Closed LgSouza19 closed 3 months ago
maybe check your data-structure:
print(df.dtypes)
WRONG - Format:
unique_id object ds object y object
y should be float64
RIGHT- Format:
unique_id object ds object y float64
I have the same issue:
timegpt_anomalies_df = timegpt.detect_anomalies(df, time_col='ds', target_col='y', freq='15T')
timegpt_anomalies_df.head()
df.info()
DatetimeIndex: 35031 entries, 2023-01-01 00:00:00 to 2023-12-31 23:45:00
Data columns (total 7 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 y 35031 non-null float64
1 DRZ (betrieblich) [MW] 35031 non-null float64
2 DRZ (abrechnungsrelevant) [MW] 35031 non-null float64
3 Ungewollter Austausch [MW] 35031 non-null float64
4 TRR für AT [MW] 35031 non-null float64
5 ds 35031 non-null datetime64[ns]
returns:
ApiError: status_code: 500, body: {'data': None, 'message': 'Request failed with status code 500', 'code': 'B30', 'requestID': '5433HPFBJY', 'support': 'If you have questions or need support, please email ops@nixtla.io'}
Hey @RoelofKuipers. I think this is due to the names of your features, can you try removing the square brackets? e.g. replace TRR für AT [MW]
with TRR für AT (MW)
.
This should be fixed now. Feel free to reopen if you encounter this error again.
Getting the following error while trying to run a forecast with country holidays set for Turkey, basic codes below the error.
ApiError: status_code: 500, body: {'data': None, 'message': 'Request failed with status code 500', 'code': 'B30', 'requestID': 'VPXXBHV867', 'support': 'If you have questions or need support, please email ops@nixtla.io'}