treeLeaveSizes = numpy.zeros(numParams)
for j in range(numRealisations):
print("")
logging.debug("j=" + str(j))
trainX, trainY, testX, testY = loadMethod(dataDir, datasetName, j)
logging.debug("Loaded dataset with " + str(trainX.shape) + " train and " + str(testX.shape) + " test examples")
trainInds = numpy.random.permutation(trainX.shape[0])[0:sampleSize]
trainX = trainX[trainInds,:]
trainY = trainY[trainInds]
#logging.debug("Training set size: " + str(trainX.shape))
methodInd = 0
idx = sampleMethod(folds, trainX.shape[0])
bestLearner, cvGrid = learner.parallelModelSelect(trainX, trainY, idx, paramDict)
predY = bestLearner.predict(testX)
meanCvGrid[methodInd, :] += cvGrid
meanErrors[methodInd] += bestLearner.getMetricMethod()(testY, predY)
meanDepths[methodInd] += bestLearner.tree.depth()
meanSizes[methodInd] += bestLearner.tree.getNumVertices()
Cvs = [-5, (folds-1)*alpha, beta[j, sampleSizeInd, :]]
#Now try penalisation
methodInd = 1
resultsList = learner.parallelPen(trainX, trainY, idx, paramDict, Cvs)
bestLearner, trainErrors, currentPenalties = resultsList[1]
meanCvGrid[methodInd, :] += trainErrors + currentPenalties
meanPenalties += currentPenalties
meanTrainError += trainErrors
def testModelSelect(self):
"""
We test the results on some data and compare to SVR.
"""
numExamples = 200
X, y = data.make_regression(numExamples, noise=0.5)
X = Standardiser().standardiseArray(X)
y = Standardiser().standardiseArray(y)
trainX = X[0:100, :]
trainY = y[0:100]
testX = X[100:, :]
testY = y[100:]
learner = DecisionTreeLearner(maxDepth=20, minSplit=10, pruneType="REP-CV")
learner.setPruneCV(8)
paramDict = {}
paramDict["setGamma"] = numpy.linspace(0.0, 1.0, 10)
paramDict["setPruneCV"] = numpy.arange(6, 11, 2, numpy.int)
folds = 5
idx = Sampling.crossValidation(folds, trainX.shape[0])
bestTree, cvGrid = learner.parallelModelSelect(trainX, trainY, idx, paramDict)
predY = bestTree.predict(testX)
error = Evaluator.rootMeanSqError(testY, predY)
print(error)
learner = DecisionTreeLearner(maxDepth=20, minSplit=5, pruneType="CART")
paramDict = {}
paramDict["setGamma"] = numpy.linspace(0.0, 1.0, 50)
folds = 5
idx = Sampling.crossValidation(folds, trainX.shape[0])
bestTree, cvGrid = learner.parallelModelSelect(trainX, trainY, idx, paramDict)
predY = bestTree.predict(testX)
error = Evaluator.rootMeanSqError(testY, predY)
print(error)
return
#Let's compare to the SVM
learner2 = LibSVM(kernel='gaussian', type="Epsilon_SVR")
paramDict = {}
paramDict["setC"] = 2.0**numpy.arange(-10, 14, 2, dtype=numpy.float)
paramDict["setGamma"] = 2.0**numpy.arange(-10, 4, 2, dtype=numpy.float)
paramDict["setEpsilon"] = learner2.getEpsilons()
idx = Sampling.crossValidation(folds, trainX.shape[0])
bestSVM, cvGrid = learner2.parallelModelSelect(trainX, trainY, idx, paramDict)
predY = bestSVM.predict(testX)
error = Evaluator.rootMeanSqError(testY, predY)
print(error)