def testParallelPen(self):
#Check if penalisation == inf when treeSize < gamma
numExamples = 100
X, y = data.make_regression(numExamples)
learner = DecisionTreeLearner(pruneType="CART", maxDepth=10, minSplit=2)
paramDict = {}
paramDict["setGamma"] = numpy.array(numpy.round(2**numpy.arange(1, 10, 0.5)-1), dtype=numpy.int)
folds = 3
alpha = 1.0
Cvs = numpy.array([(folds-1)*alpha])
idx = Sampling.crossValidation(folds, X.shape[0])
resultsList = learner.parallelPen(X, y, idx, paramDict, Cvs)
learner, trainErrors, currentPenalties = resultsList[0]
learner.setGamma(2**10)
treeSize = 0
#Let's work out the size of the unpruned tree
for trainInds, testInds in idx:
trainX = X[trainInds, :]
trainY = y[trainInds]
learner.learnModel(trainX, trainY)
treeSize += learner.tree.size
treeSize /= float(folds)
self.assertTrue(numpy.isinf(currentPenalties[paramDict["setGamma"]>treeSize]).all())
self.assertTrue(not numpy.isinf(currentPenalties[paramDict["setGamma"]<treeSize]).all())
def testCARTPrune(self):
numExamples = 500
X, y = data.make_regression(numExamples)
y = Standardiser().standardiseArray(y)
numTrain = numpy.round(numExamples * 0.33)
numValid = numpy.round(numExamples * 0.33)
trainX = X[0:numTrain, :]
trainY = y[0:numTrain]
validX = X[numTrain:numTrain+numValid, :]
validY = y[numTrain:numTrain+numValid]
testX = X[numTrain+numValid:, :]
testY = y[numTrain+numValid:]
learner = DecisionTreeLearner(pruneType="none", maxDepth=10, minSplit=2)
learner.learnModel(trainX, trainY)
learner = DecisionTreeLearner(pruneType="CART", maxDepth=10, minSplit=2, gamma=1000)
learner.learnModel(trainX, trainY)
self.assertTrue(learner.tree.getNumVertices() <= 1000)
predY = learner.predict(trainX)
learner.setGamma(200)
learner.learnModel(trainX, trainY)
self.assertTrue(learner.tree.getNumVertices() <= 200)
learner.setGamma(100)
learner.learnModel(trainX, trainY)
self.assertTrue(learner.tree.getNumVertices() <= 100)
learner = DecisionTreeLearner(pruneType="none", maxDepth=10, minSplit=2)
learner.learnModel(trainX, trainY)
predY2 = learner.predict(trainX)
#Gamma = 0 implies no pruning
nptst.assert_array_equal(predY, predY2)
#Full pruning
learner = DecisionTreeLearner(pruneType="CART", maxDepth=3, gamma=1)
learner.learnModel(trainX, trainY)
self.assertEquals(learner.tree.getNumVertices(), 1)
def testCvPrune(self):
numExamples = 500
X, y = data.make_regression(numExamples)
y = Standardiser().standardiseArray(y)
numTrain = numpy.round(numExamples * 0.33)
numValid = numpy.round(numExamples * 0.33)
trainX = X[0:numTrain, :]
trainY = y[0:numTrain]
validX = X[numTrain:numTrain+numValid, :]
validY = y[numTrain:numTrain+numValid]
testX = X[numTrain+numValid:, :]
testY = y[numTrain+numValid:]
learner = DecisionTreeLearner()
learner.learnModel(trainX, trainY)
error1 = Evaluator.rootMeanSqError(learner.predict(testX), testY)
#print(learner.getTree())
unprunedTree = learner.tree.copy()
learner.setGamma(1000)
learner.cvPrune(trainX, trainY)
self.assertEquals(unprunedTree.getNumVertices(), learner.tree.getNumVertices())
learner.setGamma(100)
learner.cvPrune(trainX, trainY)
#Test if pruned tree is subtree of current:
for vertexId in learner.tree.getAllVertexIds():
self.assertTrue(vertexId in unprunedTree.getAllVertexIds())
#The error should be better after pruning
learner.learnModel(trainX, trainY)
#learner.cvPrune(validX, validY, 0.0, 5)
learner.repPrune(validX, validY)
error2 = Evaluator.rootMeanSqError(learner.predict(testX), testY)
self.assertTrue(error1 >= error2)
idx = sampleMethod(folds, trainX.shape[0])
#Now try penalisation
resultsList = learner.parallelPen(trainX, trainY, idx, paramDict, Cvs)
bestLearner, trainErrors, currentPenalties = resultsList[0]
meanPenalties[k] += currentPenalties
meanTrainError += trainErrors
predY = bestLearner.predict(testX)
meanErrors[k] += bestLearner.getMetricMethod()(testY, predY)
#Compute ideal penalties and error on training data
meanIdealPenalities[k] += learner.parallelPenaltyGrid(trainX, trainY, testX, testY, paramDict)
for i in range(len(paramDict["setGamma"])):
allError = 0
learner.setGamma(paramDict["setGamma"][i])
for trainInds, testInds in idx:
validX = trainX[trainInds, :]
validY = trainY[trainInds]
learner.learnModel(validX, validY)
predY = learner.predict(trainX)
allError += learner.getMetricMethod()(predY, trainY)
meanAllErrors[i] += allError/float(len(idx))
k+= 1
numRealisations = float(numRealisations)
meanErrors /= numRealisations
meanPenalties /= numRealisations
meanIdealPenalities /= numRealisations