search

Nixtla / nixtla

TimeGPT-1: production ready pre-trained Time Series Foundation Model for forecasting and anomaly detection. Generative pretrained transformer for time series trained on over 100B data points. It's capable of accurately predicting various domains such as retail, electricity, finance, and IoT with just a few lines of code 🚀.
https://docs.nixtla.io
Other
1.91k stars 151 forks source link

status_code: 400 #203

Closed lihuang218 closed 2 months ago

lihuang218 commented 6 months ago

nixtlats.core.api_error.ApiError: status_code: 400, body: {'data': None, 'message': None, 'details': None, 'code': None, 'requestID': 'DK974MT6N3', 'support': 'If you have questions or need support, please email ops@nixtla.io'} 1704179538174

AzulGarza commented 6 months ago

hey @lihuang218, thanks for using TimeGPT. we experienced some intermittency in previous days. could you try again? :)

AlbertoLanaro commented 5 months ago

I'm having the same problem now

Output of the script:

INFO:nixtlats.timegpt:Calling Forecast Endpoint...
INFO:nixtlats.timegpt:Attempt 1 failed...
INFO:nixtlats.timegpt:Attempt 2 failed...
INFO:nixtlats.timegpt:Attempt 3 failed...
INFO:nixtlats.timegpt:Attempt 4 failed...
INFO:nixtlats.timegpt:Attempt 5 failed...
INFO:nixtlats.timegpt:Attempt 6 failed...

Error:

ApiError: status_code: 400, body: <!DOCTYPE html>
<html lang="en">
<head>
<meta charset="utf-8">
<title>Error</title>
</head>
<body>
<pre>Bad Request</pre>
</body>
</html>
zhongguojunhun1 commented 4 months ago

nixtlats.core.api_error.ApiError: status_code: 400, body: {'data': None, 'message': None, 'details': None, 'code': None, 'requestID': 'DK974MT6N3', 'support': 'If you have questions or need support, please email ops@nixtla.io'} 1704179538174 I also encountered the same problem. Have you solved it?

Tingji2419 commented 2 months ago

Me too. I've checked the network and my token validation. Still get the info :INFO:nixtlats.nixtla_client:Validating inputs... INFO:nixtlats.nixtla_client:Preprocessing dataframes... INFO:nixtlats.nixtla_client:Restricting input... INFO:nixtlats.nixtla_client:Calling Forecast Endpoint... INFO:nixtlats.nixtla_client:Attempt 1 failed... INFO:nixtlats.nixtla_client:Attempt 2 failed... INFO:nixtlats.nixtla_client:Attempt 3 failed... INFO:nixtlats.nixtla_client:Attempt 4 failed... INFO:nixtlats.nixtla_client:Attempt 5 failed... INFO:nixtlats.nixtla_client:Attempt 6 failed...

Tingji2419 commented 2 months ago

I've solved my problem. It was due to the incorrect form of the timestamp column ('ds' column). It should be in 'xxxx-xx-xx 00:00:00' but not 'xxxx/xx/xx 0:00'.

When using original data with 'ds' column of ''xxxx/xx/xx 0:00'', it reported error: Exception: Could not infer frequency of ds column. . This could be due to inconsistent intervals. Please check your data for missing, duplicated or irregular timestamps

And then i specified the freq='M', it reported error likes: INFO:nixtlats.nixtla_client:Attempt 1 failed.

Final i reform the 'ds' columns to 'xxxx/xx/xx 0:00' without specified the freq, it fixed.