def bagAndTrain(self, tree, dataMatrix, classVectors): numToBag = int(helpers.HyperParams.FRAC_PER_BAG * dataMatrix.shape[0]) baggedIndices = helpers.bag(np.arange(dataMatrix.shape[0]), numToBag) tree.train(dataMatrix.iloc[baggedIndices], classVectors.iloc[baggedIndices]) baggedIndicesBool = np.zeros(dataMatrix.shape[0], dtype=bool) baggedIndicesBool[baggedIndices] = True return baggedIndicesBool
def trainBoosted(self, dataMatrix, classVectors):
mislabels = self.getMislabelSet(np.arange(
dataMatrix.shape[0]), classVectors)
distribution = np.ones(mislabels.shape[0])
distribution = helpers.toProbDistribution(distribution)
numToBag = int(mislabels.shape[0])
for tree in self.trees:
mislabelIndices = helpers.bag(np.arange(mislabels.shape[0]),
numToBag, distribution)
tree.train(dataMatrix.iloc[mislabels[mislabelIndices][:,0]],
classVectors.iloc[mislabels[mislabelIndices][:,0]])
loss = self.calculatePseudoLoss(tree, dataMatrix,
mislabels, distribution)
beta = loss/(1-loss)
self.boostedBeta.append(beta)
distribution = self.updateDistribution(tree, dataMatrix, mislabels,
distribution, beta)