Skip to content

bidmc

Classes

BidmcDataset 

BidmcDataset(leads: list[int] | None = None, **kwargs)

BIDMC dataset

Source code in heartkit/datasets/bidmc.py 
24
25
26
27
28
29
30
def __init__(
    self,
    leads: list[int] | None = None,
    **kwargs,
) -> None:
    super().__init__(**kwargs)
    self.leads = leads or list(BidmcLeadsMap.values())

Attributes

name property 
name: str

Dataset name

sampling_rate property 
sampling_rate: int

Sampling rate in Hz

mean property 
mean: float

Dataset mean

std property 
std: float

Dataset st dev

patient_ids cached property 
patient_ids: NDArray

Get dataset patient IDs

Returns:

  • NDArray –

    npt.NDArray: patient IDs

Functions

get_train_patient_ids 
get_train_patient_ids() -> npt.NDArray

Get dataset training patient IDs

Returns:

  • NDArray –

    npt.NDArray: patient IDs

Source code in heartkit/datasets/bidmc.py 
62
63
64
65
66
67
68
69
def get_train_patient_ids(self) -> npt.NDArray:
    """Get dataset training patient IDs

    Returns:
        npt.NDArray: patient IDs
    """
    idx = int(len(self.patient_ids) * 0.80)
    return self.patient_ids[:idx]
get_test_patient_ids 
get_test_patient_ids() -> npt.NDArray

Get dataset patient IDs reserved for testing only

Returns:

  • NDArray –

    npt.NDArray: patient IDs

Source code in heartkit/datasets/bidmc.py 
71
72
73
74
75
76
77
78
def get_test_patient_ids(self) -> npt.NDArray:
    """Get dataset patient IDs reserved for testing only

    Returns:
        npt.NDArray: patient IDs
    """
    idx = int(len(self.patient_ids) * 0.80)
    return self.patient_ids[idx:]
patient_data 
patient_data(patient_id: int) -> Generator[h5py.Group, None, None]

Get patient data

Parameters:

  • patient_id
    (int) –

    Patient ID

Returns:

  • None –

    Generator[h5py.Group, None, None]: Patient data

Source code in heartkit/datasets/bidmc.py 
84
85
86
87
88
89
90
91
92
93
94
95
@contextlib.contextmanager
def patient_data(self, patient_id: int) -> Generator[h5py.Group, None, None]:
    """Get patient data

    Args:
        patient_id (int): Patient ID

    Returns:
        Generator[h5py.Group, None, None]: Patient data
    """
    with h5py.File(self.path / f"{self._pt_key(patient_id)}.h5", mode="r") as h5:
        yield h5
signal_generator 
signal_generator(
    patient_generator: PatientGenerator, frame_size: int, samples_per_patient: int = 1, target_rate: int | None = None
) -> Generator[npt.NDArray, None, None]

Generate random frames.

Parameters:

  • patient_generator
    (PatientGenerator) –

    Patient Generator

  • frame_size
    (int) –

    Frame size

  • samples_per_patient
    (int, default: 1 ) –

    Samples per patient. Defaults to 1.

  • target_rate
    (int, default: None ) –

    Target rate. Defaults to None.

Returns:

  • None –

    Generator[npt.NDArray, None, None]: Generator of input data

Source code in heartkit/datasets/bidmc.py 
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
def signal_generator(
    self,
    patient_generator: PatientGenerator,
    frame_size: int,
    samples_per_patient: int = 1,
    target_rate: int | None = None,
) -> Generator[npt.NDArray, None, None]:
    """Generate random frames.

    Args:
        patient_generator (PatientGenerator): Patient Generator
        frame_size (int): Frame size
        samples_per_patient (int, optional): Samples per patient. Defaults to 1.
        target_rate (int, optional): Target rate. Defaults to None.

    Returns:
        Generator[npt.NDArray, None, None]: Generator of input data
    """
    if target_rate is None:
        target_rate = self.sampling_rate

    input_size = int(np.ceil((self.sampling_rate / target_rate) * frame_size))
    for pt in patient_generator:
        with self.patient_data(pt) as h5:
            data: h5py.Dataset = h5["data"][:]
        # END WITH
        for _ in range(samples_per_patient):
            lead = random.choice(self.leads)
            start = np.random.randint(0, data.shape[1] - input_size)
            x = data[lead, start : start + input_size].squeeze()
            x = np.nan_to_num(x).astype(np.float32)
            if self.sampling_rate != target_rate:
                x = pk.signal.resample_signal(x, self.sampling_rate, target_rate, axis=0)
                x = x[:frame_size]
            # END IF
            yield x
download 
download(num_workers: int | None = None, force: bool = False)

Download dataset

This will download preprocessed HDF5 files from S3.

Parameters:

  • num_workers
    (int | None, default: None ) –
    parallel workers. Defaults to None.
  • force
    (bool, default: False ) –

    Force redownload. Defaults to False.

Source code in heartkit/datasets/bidmc.py 
136
137
138
139
140
141
142
143
144
145
def download(self, num_workers: int | None = None, force: bool = False):
    """Download dataset

    This will download preprocessed HDF5 files from S3.

    Args:
        num_workers (int | None, optional): # parallel workers. Defaults to None.
        force (bool, optional): Force redownload. Defaults to False.
    """
    raise NotImplementedError("Download not implemented for BIDMC dataset")