def testPredict2(self):
# Test on Gauss2D dataset
dataDir = PathDefaults.getDataDir()
fileName = dataDir + "Gauss2D_learn.csv"
XY = numpy.loadtxt(fileName, skiprows=1, usecols=(1, 2, 3), delimiter=",")
X = XY[:, 0:2]
y = XY[:, 2]
fileName = dataDir + "Gauss2D_test.csv"
testXY = numpy.loadtxt(fileName, skiprows=1, usecols=(1, 2, 3), delimiter=",")
testX = testXY[:, 0:2]
testY = testXY[:, 2]
X = Standardiser().standardiseArray(X)
testX = Standardiser().standardiseArray(testX)
maxDepths = range(3, 10)
trainAucs = numpy.array(
[0.7194734, 0.7284824, 0.7332185, 0.7348198, 0.7366152, 0.7367508, 0.7367508, 0.7367508]
)
testAucs = numpy.array([0.6789078, 0.6844632, 0.6867918, 0.6873420, 0.6874820, 0.6874400, 0.6874400, 0.6874400])
i = 0
# The results are approximately the same, but not exactly
for maxDepth in maxDepths:
treeRank = TreeRank(self.leafRanklearner)
treeRank.setMaxDepth(maxDepth)
treeRank.learnModel(X, y)
trainScores = treeRank.predict(X)
testScores = treeRank.predict(testX)
self.assertAlmostEquals(Evaluator.auc(trainScores, y), trainAucs[i], 2)
self.assertAlmostEquals(Evaluator.auc(testScores, testY), testAucs[i], 1)
i += 1
def testPredict2(self):
#Test on Gauss2D dataset
dataDir = PathDefaults.getDataDir()
fileName = dataDir + "Gauss2D_learn.csv"
XY = numpy.loadtxt(fileName,
skiprows=1,
usecols=(1, 2, 3),
delimiter=",")
X = XY[:, 0:2]
y = XY[:, 2] * 2 - 1
fileName = dataDir + "Gauss2D_test.csv"
testXY = numpy.loadtxt(fileName,
skiprows=1,
usecols=(1, 2, 3),
delimiter=",")
testX = testXY[:, 0:2]
testY = testXY[:, 2] * 2 - 1
#X = Standardiser().standardiseArray(X)
#testX = Standardiser().standardiseArray(testX)
maxDepths = range(3, 10)
trainAucs = numpy.array([
0.7194734, 0.7284824, 0.7332185, 0.7348198, 0.7366152, 0.7367508,
0.7367508, 0.7367508
])
testAucs = numpy.array([
0.6789078, 0.6844632, 0.6867918, 0.6873420, 0.6874820, 0.6874400,
0.6874400, 0.6874400
])
i = 0
#The results are approximately the same, but not exactly
for maxDepth in maxDepths:
treeRank = TreeRank(DecisionTree)
treeRank.setMaxDepth(maxDepth)
treeRank.learnModel(X, y)
trainScores = treeRank.predict(X)
testScores = treeRank.predict(testX)
#print(Evaluator.auc(trainScores, y), Evaluator.auc(testScores, testY))
#self.assertAlmostEquals(Evaluator.auc(trainScores, y), trainAucs[i], 2)
#self.assertAlmostEquals(Evaluator.auc(testScores, testY), testAucs[i], 1)
i += 1
#Compare tree to that of R version
tree = treeRank.getTree()
def testPredict(self):
maxDepth = 2
treeRank = TreeRank(self.leafRanklearner)
treeRank.setMaxDepth(maxDepth)
treeRank.learnModel(self.X, self.y)
scores = treeRank.predict(self.X)
scores2 = numpy.zeros(self.X.shape[0])
# Test if train and test indices are the same
tree = treeRank.getTree()
vertexIds = tree.getAllVertexIds()
for vertexId in vertexIds:
node = tree.getVertex(vertexId)
self.assertTrue((node.getTrainInds() == node.getTestInds()).all())
(d, k) = vertexId
if node.isLeafNode():
self.assertEquals(node.getScore(), (1 - float(k) / 2 ** d) * 2 ** maxDepth)
scores2[node.getTestInds()] = node.getScore()
self.assertTrue((scores == scores2).all())
def testPredict(self):
maxDepth = 2
treeRank = TreeRank(self.leafRanklearner)
treeRank.setMaxDepth(maxDepth)
treeRank.learnModel(self.X, self.y)
scores = treeRank.predict(self.X)
scores2 = numpy.zeros(self.X.shape[0])
#Test if train and test indices are the same
tree = treeRank.getTree()
vertexIds = tree.getAllVertexIds()
for vertexId in vertexIds:
node = tree.getVertex(vertexId)
self.assertTrue((node.getTrainInds() == node.getTestInds()).all())
(d, k) = vertexId
if node.isLeafNode():
self.assertEquals(node.getScore(),
(1 - float(k) / 2**d) * 2**maxDepth)
scores2[node.getTestInds()] = node.getScore()
self.assertTrue((scores == scores2).all())
def testFeaturesSize(self):
treeRank = TreeRank(self.leafRanklearner)
featureSize = 0.5
treeRank.setFeatureSize(featureSize)
treeRank.learnModel(self.X, self.y)
scores = treeRank.predict(self.X)
tree = treeRank.getTree()
vertexIds = tree.getAllVertexIds()
for vertexId in vertexIds:
node = tree.getVertex(vertexId)
# print(node.getFeatureInds())
self.assertEquals(node.getFeatureInds().shape[0], numpy.round(featureSize * self.X.shape[1]))
self.assertEquals(numpy.unique(node.getFeatureInds()).shape[0], node.getFeatureInds().shape[0])
def testFeaturesSize(self):
treeRank = TreeRank(self.leafRanklearner)
featureSize = 0.5
treeRank.setFeatureSize(featureSize)
treeRank.learnModel(self.X, self.y)
scores = treeRank.predict(self.X)
tree = treeRank.getTree()
vertexIds = tree.getAllVertexIds()
for vertexId in vertexIds:
node = tree.getVertex(vertexId)
#print(node.getFeatureInds())
self.assertEquals(node.getFeatureInds().shape[0],
numpy.round(featureSize * self.X.shape[1]))
self.assertEquals(
numpy.unique(node.getFeatureInds()).shape[0],
node.getFeatureInds().shape[0])
