BandPass#

class torch_ecg._preprocessors.BandPass(lowcut: int | float | None = 0.5, highcut: int | float | None = 45, filter_type: Literal['butter', 'fir'] = 'butter', filter_order: int | None = None, **kwargs: Any)[source]#

Bases: PreProcessor

Bandpass filtering preprocessor.

Parameters:

  • lowcut (int or float, optional) – Low cutoff frequency

  • highcut (int or float, optional) – High cutoff frequency.

  • filter_type ({"butter", "fir"}, , default "butter") – Type of the bandpass filter.

  • filter_order (int, optional) – Order of the bandpass filter.

  • **kwargs (dict, optional) – Other arguments for PreProcessor.

Examples

from torch_ecg.cfg import DEFAULTS
sig = DEFAULTS.RNG.randn(1000)
pp = BandPass(lowcut=0.5, highcut=45, filter_type="butter", filter_order=4)
sig, _ = pp(sig, 500)
apply(sig: ndarray[tuple[Any, ...], dtype[_ScalarT]], fs: int | float) → Tuple[ndarray[tuple[Any, ...], dtype[_ScalarT]], int | float][source]#

Apply the preprocessor to sig.

Parameters:

  • sig (numpy.ndarray) – The ECG signal, can be - 1d array, which is a single-lead ECG; - 2d array, which is a multi-lead ECG of “lead_first” format; - 3d array, which is a tensor of several ECGs, of shape (batch, lead, siglen).

  • fs (int or float) – Sampling frequency of the ECG signal.

Returns:

  • filtered_sig (numpy.ndarray) – Bandpass filtered ECG signal.

  • fs (int) – Sampling frequency of the filtered ECG signal.

extra_repr_keys() → List[str][source]#

Extra keys for __repr__() and __str__().