Welcome to tsbootstrap’s documentation!
tsbootstrap generates bootstrap replicates of time series data. The entire
public API is one typed function, bootstrap(), configured
with a method specification object.
import numpy as np
from tsbootstrap import bootstrap, MovingBlock
x = np.random.default_rng(0).standard_normal(200)
result = bootstrap(x, method=MovingBlock(block_length="auto"), n_bootstraps=999, random_state=0)
samples = result.values() # shape (999, 200)
oob = result.get_oob_mask() # shape (999, 200) boolean out-of-bag mask
User guide
Tutorials
API reference
- bootstrap()
- Method specifications (tsbootstrap.methods)
- Results (tsbootstrap.results)
- Diagnostics (tsbootstrap.diagnostics)
- Uncertainty quantification (tsbootstrap.uq)
- sktime adapters (tsbootstrap.adapters)
BaseTimeSeriesBootstrapIIDBootstrapMovingBlockBootstrapCircularBlockBootstrapStationaryBlockBootstrapNonOverlappingBlockBootstrapTaperedBlockBootstrapARResidualBootstrapARIMAResidualBootstrapVARResidualBootstrapSieveBootstrapBaseTimeSeriesBootstrapIIDBootstrapMovingBlockBootstrapCircularBlockBootstrapStationaryBlockBootstrapNonOverlappingBlockBootstrapTaperedBlockBootstrapARResidualBootstrapARIMAResidualBootstrapVARResidualBootstrapSieveBootstrap
- Errors and warnings (tsbootstrap.errors)