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
def saveResults(self):
"""
Compute the results and save them for a particular hormone. Does so for all
learners.
"""
metaUtils = MetabolomicsUtils()
logging.debug("Running on hormones: " + str(self.hormoneDict.keys()))
for hormoneName, hormoneConc in self.hormoneDict.items():
nonNaInds = numpy.logical_not(numpy.isnan(hormoneConc))
hormoneIndicators = metaUtils.createIndicatorLabel(hormoneConc, metaUtils.boundsDict[hormoneName])
for i in range(hormoneIndicators.shape[1]):
#Make labels -1/+1
Y = numpy.array(hormoneIndicators[nonNaInds, i], numpy.int)*2-1
for dataName, dataFeatures in self.dataDict.items():
X = dataFeatures[nonNaInds, :]
X = numpy.c_[X, self.ages[nonNaInds]]
X = Standardiser().standardiseArray(X)
if self.runCartTreeRank:
fileName = self.resultsDir + "CartTreeRank-" + hormoneName + "-" + str(i) + "-" + dataName + ".npy"
self.saveResult(X, Y, self.cartTreeRank, self.cartTreeRankParams, fileName)
if self.runRbfSvmTreeRank:
fileName = self.resultsDir + "RbfSvmTreeRank-" + hormoneName + "-" + str(i) + "-" + dataName + ".npy"
self.saveResult(X, Y, self.rbfSvmTreeRank, self.rbfSvmTreeRankParams, fileName)
if self.runL1SvmTreeRank:
fileName = self.resultsDir + "L1SvmTreeRank-" + hormoneName + "-" + str(i) + "-" + dataName + ".npy"
self.saveResult(X, Y, self.l1SvmTreeRank, self.l1SvmTreeRankParams, fileName)
#For this SVM save the weight vector
weightsFileName = self.resultsDir + "WeightsL1SvmTreeRank-" + hormoneName + "-" + str(i) + "-" + dataName + ".npy"
self.saveWeightVectorResults(X, Y, self.l1SvmTreeRank, self.l1SvmTreeRankParams, weightsFileName)
if self.runCartTreeRankForest:
fileName = self.resultsDir + "CartTreeRankForest-" + hormoneName + "-" + str(i) + "-" + dataName + ".npy"
self.saveResult(X, Y, self.cartTreeRankForest, self.cartTreeRankForestParams, fileName)
if self.runRbfSvmTreeRankForest:
fileName = self.resultsDir + "RbfSvmTreeRankForest-" + hormoneName + "-" + str(i) + "-" + dataName + ".npy"
self.saveResult(X, Y, self.rbfSvmTreeRankForest, self.rbfSvmTreeRankForestParams, fileName)
if self.runL1SvmTreeRankForest:
fileName = self.resultsDir + "L1SvmTreeRankForest-" + hormoneName + "-" + str(i) + "-" + dataName + ".npy"
self.saveResult(X, Y, self.l1SvmTreeRankForest, self.l1SvmTreeRankForestParams, fileName)
#For this SVM save the weight vector
weightsFileName = self.resultsDir + "WeightsL1SvmTreeRankForest-" + hormoneName + "-" + str(i) + "-" + dataName + ".npy"
self.saveWeightVectorResults(X, Y, self.l1SvmTreeRankForest, self.l1SvmTreeRankForestParams, weightsFileName)
if self.runRankBoost:
fileName = self.resultsDir + "RankBoost-" + hormoneName + "-" + str(i) + "-" + dataName + ".npy"
self.saveResult(X, Y, self.rankBoost, self.rankBoostParams, fileName)
if self.runRankSVM:
fileName = self.resultsDir + "RankSVM-" + hormoneName + "-" + str(i) + "-" + dataName + ".npy"
self.saveResult(X, Y, self.rankSVM, self.rankSVMParams, fileName)
logging.debug("All done. See you around!")
metaUtils = MetabolomicsUtils()
X, XStd, X2, (XoplsCortisol, XoplsTesto, XoplsIgf1), YCortisol, YTesto, YIgf1, ages = metaUtils.loadData()
dataDict = {}
numpy.random.seed(datetime.datetime.now().microsecond)
helper = MetabolomicsExpHelper(dataDict, YCortisol, YTesto, YIgf1, ages)
dataNames =[]
dataNames.extend(["raw", "pca", "Db4", "Db8", "Haar"])
#algorithms = ["CartTreeRank", "CartTreeRankForest", "L1SvmTreeRank", "L1SvmTreeRankForest", "RbfSvmTreeRank", "RbfSvmTreeRankForest", "RankBoost", "RankSVM"]
algorithms = ["CartTreeRankForest", "L1SvmTreeRankForest", "RbfSvmTreeRankForest", "RankBoost", "RankSVM"]
algorithmsAbbr = ["CART-TRF", "L1-TRF", "RBF-TRF", "RB", "RSVM"]
hormoneNameIndicators = []
for i, (hormoneName, hormoneConc) in enumerate(helper.hormoneDict.items()):
hormoneIndicators = metaUtils.createIndicatorLabel(hormoneConc, metaUtils.boundsDict[hormoneName])
for j in range(hormoneIndicators.shape[1]):
hormoneNameIndicators.append(hormoneName + "-" +str(j))
numIndicators = 3
testAucsMean = numpy.zeros((len(hormoneNameIndicators), len(dataNames), len(algorithms)))
testAucsStd = numpy.zeros((len(hormoneNameIndicators), len(dataNames), len(algorithms)))
numMissingFiles = 0
for i, hormoneNameIndicator in enumerate(hormoneNameIndicators):
for j, dataName in enumerate(dataNames):
for k, alg in enumerate(algorithms):
fileName = resultsDir + alg + "-" + hormoneNameIndicator + "-" + dataName + ".npy"
try:
