def recursiveSplit(self, X, y, argsortX, nodeId):
"""
Give a sample of data and a node index, we find the best split and
add children to the tree accordingly.
"""
if len(nodeId) - 1 >= self.maxDepth:
return
node = self.tree.getVertex(nodeId)
bestError, bestFeatureInd, bestThreshold, bestLeftInds, bestRightInds = findBestSplit(
self.minSplit, X, y, node.getTrainInds(), argsortX)
#The split may have 0 items in one set, so don't split
if bestLeftInds.sum() != 0 and bestRightInds.sum() != 0:
node.setError(bestError)
node.setFeatureInd(bestFeatureInd)
node.setThreshold(bestThreshold)
leftChildId = self.getLeftChildId(nodeId)
leftChild = DecisionNode(bestLeftInds, y[bestLeftInds].mean())
self.tree.addChild(nodeId, leftChildId, leftChild)
if leftChild.getTrainInds().shape[0] >= self.minSplit:
self.recursiveSplit(X, y, argsortX, leftChildId)
rightChildId = self.getRightChildId(nodeId)
rightChild = DecisionNode(bestRightInds, y[bestRightInds].mean())
self.tree.addChild(nodeId, rightChildId, rightChild)
if rightChild.getTrainInds().shape[0] >= self.minSplit:
self.recursiveSplit(X, y, argsortX, rightChildId)
def recursiveSplit(self, X, y, argsortX, nodeId):
"""
Give a sample of data and a node index, we find the best split and
add children to the tree accordingly.
"""
if len(nodeId)-1 >= self.maxDepth:
return
node = self.tree.getVertex(nodeId)
bestError, bestFeatureInd, bestThreshold, bestLeftInds, bestRightInds = findBestSplit(self.minSplit, X, y, node.getTrainInds(), argsortX)
#The split may have 0 items in one set, so don't split
if bestLeftInds.sum() != 0 and bestRightInds.sum() != 0:
node.setError(bestError)
node.setFeatureInd(bestFeatureInd)
node.setThreshold(bestThreshold)
leftChildId = self.getLeftChildId(nodeId)
leftChild = DecisionNode(bestLeftInds, y[bestLeftInds].mean())
self.tree.addChild(nodeId, leftChildId, leftChild)
if leftChild.getTrainInds().shape[0] >= self.minSplit:
self.recursiveSplit(X, y, argsortX, leftChildId)
rightChildId = self.getRightChildId(nodeId)
rightChild = DecisionNode(bestRightInds, y[bestRightInds].mean())
self.tree.addChild(nodeId, rightChildId, rightChild)
if rightChild.getTrainInds().shape[0] >= self.minSplit:
self.recursiveSplit(X, y, argsortX, rightChildId)
def growTree(self, X, y, argsortX, startId):
"""
Grow a tree using a stack. Give a sample of data and a node index, we
find the best split and add children to the tree accordingly. We perform
pre-pruning based on the penalty.
"""
eps = 10**-4
idStack = [startId]
while len(idStack) != 0:
nodeId = idStack.pop()
node = self.tree.getVertex(nodeId)
accuracies, thresholds = findBestSplitRisk(self.minSplit, X, y,
node.getTrainInds(),
argsortX)
#Choose best feature based on gains
accuracies += eps
bestFeatureInd = Util.randomChoice(accuracies)[0]
bestThreshold = thresholds[bestFeatureInd]
nodeInds = node.getTrainInds()
bestLeftInds = numpy.sort(nodeInds[numpy.arange(nodeInds.shape[0])[
X[:, bestFeatureInd][nodeInds] < bestThreshold]])
bestRightInds = numpy.sort(nodeInds[numpy.arange(
nodeInds.shape[0])[
X[:, bestFeatureInd][nodeInds] >= bestThreshold]])
#The split may have 0 items in one set, so don't split
if bestLeftInds.sum() != 0 and bestRightInds.sum(
) != 0 and self.tree.depth() < self.maxDepth:
node.setError(1 - accuracies[bestFeatureInd])
node.setFeatureInd(bestFeatureInd)
node.setThreshold(bestThreshold)
leftChildId = self.getLeftChildId(nodeId)
leftChild = DecisionNode(bestLeftInds,
Util.mode(y[bestLeftInds]))
self.tree.addChild(nodeId, leftChildId, leftChild)
if leftChild.getTrainInds().shape[0] >= self.minSplit:
idStack.append(leftChildId)
rightChildId = self.getRightChildId(nodeId)
rightChild = DecisionNode(bestRightInds,
Util.mode(y[bestRightInds]))
self.tree.addChild(nodeId, rightChildId, rightChild)
if rightChild.getTrainInds().shape[0] >= self.minSplit:
idStack.append(rightChildId)
def growSkLearn(self, X, y):
"""
Grow a decision tree from sklearn.
"""
from sklearn.tree import DecisionTreeRegressor
regressor = DecisionTreeRegressor(max_depth=self.maxDepth,
min_samples_split=self.minSplit)
regressor.fit(X, y)
#Convert the sklearn tree into our tree
nodeId = (0, )
nodeStack = [(nodeId, 0)]
node = DecisionNode(numpy.arange(X.shape[0]), regressor.tree_.value[0])
self.tree.setVertex(nodeId, node)
while len(nodeStack) != 0:
nodeId, nodeInd = nodeStack.pop()
node = self.tree.getVertex(nodeId)
node.setError(regressor.tree_.best_error[nodeInd])
node.setFeatureInd(regressor.tree_.feature[nodeInd])
node.setThreshold(regressor.tree_.threshold[nodeInd])
if regressor.tree_.children[nodeInd, 0] != -1:
leftChildInds = node.getTrainInds()[
X[node.getTrainInds(),
node.getFeatureInd()] < node.getThreshold()]
leftChildId = self.getLeftChildId(nodeId)
leftChild = DecisionNode(
leftChildInds,
regressor.tree_.value[regressor.tree_.children[nodeInd,
0]])
self.tree.addChild(nodeId, leftChildId, leftChild)
nodeStack.append((self.getLeftChildId(nodeId),
regressor.tree_.children[nodeInd, 0]))
if regressor.tree_.children[nodeInd, 1] != -1:
rightChildInds = node.getTrainInds()[
X[node.getTrainInds(),
node.getFeatureInd()] >= node.getThreshold()]
rightChildId = self.getRightChildId(nodeId)
rightChild = DecisionNode(
rightChildInds,
regressor.tree_.value[regressor.tree_.children[nodeInd,
1]])
self.tree.addChild(nodeId, rightChildId, rightChild)
nodeStack.append((self.getRightChildId(nodeId),
regressor.tree_.children[nodeInd, 1]))
def growTree(self, X, y, argsortX, startId):
"""
Grow a tree using a stack. Give a sample of data and a node index, we
find the best split and add children to the tree accordingly. We perform
pre-pruning based on the penalty.
"""
eps = 10**-4
idStack = [startId]
while len(idStack) != 0:
nodeId = idStack.pop()
node = self.tree.getVertex(nodeId)
accuracies, thresholds = findBestSplitRisk(self.minSplit, X, y, node.getTrainInds(), argsortX)
#Choose best feature based on gains
accuracies += eps
bestFeatureInd = Util.randomChoice(accuracies)[0]
bestThreshold = thresholds[bestFeatureInd]
nodeInds = node.getTrainInds()
bestLeftInds = numpy.sort(nodeInds[numpy.arange(nodeInds.shape[0])[X[:, bestFeatureInd][nodeInds]<bestThreshold]])
bestRightInds = numpy.sort(nodeInds[numpy.arange(nodeInds.shape[0])[X[:, bestFeatureInd][nodeInds]>=bestThreshold]])
#The split may have 0 items in one set, so don't split
if bestLeftInds.sum() != 0 and bestRightInds.sum() != 0 and self.tree.depth() < self.maxDepth:
node.setError(1-accuracies[bestFeatureInd])
node.setFeatureInd(bestFeatureInd)
node.setThreshold(bestThreshold)
leftChildId = self.getLeftChildId(nodeId)
leftChild = DecisionNode(bestLeftInds, Util.mode(y[bestLeftInds]))
self.tree.addChild(nodeId, leftChildId, leftChild)
if leftChild.getTrainInds().shape[0] >= self.minSplit:
idStack.append(leftChildId)
rightChildId = self.getRightChildId(nodeId)
rightChild = DecisionNode(bestRightInds, Util.mode(y[bestRightInds]))
self.tree.addChild(nodeId, rightChildId, rightChild)
if rightChild.getTrainInds().shape[0] >= self.minSplit:
idStack.append(rightChildId)
def growSkLearn(self, X, y):
"""
Grow a decision tree from sklearn.
"""
from sklearn.tree import DecisionTreeRegressor
regressor = DecisionTreeRegressor(max_depth = self.maxDepth, min_samples_split=self.minSplit)
regressor.fit(X, y)
#Convert the sklearn tree into our tree
nodeId = (0, )
nodeStack = [(nodeId, 0)]
node = DecisionNode(numpy.arange(X.shape[0]), regressor.tree_.value[0])
self.tree.setVertex(nodeId, node)
while len(nodeStack) != 0:
nodeId, nodeInd = nodeStack.pop()
node = self.tree.getVertex(nodeId)
node.setError(regressor.tree_.best_error[nodeInd])
node.setFeatureInd(regressor.tree_.feature[nodeInd])
node.setThreshold(regressor.tree_.threshold[nodeInd])
if regressor.tree_.children[nodeInd, 0] != -1:
leftChildInds = node.getTrainInds()[X[node.getTrainInds(), node.getFeatureInd()] < node.getThreshold()]
leftChildId = self.getLeftChildId(nodeId)
leftChild = DecisionNode(leftChildInds, regressor.tree_.value[regressor.tree_.children[nodeInd, 0]])
self.tree.addChild(nodeId, leftChildId, leftChild)
nodeStack.append((self.getLeftChildId(nodeId), regressor.tree_.children[nodeInd, 0]))
if regressor.tree_.children[nodeInd, 1] != -1:
rightChildInds = node.getTrainInds()[X[node.getTrainInds(), node.getFeatureInd()] >= node.getThreshold()]
rightChildId = self.getRightChildId(nodeId)
rightChild = DecisionNode(rightChildInds, regressor.tree_.value[regressor.tree_.children[nodeInd, 1]])
self.tree.addChild(nodeId, rightChildId, rightChild)
nodeStack.append((self.getRightChildId(nodeId), regressor.tree_.children[nodeInd, 1]))
