DiscreteFourierTransform

class pyts.approximation.DiscreteFourierTransform(n_coefs: int | float | None = None, drop_sum: bool = False, anova: bool = False, norm_mean: bool = False, norm_std: bool = False)

Discrete Fourier Transform.

Parameters:

n_coefsNone, int or float (default = None)

The number of Fourier coefficients to keep. If None, all the Fourier coeeficients are kept. If an integer, the n_coefs most significant Fourier coefficients are returned if anova=True, otherwise the first n_coefs Fourier coefficients are returned. If a float, it represents a percentage of the size of each time series and must be between 0 and 1. The number of coefficients will be computed as ceil(n_coefs * (n_timestamps - 1)) if drop_sum=True and ceil(n_coefs * n_timestamps) if drop_sum=False.

drop_sumbool (default = False)

If True, the first Fourier coefficient (i.e. the sum of the subseries) is dropped. Otherwise, it is kept.

anovabool (default = False)

If True, the Fourier coefficient selection is done via a one-way ANOVA test. If False, the first Fourier coefficients are selected.

norm_meanbool (default = False)

If True, center each time series before scaling.

norm_stdbool (default = False)

If True, scale each time series to unit variance.

Attributes:

support_array, shape = (n_coefs,)

Indices of the kept Fourier coefficients.

References

[1]

P. Schäfer, and M. Högqvist, “SFA: A Symbolic Fourier Approximation and Index for Similarity Search in High Dimensional Datasets”, International Conference on Extending Database Technology, 15, 516-527 (2012).

Examples

>>> from pyts.approximation import DiscreteFourierTransform
>>> from pyts.datasets import load_gunpoint
>>> X, _, _, _ = load_gunpoint(return_X_y=True)
>>> transformer = DiscreteFourierTransform(n_coefs=4)
>>> X_new = transformer.fit_transform(X)
>>> X_new.shape
(50, 4)

Methods

__init__([n_coefs, drop_sum, anova, ...])
fit(X[, y])	Learn indices of the Fourier coefficients to keep.
fit_transform(X[, y])	Learn and return the Fourier coeeficients to keep.
get_metadata_routing()	Get metadata routing of this object.
get_params([deep])	Get parameters for this estimator.
set_params(**params)	Set the parameters of this estimator.
transform(X)	Return the selected Fourier coefficients for each sample.

__init__(n_coefs: int | float | None = None, drop_sum: bool = False, anova: bool = False, norm_mean: bool = False, norm_std: bool = False) → None

fit(X: ArrayLike, y: ArrayLike | None = None) → Self

Learn indices of the Fourier coefficients to keep.

Parameters:

Xarray-like, shape = (n_samples, n_timestamps)

Training vector.

yNone or array-like, shape = (n_samples,) (default = None)

Class labels for each data sample. Only used if anova=True.

Returns:

selfobject

fit_transform(X: ArrayLike, y: ArrayLike | None = None) → NDArray[float64]

Learn and return the Fourier coeeficients to keep.

Parameters:

Xarray-like, shape = (n_samples, n_timestamps)

Training vector, where n_samples in the number of samples and n_features is the number of features.

yNone or array-like, shape = (n_samples,) (default = None)

Class labels for each data sample.

Returns:

X_newarray, shape (n_samples, n_coefs)

The selected Fourier coefficients for each sample.

transform(X: ArrayLike) → NDArray[float64]

Return the selected Fourier coefficients for each sample.

Parameters:

Xarray-like, shape (n_samples, n_timestamps)

Input data.

Returns:

X_newarray, shape (n_samples, n_coefs)

The selected Fourier coefficients for each sample.

Examples using pyts.approximation.DiscreteFourierTransform

Discrete Fourier Transform

Discrete Fourier Transform