ApiError: status_code: 500

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 🚀.

Other

1.91k stars 151 forks source link

ApiError: status_code: 500, body: {'data': None, 'message': 'Request failed with status code 500', 'code': 'B30', 'requestID': 'ZQBEUBHYQT', 'support': 'If you have questions or need support, please email [ops@nixtla.io](mailto:ops@nixtla.io)'}

I'm trying to just implement a minimal example but getting this error - any idea why that might be?

Here is my example:

import pandas as pd
import numpy as np
from nixtlats import TimeGPT

num_rows = 5000
start_time = pd.Timestamp.now().floor('T')
timestamps = pd.date_range(start=start_time, periods=num_rows, freq='T')
metric_values = np.random.random(size=num_rows)

df = pd.DataFrame({'metric_timestamp': timestamps, 'metric_value': metric_values})

df = df.set_index('metric_timestamp').resample('1H').mean().reset_index()

print(df.shape)
print(df.head())

timegpt = TimeGPT(token='XXX')
timegpt_anomalies_df = timegpt.detect_anomalies(
    df, 
    time_col='metric_timestamp', 
    target_col='metric_value', 
    freq='1H'
)
print(timegpt_anomalies_df.head())

Nixtla / nixtla

ApiError: status_code: 500 #162