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 testCreateIndicatorLabels(self):
metaUtils = MetabolomicsUtils()
X, XStd, X2, (XoplsCortisol, XoplsTesto, XoplsIgf1), YCortisol, YTesto, YIgf1, ages = metaUtils.loadData()
YCortisol = YCortisol[numpy.logical_not(numpy.isnan(YCortisol))]
YCortisolIndicators = metaUtils.createIndicatorLabel(YCortisol, metaUtils.boundsDict["Cortisol"])
YTesto = YTesto[numpy.logical_not(numpy.isnan(YTesto))]
YTestoIndicators = metaUtils.createIndicatorLabel(YTesto, metaUtils.boundsDict["Testosterone"])
YIgf1 = YIgf1[numpy.logical_not(numpy.isnan(YIgf1))]
YIgf1Indicators = metaUtils.createIndicatorLabel(YIgf1, metaUtils.boundsDict["IGF1"])
s = numpy.sum(YCortisolIndicators, 1)
nptst.assert_array_equal(s, numpy.ones(s.shape[0]))
s = numpy.sum(YTestoIndicators, 1)
nptst.assert_array_equal(s, numpy.ones(s.shape[0]))
s = numpy.sum(YIgf1Indicators, 1)
nptst.assert_array_equal(s, numpy.ones(s.shape[0]))
#Now compare to those labels in the file
X, X2, (XoplsCortisol, XoplsTesto, XoplsIgf1), YCortisol, YTesto, YIgf1, ages = metaUtils.loadData()
dataDir = PathDefaults.getDataDir() + "metabolomic/"
fileName = dataDir + "data.RMN.total.6.txt"
data = pandas.read_csv(fileName, delimiter=",")
YCortisolIndicators = metaUtils.createIndicatorLabel(YCortisol, metaUtils.boundsDict["Cortisol"])
YCortisolIndicators2 = numpy.array(data[["Ind.Cortisol.1", "Ind.Cortisol.2", "Ind.Cortisol.3"]])
for i in range(YCortisolIndicators.shape[0]):
if not numpy.isnan(YCortisol[i]) and not numpy.isnan(YCortisolIndicators2[i, :]).any():
#nptst.assert_almost_equal(YCortisolIndicators2[i, :], YCortisolIndicators[i, :])
pass
YTestoIndicators = metaUtils.createIndicatorLabel(YTesto, metaUtils.boundsDict["Testosterone"])
YTestoIndicators2 = numpy.array(data[["Ind.Testo.1", "Ind.Testo.2", "Ind.Testo.3"]])
for i in range(YTestoIndicators.shape[0]):
if not numpy.isnan(YTesto[i]) and not numpy.isnan(YTestoIndicators2[i, :]).any():
#print(i, YTesto[i])
nptst.assert_almost_equal(YTestoIndicators2[i, :], YTestoIndicators[i, :])
YIgf1Indicators = metaUtils.createIndicatorLabel(YIgf1, metaUtils.boundsDict["IGF1"])
YIgf1Indicators2 = numpy.array(data[["Ind.IGF1.1", "Ind.IGF1.2", "Ind.IGF1.3"]])
for i in range(YIgf1Indicators.shape[0]):
if not numpy.isnan(YIgf1[i]) and not numpy.isnan(YIgf1Indicators2[i, :]).any():
#print(i, YIgf1[i])
#nptst.assert_almost_equal(YIgf1Indicators2[i, :], YIgf1Indicators[i, :])
pass
from socket import gethostname
from sklearn.decomposition import PCA
"""
Run a variety of bipartite ranking on the metabolomics data
"""
logging.basicConfig(stream=sys.stdout, level=logging.DEBUG)
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
def testLoadData(self):
metaUtils = MetabolomicsUtils()
X, XStd, X2, (XoplsCortisol, XoplsTesto, XoplsIgf1), YCortisol, YTesto, YIgf1, ages = metaUtils.loadData()
import numpy from wallhack.metabolomics.MetabolomicsUtils import MetabolomicsUtils X, X2, df = MetabolomicsUtils.loadData() #Just figure out the boundaries of the levels numpy.set_printoptions(threshold=3000) labelNames = ["IGF1.val", "Cortisol.val", "Testosterone.val"] labelNames2 = ["Ind.IGF1.1", "Ind.IGF1.2", "Ind.IGF1.3"] YList = MetabolomicsUtils.createLabelList(df, labelNames) YList2 = MetabolomicsUtils.createLabelList(df, labelNames2) Y, inds = YList[0] Y1 = numpy.array(df.rx(labelNames2[0])).ravel()[inds] Y2 = numpy.array(df.rx(labelNames2[1])).ravel()[inds] Y3 = numpy.array(df.rx(labelNames2[2])).ravel()[inds] inds = numpy.argsort(Y) YY = numpy.c_[Y[inds], Y1[inds]] YY = numpy.c_[YY, Y2[inds]] YY = numpy.c_[YY, Y3[inds]] print(YY) labelNames2 = ["Ind.Cortisol.1", "Ind.Cortisol.2", "Ind.Cortisol.3"] YList2 = MetabolomicsUtils.createLabelList(df, labelNames2) Y, inds = YList[1] Y1 = numpy.array(df.rx(labelNames2[0])).ravel()[inds] Y2 = numpy.array(df.rx(labelNames2[1])).ravel()[inds] Y3 = numpy.array(df.rx(labelNames2[2])).ravel()[inds]