`elasticai.preprocessor._basics`#

Module Contents#

Classes#

`DataTransient`	Dataclass for handling the transient data inside the pipeline Attributes: data: Numpy array of the data sampling_rate: Float with sampling rate [Hz]
`DataSpectral`	Dataclass for handling the spectral data inside the pipeline Attributes: data: Numpy array of the data sampling_rate: Float with sampling rate [Hz]
`DataWaveform`	Dataclass for handling the waveform data inside the pipeline Attributes: waveform: Numpy array of the data xpos: Numpy array with positions which an event is detected label: Numpy array with labels for each event sampling_rate: Float with sampling rate [Hz]
`PreprocessingModule`

Functions#

get_path_to_project

Function for getting the path to find the project folder structure in application.

Data#

`TIn`
`TOut`

API#

elasticai.preprocessor._basics.get_path_to_project(new_folder: str = '') → pathlib.Path[source]#

Function for getting the path to find the project folder structure in application.

Parameters:: new_folder – New folder path
Returns:: String of absolute path to start the project structure

class elasticai.preprocessor._basics.DataTransient[source]#

Dataclass for handling the transient data inside the pipeline Attributes: data: Numpy array of the data sampling_rate: Float with sampling rate [Hz]

data: numpy.ndarray | Any#: None

sampling_rate: float#: None

class elasticai.preprocessor._basics.DataSpectral[source]#

Dataclass for handling the spectral data inside the pipeline Attributes: data: Numpy array of the data sampling_rate: Float with sampling rate [Hz]

data: numpy.ndarray#: None

freq: numpy.ndarray#: None

sampling_rate: float#: None

class elasticai.preprocessor._basics.DataWaveform[source]#

Dataclass for handling the waveform data inside the pipeline Attributes: waveform: Numpy array of the data xpos: Numpy array with positions which an event is detected label: Numpy array with labels for each event sampling_rate: Float with sampling rate [Hz]

waveform: numpy.ndarray#: None

xpos: numpy.ndarray#: None

label: numpy.ndarray#: None

sampling_rate: float#: None

property length: int#

property num_samples: int#

property is_data_labeled: bool#

elasticai.preprocessor._basics.TIn#: ‘TypeVar(…)’

elasticai.preprocessor._basics.TOut#: ‘TypeVar(…)’

class elasticai.preprocessor._basics.PreprocessingModule[source]#

Bases: abc.ABC, typing.Generic[elasticai.preprocessor._basics.TIn, elasticai.preprocessor._basics.TOut]

abstractmethod __call__(x: elasticai.preprocessor._basics.TIn) → elasticai.preprocessor._basics.TOut[source]#

abstractmethod forward(x: numpy.ndarray) → numpy.ndarray[source]#

Forward function for processing the input data stream to new output format

Parameters:: x – Numpy array with input data stream
Returns:: Numpy array with output data stream

__repr__() → str[source]#

abstractmethod create_design(id: str, target: str, path2save: pathlib.Path, total_bitwidth: int, frac_bitwidth: int, is_signed: bool) → None[source]#

Function for creating the hardware design of this processing module

Parameters:

id – String with ID of this hardware design
target – Target for hardware design (PC, MCU, FPGA, ASIC)
path2save – Path to the saved hardware designs
total_bitwidth – Integer with total bitwidth of each value for processing
frac_bitwidth – Integer with fraction bitwidth if FxP is applied
is_signed – Boolean if signed integers is used

Returns:

None