Quickstart guide to deploy and use TimeGEN-1 on Azure with the Nixtla Python SDK for time series forecasting.
Step 1: Set up a TimeGEN-1 endpoint on Azure and generate an API key
TimeGEN-1 model catalog deployment option.
Endpoint URL and API key for TimeGEN-1.
Step 2: Install Nixtla Python SDK
Step 3: Import and instantiate the Nixtla client
Step 4: Load your time series data
AirPassengers time series sample visualized.
Data Requirements
Saving Figures
Step 5: Generate forecasts
forecast
method from the Nixtla client to forecast the next 12 months.df
: Pandas DataFrame with time series data\• h
: Forecast horizon (number of steps ahead)\• freq
: Time series frequency (pandas frequency aliases)\• time_col
: Name of timestamp column\• target_col
: Name of forecast variableForecast API Call Log
timestamp | TimeGPT | |
---|---|---|
0 | 1961-01-01 | 437.837921 |
1 | 1961-02-01 | 426.062714 |
2 | 1961-03-01 | 463.116547 |
3 | 1961-04-01 | 478.244507 |
4 | 1961-05-01 | 505.646484 |
Forecast visualization for the AirPassengers dataset.