def testGetWaveletFeaturesTest(self):
#See if we can reproduce the data from the wavelet
X, X2, Xs, Xopls, YList, df = MetabolomicsUtils.loadData()
waveletStr = 'db4'
mode = "zpd"
level = 10
C = pywt.wavedec(X[0, :], waveletStr, level=level, mode=mode)
X0 = pywt.waverec(C, waveletStr, mode)
tol = 10**-6
self.assertTrue(numpy.linalg.norm(X0 - X[0, :]) < tol)
def reconstructSignal(X, Xw, waveletStr, level, mode, C):
Xrecstr = numpy.zeros(X.shape)
for i in range(Xw.shape[0]):
C2 = []
colIndex = 0
for j in range(len(list(C))):
C2.append(Xw[i, colIndex:colIndex+len(C[j])])
colIndex += len(C[j])
Xrecstr[i, :] = pywt.waverec(tuple(C2), waveletStr, mode)
return Xrecstr
#Now do the same for the whole X
C = pywt.wavedec(X[0, :], waveletStr, level=level, mode=mode)
Xw = MetabolomicsUtils.getWaveletFeatures(X, waveletStr, level, mode)
Xrecstr = reconstructSignal(X, Xw, waveletStr, level, mode, C)
self.assertTrue(numpy.linalg.norm(X - Xrecstr) < tol)
waveletStr = 'db8'
C = pywt.wavedec(X[0, :], waveletStr, level=level, mode=mode)
Xw = MetabolomicsUtils.getWaveletFeatures(X, waveletStr, level, mode)
Xrecstr = reconstructSignal(X, Xw, waveletStr, level, mode, C)
self.assertTrue(numpy.linalg.norm(X - Xrecstr) < tol)
waveletStr = 'haar'
C = pywt.wavedec(X[0, :], waveletStr, level=level, mode=mode)
Xw = MetabolomicsUtils.getWaveletFeatures(X, waveletStr, level, mode)
Xrecstr = reconstructSignal(X, Xw, waveletStr, level, mode, C)
self.assertTrue(numpy.linalg.norm(X - Xrecstr) < tol)
def testReconstructSignal(self):
numExamples = 100
numFeatures = 16
X = numpy.random.rand(numExamples, numFeatures)
level = 10
mode = "cpd"
waveletStr = "db4"
C = pywt.wavedec(X[0, :], waveletStr, mode, level=10)
Xw = MetabolomicsUtils.getWaveletFeatures(X, waveletStr, level, mode)
X2 = MetabolomicsUtils.reconstructSignal(X, Xw, waveletStr, mode, C)
tol = 10**-6
self.assertTrue(numpy.linalg.norm(X - X2) < tol)
def testFilterWavelet(self):
numExamples = 100
numFeatures = 16
X = numpy.random.rand(numExamples, numFeatures)
level = 10
mode = "cpd"
waveletStr = "db4"
C = pywt.wavedec(X[0, :], waveletStr, mode, level=10)
Xw = MetabolomicsUtils.getWaveletFeatures(X, waveletStr, level, mode)
N = 10
Xw2, inds = MetabolomicsUtils.filterWavelet(Xw, N)
tol = 10**-6
self.assertEquals(inds.shape[0], N)
self.assertTrue(numpy.linalg.norm( Xw[:, inds] - Xw2[:, inds] ) < tol)
zeroInds = numpy.setdiff1d(numpy.arange(Xw.shape[1]), inds)
self.assertTrue(numpy.linalg.norm(Xw2[:, zeroInds]) < tol)
logging.debug("Running from machine " + str(gethostname()))
numpy.random.seed(21)
os.system('taskset -p 0xffffffff %d' % os.getpid())
dataDir = PathDefaults.getDataDir() + "metabolomic/"
metaUtils = MetabolomicsUtils()
X, XStd, X2, (XoplsCortisol, XoplsTesto, XoplsIgf1), YCortisol, YTesto, YIgf1, ages = metaUtils.loadData()
#We model 99.1% of the spectrum with 100 eigenvectors
pca = PCA(n_components=100)
XPca = pca.fit_transform(X)
mode = "cpd"
level = 10
XwDb4 = MetabolomicsUtils.getWaveletFeatures(X, 'db4', level, mode)
XwDb8 = MetabolomicsUtils.getWaveletFeatures(X, 'db8', level, mode)
XwHaar = MetabolomicsUtils.getWaveletFeatures(X, 'haar', level, mode)
dataDict = {}
dataDict["raw"] = X
dataDict["pca"] = XPca
#dataDict["log"] = X2
dataDict["Db4"] = XwDb4
dataDict["Db8"] = XwDb8
dataDict["Haar"] = XwHaar
numpy.random.seed(datetime.datetime.now().microsecond)
parser = argparse.ArgumentParser(description='Run the metabolomics experiments')
#Now try some filtering and plot N versus reconstruction error
Ns = range(0, 700, 50)
waveletStrs = ['haar', 'db4', 'db8']
waveletStrs2 = ['Haar', 'Db4', 'Db8']
errors = numpy.zeros((len(waveletStrs), len(Ns)))
mode = "cpd"
standardiser = Standardiser()
#X = standardiser.centreArray(X)
plotStyles = ['k-', 'k--', 'k-.', 'k:', 'k.']
for i in range(len(waveletStrs)):
print(i)
waveletStr = waveletStrs[i]
Xw = MetabolomicsUtils.getWaveletFeatures(X, waveletStr, level, mode)
C = pywt.wavedec(X[0, :], waveletStr, level=level, mode=mode)
for j in range(len(Ns)):
N = Ns[j]
Xw2, inds = MetabolomicsUtils.filterWavelet(Xw, N)
X2 = MetabolomicsUtils.reconstructSignal(X, Xw2, waveletStr, mode, C)
errors[i, j] = numpy.linalg.norm(X - X2)
#Plot example wavelet after filtering
waveletStr = "haar"
N = 100
Xw = MetabolomicsUtils.getWaveletFeatures(X, waveletStr, level, mode)
C = pywt.wavedec(X[0, :], waveletStr, level=level, mode=mode)
Xw2, inds = MetabolomicsUtils.filterWavelet(Xw, N)
