Pad#

class mobgap.data_transform.Pad( pad_len_s: float | tuple[float, float], *, mode: str = 'reflect', constant_values: float | Sequence[float] | None = None, )[source]#

Pad the input data using various padding strategies.

Under the hood we use the numpy.pad function to pad the data.

Parameters:

pad_len_s: Padding len in seconds. If a single value is given, the same padding is applied to the beginning and end of the data. If a tuple is given, the first value is used for the beginning and the second for the end. The value is converted to samples using the sampling rate of the data.
mode: Padding mode. See numpy.pad for more information.
constant_values: The constant value to use for padding in case mode is constant. See numpy.pad for more information.

Other Parameters:

data: The raw data passed to the transform method. This can either be a dataframe, a series, or a numpy array.
sampling_rate_hz: The sampling rate of the IMU data in Hz passed to the transform method.

Attributes:

transformed_data_: The transformed data. The datatype matches the datatype of the passed data.
pad_len_samples_: The calculated padding len in samples as calculated from the provided pad_len_s and the sampling rate.

Notes

We don’t yet support all padding modes. Please open an issue if you need support for a specific mode.

Methods

`clone`()	Create a new instance of the class with all parameters copied over.
`get_inverse_transformer`()	Get the inverse transformer for the padding.
`get_params`([deep])	Get parameters for this algorithm.
`set_params`(**params)	Set the parameters of this Algorithm.
`transform`(data, *[, sampling_rate_hz])	%(transform_short)s.

__init__( pad_len_s: float | tuple[float, float], *, mode: str = 'reflect', constant_values: float | Sequence[float] | None = None, ) → None[source]#

clone() → Self[source]#

Create a new instance of the class with all parameters copied over.

This will create a new instance of the class itself and all nested objects

get_inverse_transformer() → Crop[source]#

Get the inverse transformer for the padding.

This returns a Crop transformer that can be used to crop the data back to its original size.

get_params(deep: bool = True) → dict[str, Any][source]#

Get parameters for this algorithm.

Parameters:

deep: Only relevant if object contains nested algorithm objects. If this is the case and deep is True, the params of these nested objects are included in the output using a prefix like nested_object_name__ (Note the two “_” at the end)

Returns:

set_params(**params: Any) → Self[source]#

Set the parameters of this Algorithm.

To set parameters of nested objects use nested_object_name__para_name=.

transform(

data: Series | DataFrame | ndarray,

*,

sampling_rate_hz: float | None = None,

**_: Unpack[dict[str, Any]],

) → Self[source]#

%(transform_short)s.

Parameters: