Forecast a univariate series using Chronax

This guide shows you how to initialize a model, fit it to historical data, and generate future predictions for a single time series. Use this approach when you have a standard time series forecasting problem without exogenous variables.

Prerequisites

Chronax installed (pip install chronax).
import jax.numpy as jnp for array handling.
Your historical data y must be a 1-D jnp.ndarray of type float32.

Steps

1. Prepare the data

Define your historical time series data y. Chronax models expect JAX arrays.

import jax.numpy as jnp
# Example: 100 historical observations
y = jnp.array([
    10.1, 10.5, 10.3, 10.8, 11.0, 11.2, 11.5, 11.3, 11.7, 12.0
], dtype=jnp.float32)
# In a real scenario, y would contain hundreds or thousands of points.

2. Initialize the forecasting model

Import and instantiate a Chronax model. We will use AutoARIMA as a robust baseline model.

from chronax.models import AutoARIMA

# Initialize the model.
# TODO: confirm AutoARIMA constructor arguments against the API
model = AutoARIMA()

3. Fit the model to the historical data

Use the fit method, passing only the historical series y.

# Fit the model. The model learns the parameters from the data.
# The fit method returns the fitted model instance.
fitted_model = model.fit(y)

4. Generate the forecast

Use the predict method on the fitted model, specifying the forecast horizon h (the number of steps into the future you want to predict).

# Forecast 5 steps into the future (h=5)
h = 5
out = fitted_model.predict(h=h)

# The result is a dictionary. Access the mean forecast array:
forecast_mean = out["mean"]

print(f"Forecasted values for the next {h} steps:")
print(forecast_mean)

Full example

import jax.numpy as jnp
from chronax.models import AutoARIMA

# 1. Prepare the data
y = jnp.array([
    10.1, 10.5, 10.3, 10.8, 11.0, 11.2, 11.5, 11.3, 11.7, 12.0,
    12.2, 12.5, 12.3, 12.8, 13.0, 13.2, 13.5, 13.3, 13.7, 14.0
], dtype=jnp.float32)

# 2. Initialize the forecasting model
# TODO: confirm AutoARIMA constructor arguments against the API
model = AutoARIMA()

# 3. Fit the model to the historical data
fitted_model = model.fit(y)

# 4. Generate the forecast
h = 5
out = fitted_model.predict(h=h)

forecast_mean = out["mean"]

print(f"Historical data length: {len(y)}")
print(f"Forecast horizon (h): {h}")
print(f"Forecast mean: {forecast_mean}")

Next steps

Learn how to add prediction intervals using the level argument in predict.
Explore other models in chronax.models, such as ETS or TFT.
Understand the model.forecast() method for combined fitting and prediction.
See how to incorporate exogenous features using the X argument in fit.