, 4:47 PMdf
argument of predict and a futr_df
for it. The easiest way to see the expected structure is to install from github, run fit and the run the make_future_dataframe
method providing the df with your new idsFelix Saretzky
12/13/2023, 4:52 PMFarzad E
12/13/2023, 5:00 PM