def testLearnModel2(self):
#We want to make sure the learnt tree with gamma = 0 maximise the
#empirical risk
minSplit = 20
maxDepth = 3
gamma = 0.01
learner = PenaltyDecisionTree(minSplit=minSplit,
maxDepth=maxDepth,
gamma=gamma,
pruning=False)
#Vary sampleSize
numpy.random.seed(21)
learner.setSampleSize(1)
learner.learnModel(self.X, self.y)
error1 = learner.treeObjective(self.X, self.y)
numpy.random.seed(21)
learner.setSampleSize(5)
learner.learnModel(self.X, self.y)
error2 = learner.treeObjective(self.X, self.y)
numpy.random.seed(21)
learner.setSampleSize(10)
learner.learnModel(self.X, self.y)
error3 = learner.treeObjective(self.X, self.y)
self.assertTrue(error1 >= error2)
self.assertTrue(error2 >= error3)
#Now vary max depth
learner.gamma = 0
numpy.random.seed(21)
learner.setSampleSize(1)
learner.minSplit = 1
learner.maxDepth = 3
learner.learnModel(self.X, self.y)
predY = learner.predict(self.X)
error1 = Evaluator.binaryError(self.y, predY)
numpy.random.seed(21)
learner.maxDepth = 5
learner.learnModel(self.X, self.y)
predY = learner.predict(self.X)
error2 = Evaluator.binaryError(self.y, predY)
numpy.random.seed(21)
learner.maxDepth = 10
learner.learnModel(self.X, self.y)
predY = learner.predict(self.X)
error3 = Evaluator.binaryError(self.y, predY)
self.assertTrue(error1 >= error2)
self.assertTrue(error2 >= error3)
def testLearnModel2(self):
#We want to make sure the learnt tree with gamma = 0 maximise the
#empirical risk
minSplit = 20
maxDepth = 3
gamma = 0.01
learner = PenaltyDecisionTree(minSplit=minSplit, maxDepth=maxDepth, gamma=gamma, pruning=False)
#Vary sampleSize
numpy.random.seed(21)
learner.setSampleSize(1)
learner.learnModel(self.X, self.y)
error1 = learner.treeObjective(self.X, self.y)
numpy.random.seed(21)
learner.setSampleSize(5)
learner.learnModel(self.X, self.y)
error2 = learner.treeObjective(self.X, self.y)
numpy.random.seed(21)
learner.setSampleSize(10)
learner.learnModel(self.X, self.y)
error3 = learner.treeObjective(self.X, self.y)
self.assertTrue(error1 >= error2)
self.assertTrue(error2 >= error3)
#Now vary max depth
learner.gamma = 0
numpy.random.seed(21)
learner.setSampleSize(1)
learner.minSplit = 1
learner.maxDepth = 3
learner.learnModel(self.X, self.y)
predY = learner.predict(self.X)
error1 = Evaluator.binaryError(self.y, predY)
numpy.random.seed(21)
learner.maxDepth = 5
learner.learnModel(self.X, self.y)
predY = learner.predict(self.X)
error2 = Evaluator.binaryError(self.y, predY)
numpy.random.seed(21)
learner.maxDepth = 10
learner.learnModel(self.X, self.y)
predY = learner.predict(self.X)
error3 = Evaluator.binaryError(self.y, predY)
self.assertTrue(error1 >= error2)
self.assertTrue(error2 >= error3)
def testPrune(self):
startId = (0, )
minSplit = 20
maxDepth = 5
gamma = 0.05
learner = PenaltyDecisionTree(minSplit=minSplit,
maxDepth=maxDepth,
gamma=gamma,
pruning=False)
trainX = self.X[100:, :]
trainY = self.y[100:]
testX = self.X[0:100, :]
testY = self.y[0:100]
argsortX = numpy.zeros(trainX.shape, numpy.int)
for i in range(trainX.shape[1]):
argsortX[:, i] = numpy.argsort(trainX[:, i])
argsortX[:, i] = numpy.argsort(argsortX[:, i])
learner.tree = DictTree()
rootNode = DecisionNode(numpy.arange(trainX.shape[0]),
Util.mode(trainY))
learner.tree.setVertex(startId, rootNode)
learner.growTree(trainX, trainY, argsortX, startId)
learner.shapeX = trainX.shape
learner.predict(trainX, trainY)
learner.computeAlphas()
obj1 = learner.treeObjective(trainX, trainY)
size1 = learner.tree.getNumVertices()
#Now we'll prune
learner.prune(trainX, trainY)
obj2 = learner.treeObjective(trainX, trainY)
size2 = learner.tree.getNumVertices()
self.assertTrue(obj1 >= obj2)
self.assertTrue(size1 >= size2)
#Check there are no nodes with alpha>alphaThreshold
for vertexId in learner.tree.getAllVertexIds():
self.assertTrue(
learner.tree.getVertex(vertexId).alpha <=
learner.alphaThreshold)
def testPrune(self):
startId = (0, )
minSplit = 20
maxDepth = 5
gamma = 0.05
learner = PenaltyDecisionTree(minSplit=minSplit, maxDepth=maxDepth, gamma=gamma, pruning=False)
trainX = self.X[100:, :]
trainY = self.y[100:]
testX = self.X[0:100, :]
testY = self.y[0:100]
argsortX = numpy.zeros(trainX.shape, numpy.int)
for i in range(trainX.shape[1]):
argsortX[:, i] = numpy.argsort(trainX[:, i])
argsortX[:, i] = numpy.argsort(argsortX[:, i])
learner.tree = DictTree()
rootNode = DecisionNode(numpy.arange(trainX.shape[0]), Util.mode(trainY))
learner.tree.setVertex(startId, rootNode)
learner.growTree(trainX, trainY, argsortX, startId)
learner.shapeX = trainX.shape
learner.predict(trainX, trainY)
learner.computeAlphas()
obj1 = learner.treeObjective(trainX, trainY)
size1 = learner.tree.getNumVertices()
#Now we'll prune
learner.prune(trainX, trainY)
obj2 = learner.treeObjective(trainX, trainY)
size2 = learner.tree.getNumVertices()
self.assertTrue(obj1 >= obj2)
self.assertTrue(size1 >= size2)
#Check there are no nodes with alpha>alphaThreshold
for vertexId in learner.tree.getAllVertexIds():
self.assertTrue(learner.tree.getVertex(vertexId).alpha <= learner.alphaThreshold)
def testLearnModel(self):
minSplit = 20
maxDepth = 3
gamma = 0.00
X, y = self.X, self.y
testX = X[100:, :]
testY = y[100:]
X = X[0:100, :]
y = y[0:100]
learner = PenaltyDecisionTree(minSplit=minSplit,
maxDepth=maxDepth,
gamma=gamma)
learner.learnModel(X, y)
tree = learner.getTree()
#Work out penalty cost
predY = learner.predict(X)
predTestY = learner.predict(testX)
n = float(X.shape[0])
d = X.shape[1]
T = tree.getNumVertices()
error = (1 - gamma) * numpy.sum(predY != y) / n
testError = numpy.sum(predTestY != testY) / float(testY.shape[0])
error += gamma * numpy.sqrt(T)
self.assertEquals(error, learner.treeObjective(X, y))
#Check if the values in the tree nodes are correct
for vertexId in tree.getAllVertexIds():
vertex = tree.getVertex(vertexId)
self.assertTrue(vertex.getValue() == 1.0
or vertex.getValue() == -1.0)
if tree.isNonLeaf(vertexId):
self.assertTrue(0 <= vertex.getFeatureInd() <= X.shape[1])
self.assertTrue(0 <= vertex.getError() <= 1)
def testLearnModel(self):
minSplit = 20
maxDepth = 3
gamma = 0.00
X, y = self.X, self.y
testX = X[100:, :]
testY = y[100:]
X = X[0:100, :]
y = y[0:100]
learner = PenaltyDecisionTree(minSplit=minSplit, maxDepth=maxDepth, gamma=gamma)
learner.learnModel(X, y)
tree = learner.getTree()
#Work out penalty cost
predY = learner.predict(X)
predTestY = learner.predict(testX)
n = float(X.shape[0])
d = X.shape[1]
T = tree.getNumVertices()
error = (1-gamma)*numpy.sum(predY!=y)/n
testError = numpy.sum(predTestY!=testY)/float(testY.shape[0])
error += gamma*numpy.sqrt(T)
self.assertEquals(error, learner.treeObjective(X, y))
#Check if the values in the tree nodes are correct
for vertexId in tree.getAllVertexIds():
vertex = tree.getVertex(vertexId)
self.assertTrue(vertex.getValue()==1.0 or vertex.getValue()==-1.0)
if tree.isNonLeaf(vertexId):
self.assertTrue(0 <= vertex.getFeatureInd() <= X.shape[1])
self.assertTrue(0 <= vertex.getError() <= 1)
