SeasonalNaiveForecaster

class omnicast.SeasonalNaiveForecaster(seasonal_period)

Bases: BaseForecaster

Repeat values from the latest seasonal cycle.

Examples

>>> import pandas as pd
>>> from omnicast import SeasonalNaiveForecaster
>>> y = pd.Series([10.0, 20.0, 15.0, 25.0, 11.0, 21.0, 16.0, 26.0])
>>> model = SeasonalNaiveForecaster(seasonal_period=4).fit(y)
>>> model.predict(horizon=4).mean.round(2).tolist()
[11.0, 21.0, 16.0, 26.0]

Notes

When to use this model

Best for	The baseline to beat whenever a series has real seasonal structure; captures the seasonal swing for free
Avoid when	The series has no repeating cycle, or a trend on top of the cycle that repeating last year’s values would miss
Handles trend	No
Handles seasonality	Yes (repeats the last full cycle)
Extra dependencies	None
Min. observations	seasonal_period + 1

Parameters:

seasonal_period (int)

fit(y, X=None)

Return type:

BaseForecaster

Parameters:

• y (Iterable[float] | Series)

• X (object)

fit_predict(y, horizon, **kwargs)

Return type:

ForecastResult

Parameters:

• y (Iterable[float] | Series)

• horizon (int)

• kwargs (object)

get_params()

Return type:

dict[str, object]

predict(horizon, X=None, level=(80, 95))

Return type:

ForecastResult

Parameters:

• horizon (int)

• X (object)

• level (float | Iterable[float])

Repeats the value from the same point in the last full seasonal cycle instead of just the last observation. It’s the baseline to beat whenever a series has real seasonal structure – NaiveForecaster will systematically miss the seasonal swing that this model captures for free.

from omnicast import SeasonalNaiveForecaster

model = SeasonalNaiveForecaster(seasonal_period=12).fit(y)
forecast = model.predict(horizon=6, level=[80, 95])
print(forecast.to_frame())

          mean  lower_80  upper_80  lower_95  upper_95
2026-01  179.1    145.05    213.15    127.02    231.18
2026-02  189.2    155.15    223.25    137.12    241.28
2026-03  192.8    158.75    226.85    140.72    244.88
2026-04  197.6    163.55    231.65    145.52    249.68
2026-05  198.6    164.55    232.65    146.52    250.68
2026-06  196.3    162.25    230.35    144.22    248.38

Each forecast reuses the corresponding month from 2025. Intervals scale with sqrt(sigma2 * cycles_ahead), so the January-2026 forecast (one cycle ahead of the December-2025 cutoff for that month) has a narrower interval than a forecast two full cycles out would.

seasonal_period is required and validated eagerly: constructing SeasonalNaiveForecaster(seasonal_period=0) raises ValueError before fit is ever called. fit additionally requires len(y) > seasonal_period – at least one full cycle of history.