def __init__(self, YList, X, featuresName, ages, args):
super(MetabolomicsExpRunner, self).__init__(args=args)
self.X = X
self.YList = YList #The list of concentrations
self.featuresName = featuresName
self.args = args
self.ages = ages
self.maxDepth = 10
self.numTrees = 10
self.sampleSize = 1.0
self.sampleReplace = True
self.folds = 5
self.resultsDir = PathDefaults.getOutputDir() + "metabolomics/"
self.leafRankGenerators = []
self.leafRankGenerators.append((LinearSvmGS.generate(), "SVM"))
self.leafRankGenerators.append((SvcGS.generate(), "RBF-SVM"))
self.leafRankGenerators.append((DecisionTree.generate(), "CART"))
self.pcaLeafRankGenerators = [(LinearSvmPca.generate(), "LinearSVM-PCA")]
self.funcLeafRankGenerators = []
self.funcLeafRankGenerators.append((LinearSvmFGs.generate, "SVMF"))
self.funcLeafRankGenerators.append((SvcFGs.generate, "RBF-SVMF"))
self.funcLeafRankGenerators.append((DecisionTreeF.generate, "CARTF"))
#Store all the label vectors and their missing values
YIgf1Inds, YICortisolInds, YTestoInds = MetabolomicsUtils.createIndicatorLabels(YList)
self.hormoneInds = [YIgf1Inds, YICortisolInds, YTestoInds]
self.hormoneNames = MetabolomicsUtils.getLabelNames()
class DecisionTreeF(AbstractFunctionalPredictor):
def __init__(self):
super(DecisionTreeF, self).__init__()
self.decisionTree = DecisionTree()
def learnModel(self, X, y, folds=3):
"""
Train using the given examples and labels, however first conduct grid
search in conjunction with cross validation to find the best parameters.
We also conduct filtering with a variety of values.
"""
if self.waveletInds == None:
self.waveletInds = numpy.arange(X.shape[1])
nonWaveletInds = numpy.setdiff1d(numpy.arange(X.shape[1]), self.waveletInds)
Xw = X[:, self.waveletInds]
Xo = X[:, nonWaveletInds]
featureInds = numpy.flipud(numpy.argsort(numpy.sum(Xw**2, 0)))
meanAUCs = numpy.zeros(self.candidatesN.shape[0])
stdAUCs = numpy.zeros(self.candidatesN.shape[0])
#Standardise the data
Xw = Standardiser().standardiseArray(Xw)
Xo = Standardiser().standardiseArray(Xo)
for i in range(self.candidatesN.shape[0]):
newX = numpy.c_[Xw[:, featureInds[0:self.candidatesN[i]]], Xo]
meanAUCs[i], stdAUCs[i] = self.decisionTree.evaluateStratifiedCv(newX, y, folds, metricMethod=Evaluator.auc)
bestI = numpy.argmax(meanAUCs)
self.featureInds = numpy.r_[self.waveletInds[featureInds[0:self.candidatesN[bestI]]], nonWaveletInds]
logging.debug("Best learner found: " + str(self.decisionTree) + " N:" + str(self.candidatesN[bestI]))
self.standardiser = Standardiser()
newX = self.standardiser.standardiseArray(X[:, self.featureInds])
self.decisionTree.learnModel(newX, y)
def predict(self, X):
newX = self.standardiser.standardiseArray(X[:, self.featureInds])
return self.decisionTree.predict(newX)
@staticmethod
def generate(waveletInds=None):
"""
Generate a classifier which does a grid search.
"""
def generatorFunc():
decisionTree = DecisionTreeF()
decisionTree.setWaveletInds(waveletInds)
return decisionTree
return generatorFunc
def setWeight(self, weight):
self.decisionTree.setWeight(weight)
def __init__(self):
super(DecisionTreeF, self).__init__()
self.decisionTree = DecisionTree()