model.selection

model.selection

Compatibility helpers for array-based model selection.

Aligned financial datasets and split metadata are owned by :mod:qrt.dataset. This module retains an array-index generator for callers that need sklearn’s native interface.

q.model.selection.timeseries_split(X, n_splits=5, gap=5)

Examples

>>> for train_idx, test_idx in q.model.selection.timeseries_split(X, n_splits=5):
...     ...

Functions

Name	Description
timeseries_split	Yield sklearn expanding or rolling train/test position arrays.

timeseries_split

model.selection.timeseries_split(
    X,
    n_splits=5,
    *,
    max_train_size=None,
    test_size=None,
    gap=0,
)

Yield sklearn expanding or rolling train/test position arrays.

Use :class:qrt.dataset.TimeSeriesSplit when aligned features, targets, metadata, named partitions, diagnostics, or purging are required.