neuraxle.steps.features

Featurization Steps

You can find here steps that featurize your data.

Classes

Cheap3DTo2DTransformer()

Prebuild class to featurize 3D data into 2D data for simple classification or regression, for instance.

FFTPeakBinWithValue()

Compute peak fft bins (int), and their magnitudes’ value (float), to concatenate them.

class neuraxle.steps.features.Cheap3DTo2DTransformer[source]

Prebuild class to featurize 3D data into 2D data for simple classification or regression, for instance.

You can enable, or disable features using hyperparams :

step = Cheap3DTo2DTransformer().set_hyperparams(hyperparams={
    'FFT__enabled': True,
    'NumpyMean__enabled': True,
    'NumpyMedian__enabled': True,
    'NumpyMin__enabled': True,
    'NumpyMax__enabled': True
})
_abc_cache = <_weakrefset.WeakSet object>[source]
_abc_negative_cache = <_weakrefset.WeakSet object>[source]
_abc_negative_cache_version = 57
_abc_registry = <_weakrefset.WeakSet object>[source]
class neuraxle.steps.features.FFTPeakBinWithValue[source]

Compute peak fft bins (int), and their magnitudes’ value (float), to concatenate them. This is intended to be used only after a NumpyFFT absolute step.

_abc_cache = <_weakrefset.WeakSet object>[source]
_abc_negative_cache = <_weakrefset.WeakSet object>[source]
_abc_negative_cache_version = 57
_abc_registry = <_weakrefset.WeakSet object>[source]