if col in posCols()] generatedFeatures['features'] = [f for f in generatedFeatures['features'] if f in posFeatures().keys()] return generatedFeatures def getSimpleFreqDomainFeatures(data, requiredFeatures=None): requiredFeatures = checkRequiredFeatures(requiredFeatures) data = toFreq(data[requiredFeatures['cols']]) features = dict() for f in requiredFeatures['features']: features.update(posFeatures()[f](data, f)) return features if __name__ == '__main__': import dataTransform.accproc as ac import dataTransform.Preprocessing as pp for i in range(9): nb = int(i + 1) if nb == 4: data = ac.readGCDCFormat("..\data\Runs\Tina\enkel\DATA-00" + `nb` + ".csv") data = ac.preprocessGCDC(data) filtered = pp.filterRun3(data) print(getSimpleFreqDomainFeatures(data, None))
def getRunningPart(data, hip): try: return pp.filterRun3(data, hip) except: return None
def getSimplePeakFeatures(data, requiredFeatures=None): generatedFeatures = {'cols': posPeaks(), 'features': posFeatures().keys()} if requiredFeatures is None: requiredFeatures = generatedFeatures generatedFeatures.update(requiredFeatures) peaks = toPeaks(data, generatedFeatures['cols']) features = dict() for f in generatedFeatures['features']: features.update(applyFun(peaks, posFeatures()[f], f)) return features if __name__ == '__main__': import dataTransform.accproc as ac import dataTransform.Preprocessing as pp for i in range(9): nb = int(i + 1) if nb == 4: data = ac.readGCDCFormat("..\..\Runs\Tina\enkel\DATA-00" + `nb` + ".csv") data = ac.preprocessGCDC(data) filtered = pp.filterRun3(data, False) print(getSimplePeakFeatures(data))