icecube.radcube.ml_tools.SingleChannelClassifier module

class icecube.radcube.ml_tools.SingleChannelClassifier.SingleChannelClassifier(modelFile)

Bases: object

Loads in trained model and has functions to return a classification score for a passed in waveform. The user is required to perform any preprocessing of the waveforms (e.g. upsampling, bandpassing) outside of a normalization. The models are trained on 4000 bins long waveform, so the input waveform sould also be 4000 bins long.

Parameters:

modelFile (.h5) – Trained model file to be used to classify the waveforms

ClassifyAntennaTimeSeries(ts)
Parameters:

ts – an AntennaTimeSeries instance to be classified

Returns:

the predicted value between (0-1) for the passed in time series

ClassifyNumpyArray(array)
Parameters:

array – numpy array that has shape (<N waveforms>,<waveform length>,1) and has been normalized to peak at +/-1

Returns:

an array of prediction values