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('parent process:' + str(os.getppid()))
logging.debug('process id:' + str(os.getpid()))
self.saveResults(self.funcLeafRankGenerators, False)
logging.basicConfig(stream=sys.stdout, level=logging.DEBUG)
logging.debug("Running from machine " + str(gethostname()))
numpy.random.seed(21)
dataDir = PathDefaults.getDataDir() + "metabolomic/"
X, X2, Xs, XOpls, YList, ages, df = MetabolomicsUtils.loadData()
waveletStr = 'db4'
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)
dataList = []
dataList.extend([(XwDb4, "db4")])
lock = multiprocessing.Lock()
numpy.random.seed(datetime.datetime.now().microsecond)
#numpy.random.seed(21)
permInds = numpy.random.permutation(len(dataList))
numpy.random.seed(21)
try:
for ind in permInds:
logging.debug('module name:' + __name__)
logging.debug('parent process:' + str(os.getppid()))
logging.debug('process id:' + str(os.getpid()))
self.saveResults(self.pcaLeafRankGenerators, "pca")
logging.basicConfig(stream=sys.stdout, level=logging.DEBUG)
logging.debug("Running from machine " + str(gethostname()))
numpy.random.seed(21)
dataDir = PathDefaults.getDataDir() + "metabolomic/"
X, X2, Xs, XOpls, YList, ages, df = MetabolomicsUtils.loadData()
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)
#Filter the wavelets
Ns = [10, 25, 50, 75, 100]
dataList = []
for i in range(len(Ns)):
N = Ns[i]
XwDb4F, inds = MetabolomicsUtils.filterWavelet(XwDb4, N)
dataList.append((XwDb4F[:, inds], "Db4-" + str(N)))
XwDb8F, inds = MetabolomicsUtils.filterWavelet(XwDb8, N)
dataList.append((XwDb8F[:, inds], "Db8-" + str(N)))
from apgl.util.PathDefaults import PathDefaults
from exp.metabolomics.MetabolomicsUtils import MetabolomicsUtils
import numpy
import pywt
dataDir = PathDefaults.getDataDir() + "functional/"
fileName = dataDir + "synthetic_control.data"
X = numpy.loadtxt(fileName)
#Ignore first 200 examples
X = X[200:, :]
Y = numpy.zeros(X.shape[0])
Y[0:200] = -1 #Increading trend and decreasing trend
Y[200:] = 1 #Upward shift and downward shift
#Compute wavelets
waveletStr = "db2"
level = 2
mode = "cpd"
Xw = MetabolomicsUtils.getWaveletFeatures(X, waveletStr, level, mode)
print(X.shape)
print(Xw.shape)
C = pywt.wavedec(X[0, :], waveletStr, mode, level)
for c in C:
print(c.shape)
logging.debug("process id:" + str(os.getpid()))
self.saveResults(self.funcLeafRankGenerators, False)
logging.basicConfig(stream=sys.stdout, level=logging.DEBUG)
logging.debug("Running from machine " + str(gethostname()))
numpy.random.seed(21)
dataDir = PathDefaults.getDataDir() + "metabolomic/"
X, X2, Xs, XOpls, YList, ages, df = MetabolomicsUtils.loadData()
waveletStr = "db4"
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)
dataList = []
dataList.extend([(XwDb4, "db4")])
lock = multiprocessing.Lock()
numpy.random.seed(datetime.datetime.now().microsecond)
# numpy.random.seed(21)
permInds = numpy.random.permutation(len(dataList))
numpy.random.seed(21)
try:
for ind in permInds:
