ppg_synthetic

logger = helia.utils.setup_logger(__name__)

PpgSyntheticParams()

PPG Synthetic signal generator parameters

sample_rate: float = Field(500, description='Signal sample rate (Hz)')

duration: int = Field(10, description='Signal duration in sec')

heart_rate: tuple[float, float] = Field((40, 120), description='Heart rate range')

frequency_modulation: tuple[float, float] = Field((0.2, 0.4), description='Frequency modulation strength [0,1]')

ibi_randomness: tuple[float, float] = Field((0.05, 0.15), description='IBI randomness in range [0,1]')

noise_multiplier: tuple[float, float] = Field((0, 0), description='Noise multiplier range')

PpgSyntheticDataset(
    num_pts: int = 250,
    params: dict | None = None,
    path: str = Path(tempfile.gettempdir()) / 'ppg-synthetic',
    **kwargs={},
) -> None

PPG synthetic dataset creates 1-lead PPG signal using physioKIT.

Example:

import heartkit as hk

# Create synthetic PPG dataset:
# - 10 patients
# - 500 Hz sample rate
# - 10 sec duration
# - heart rate between 40 and 120 bpm
# - frequency modulation between 0.2 and 0.4
# - IBI randomness between 0.05 and 0.15
# - no noise
ds = hk.datasets.PpgSyntheticDataset(
    num_pts=10,
    params=dict(
        sample_rate=500,
        duration=10,
        heart_rate=(40, 120),
        frequency_modulation=(0.2, 0.4),
        ibi_randomness=(0.05, 0.15),
        noise_multiplier=(0, 0),
    )
)

with ds.patient_data[ds.patient_ids[0]] as pt:
    ppg = pt["data"][:]
    segs = pt["segmentations"][:]
    fids = pt["fiducials"][:]
# END WITH

Parameters

Parameters of PpgSyntheticDataset
Name	Type	Default	Description
`num_pts`	`int`	250	Number of patients. Defaults to 250.
`params`	`dict \| None`	None	PPG synthetic parameters (PpgSyntheticParams). Defaults to None.
`path`	`str`	Path(tempfile.gettempdir()) / 'ppg-synthetic'	Path to dataset. Defaults to Path(tempfile.gettempdir()) / "ppg-synthetic".

params = PpgSyntheticParams(**params or {})

name: str

Dataset name

sampling_rate: int

Sampling rate in Hz

mean: float

Dataset mean

std: float

Dataset st dev

patient_ids: npt.NDArray

Get dataset patient IDs

get_train_patient_ids() -> npt.NDArray

Get dataset training patient IDs

Returns

Returns of get_train_patient_ids
Type	Description
`npt.NDArray`	npt.NDArray: patient IDs

get_test_patient_ids() -> npt.NDArray

Get dataset patient IDs reserved for testing only

Returns

Returns of get_test_patient_ids
Type	Description
`npt.NDArray`	npt.NDArray: patient IDs

pt_key(patient_id: int)

Get patient key

load_patient_data(patient_id: int)

build_cache()

Build cache

patient_data(patient_id: int) -> Generator[PatientData, None, None]

Get patient data

Parameters

Parameters of patient_data
Name	Type	Default	Description
`patient_id`	`int`	Required	Patient ID

Returns

Returns of patient_data
Type	Description
`None`	Generator[PatientData, None, None]: Patient data

signal_generator(
    patient_generator: PatientGenerator,
    frame_size: int,
    samples_per_patient: int = 1,
    target_rate: int | None = None,
) -> Generator[npt.NDArray, None, None]

Generate frames using patient generator.

Parameters

Parameters of signal_generator
Name	Type	Default	Description
`patient_generator`	`PatientGenerator`	Required	Generator that yields patient data.
`frame_size`	`int`	Required	Frame size
`samples_per_patient`	`int`	1	Samples per patient. Defaults to 1.
`target_rate`	`int \| None`	None	Target rate. Defaults to None.

Returns

Returns of signal_generator
Value	Type	Description
`SampleGenerator`	`None`	Generator of input data of shape (frame_size, 1)

download(num_workers: int | None = None, force: bool = False)

Download dataset

Parameters

Parameters of download
Name	Type	Default	Description
`num_workers`	`int \| None`	None	# parallel workers. Defaults to None.
`force`	`bool`	False	Force redownload. Defaults to False.

close()

Close dataset

add_noise(ppg: npt.NDArray)

Add noise to PPG signal.