`elasticai.preprocessor.windower.window`#

Module Contents#

Classes#

`SettingsWindow`	Class for defining the properties for applying a window sequenzer on transient signals Attributes: sampling_rate: Floating value with sampling rate of the transient signal [Hz] window_sec: Floating value with the size of the window [s] overlap_sec: Floating value with overlapping the sequences [s]
`WindowSequencer`

Functions#

transformation_window_method

Generating window for smoothing input of signal transformation method.

Data#

DefaultSettingsWindow

API#

elasticai.preprocessor.windower.window.transformation_window_method(window_size: int, method: str = 'hamming') → numpy.ndarray[source]#

Generating window for smoothing input of signal transformation method.

Parameters:

window_size – Integer number with size of the window
method – Selection of window method [‘’: Ones, ‘hamming’, ‘hanning’, ‘gaussian’, ‘bartlett’, ‘blackman’]

Returns:

Numpy array with window

class elasticai.preprocessor.windower.window.SettingsWindow[source]#

Class for defining the properties for applying a window sequenzer on transient signals Attributes: sampling_rate: Floating value with sampling rate of the transient signal [Hz] window_sec: Floating value with the size of the window [s] overlap_sec: Floating value with overlapping the sequences [s]

sampling_rate: float#: None

window_sec: float#: None

overlap_sec: float#: None

property window_length: int#: Returning an integer with total number of samples for building the window sequence

property overlap_length: int#: Returning an integer with total number of samples for overlapping

elasticai.preprocessor.windower.window.DefaultSettingsWindow#: ‘SettingsWindow(…)’

class elasticai.preprocessor.windower.window.WindowSequencer(settings: elasticai.preprocessor.windower.window.SettingsWindow)[source]#

Initialization

Class for applying a window sequenzer on transient signals

Parameters:: settings – Class SettingsWindow with definitions for the window sequenzer
Returns:: None

sequence(signal: numpy.ndarray) → numpy.ndarray[source]#

Building a sequence-to-sequence output array from signal input

Parameters:: signal – Numpy array with input signal to build the sequence with shape=(N, )
Returns:: Numpy array of sequence signals with shape=(M, window length)

slide(signal: numpy.ndarray) → numpy.ndarray[source]#

Building a sliding window sequencer on signal input

Parameters:: signal – Numpy array with input signal to build the sequence with shape=(N, )
Returns:: Numpy array of sequence signals with shape=(M, window length)

window_event_detected(signal: numpy.ndarray, thr: float, pre_time: float, do_abs: bool = False) → numpy.ndarray[source]#

Building a window sequencer based on an event-detection (absolute input)