numValidExamples = numExamples*0.1 trainX = X[0:numTrainExamples, :] trainY = y[0:numTrainExamples] validX = X[numTrainExamples:numTrainExamples+numValidExamples, :] validY = y[numTrainExamples:numTrainExamples+numValidExamples] testX = X[numTrainExamples+numValidExamples:, :] testY = y[numTrainExamples+numValidExamples:] learner = DecisionTreeLearner(minSplit=1, maxDepth=50) learner.learnModel(trainX, trainY) #Seem to be optimal alphaThreshold = 100.0 learner.setAlphaThreshold(alphaThreshold) learner.repPrune(validX, validY) #learner.tree = learner.tree.cut(3) predY = learner.predict(testX) plt.figure(0) plt.scatter(testX[:, 0], testX[:, 1], c=testY, s=50, vmin=0, vmax=1) plt.colorbar() plt.figure(1) plt.scatter(testX[:, 0], testX[:, 1], c=predY, s=50, vmin=0, vmax=1) plt.colorbar() colormap = matplotlib.cm.get_cmap()
