def testSetSvmType(self): try: import sklearn except ImportError as error: return numExamples = 100 numFeatures = 10 X = numpy.random.randn(numExamples, numFeatures) X = Standardiser().standardiseArray(X) c = numpy.random.randn(numFeatures) y = numpy.dot(X, numpy.array([c]).T).ravel() + 1 y2 = numpy.array(y > 0, numpy.int32) * 2 - 1 svm = LibSVM() svm.setSvmType("Epsilon_SVR") self.assertEquals(svm.getType(), "Epsilon_SVR") #Try to get a good error Cs = 2**numpy.arange(-6, 4, dtype=numpy.float) epsilons = 2**numpy.arange(-6, 4, dtype=numpy.float) bestError = 10 for C in Cs: for epsilon in epsilons: svm.setEpsilon(epsilon) svm.setC(C) svm.learnModel(X, y) yp = svm.predict(X) if Evaluator.rootMeanSqError(y, yp) < bestError: bestError = Evaluator.rootMeanSqError(y, yp) self.assertTrue( bestError < Evaluator.rootMeanSqError(y, numpy.zeros(y.shape[0]))) svm.setSvmType("C_SVC") svm.learnModel(X, y2) yp2 = svm.predict(X) self.assertTrue(0 <= Evaluator.binaryError(y2, yp2) <= 1)
def testSetSvmType(self): try: import sklearn except ImportError as error: return numExamples = 100 numFeatures = 10 X = numpy.random.randn(numExamples, numFeatures) X = Standardiser().standardiseArray(X) c = numpy.random.randn(numFeatures) y = numpy.dot(X, numpy.array([c]).T).ravel() + 1 y2 = numpy.array(y > 0, numpy.int32)*2 -1 svm = LibSVM() svm.setSvmType("Epsilon_SVR") self.assertEquals(svm.getType(), "Epsilon_SVR") #Try to get a good error Cs = 2**numpy.arange(-6, 4, dtype=numpy.float) epsilons = 2**numpy.arange(-6, 4, dtype=numpy.float) bestError = 10 for C in Cs: for epsilon in epsilons: svm.setEpsilon(epsilon) svm.setC(C) svm.learnModel(X, y) yp = svm.predict(X) if Evaluator.rootMeanSqError(y, yp) < bestError: bestError = Evaluator.rootMeanSqError(y, yp) self.assertTrue(bestError < Evaluator.rootMeanSqError(y, numpy.zeros(y.shape[0]))) svm.setSvmType("C_SVC") svm.learnModel(X, y2) yp2 = svm.predict(X) self.assertTrue(0 <= Evaluator.binaryError(y2, yp2) <= 1)
def testCvPrune(self): numExamples = 500 X, y = data.make_regression(numExamples) y = Standardiser().standardiseArray(y) numTrain = numpy.round(numExamples * 0.33) numValid = numpy.round(numExamples * 0.33) trainX = X[0:numTrain, :] trainY = y[0:numTrain] validX = X[numTrain:numTrain+numValid, :] validY = y[numTrain:numTrain+numValid] testX = X[numTrain+numValid:, :] testY = y[numTrain+numValid:] learner = DecisionTreeLearner() learner.learnModel(trainX, trainY) error1 = Evaluator.rootMeanSqError(learner.predict(testX), testY) #print(learner.getTree()) unprunedTree = learner.tree.copy() learner.setGamma(1000) learner.cvPrune(trainX, trainY) self.assertEquals(unprunedTree.getNumVertices(), learner.tree.getNumVertices()) learner.setGamma(100) learner.cvPrune(trainX, trainY) #Test if pruned tree is subtree of current: for vertexId in learner.tree.getAllVertexIds(): self.assertTrue(vertexId in unprunedTree.getAllVertexIds()) #The error should be better after pruning learner.learnModel(trainX, trainY) #learner.cvPrune(validX, validY, 0.0, 5) learner.repPrune(validX, validY) error2 = Evaluator.rootMeanSqError(learner.predict(testX), testY) self.assertTrue(error1 >= error2)
#Figure out why the penalty is increasing X = trainX y = trainY for i in range(foldsSet.shape[0]): folds = foldsSet[i] idx = Sampling.crossValidation(folds, validX.shape[0]) penalty = 0 fullError = 0 trainError = 0 learner.learnModel(validX, validY) predY = learner.predict(X) predValidY = learner.predict(validX) idealPenalty = Evaluator.rootMeanSqError(predY, y) - Evaluator.rootMeanSqError(predValidY, validY) for trainInds, testInds in idx: trainX = validX[trainInds, :] trainY = validY[trainInds] #learner.setGamma(gamma) #learner.setC(C) learner.learnModel(trainX, trainY) predY = learner.predict(validX) predTrainY = learner.predict(trainX) fullError += Evaluator.rootMeanSqError(predY, validY) trainError += Evaluator.rootMeanSqError(predTrainY, trainY) penalty += Evaluator.rootMeanSqError(predY, validY) - Evaluator.rootMeanSqError(predTrainY, trainY) print((folds-1)*fullError/folds, (folds-1)*trainError/folds, (folds-1)*penalty/folds)
def testModelSelect(self): """ We test the results on some data and compare to SVR. """ numExamples = 200 X, y = data.make_regression(numExamples, noise=0.5) X = Standardiser().standardiseArray(X) y = Standardiser().standardiseArray(y) trainX = X[0:100, :] trainY = y[0:100] testX = X[100:, :] testY = y[100:] learner = DecisionTreeLearner(maxDepth=20, minSplit=10, pruneType="REP-CV") learner.setPruneCV(8) paramDict = {} paramDict["setGamma"] = numpy.linspace(0.0, 1.0, 10) paramDict["setPruneCV"] = numpy.arange(6, 11, 2, numpy.int) folds = 5 idx = Sampling.crossValidation(folds, trainX.shape[0]) bestTree, cvGrid = learner.parallelModelSelect(trainX, trainY, idx, paramDict) predY = bestTree.predict(testX) error = Evaluator.rootMeanSqError(testY, predY) print(error) learner = DecisionTreeLearner(maxDepth=20, minSplit=5, pruneType="CART") paramDict = {} paramDict["setGamma"] = numpy.linspace(0.0, 1.0, 50) folds = 5 idx = Sampling.crossValidation(folds, trainX.shape[0]) bestTree, cvGrid = learner.parallelModelSelect(trainX, trainY, idx, paramDict) predY = bestTree.predict(testX) error = Evaluator.rootMeanSqError(testY, predY) print(error) return #Let's compare to the SVM learner2 = LibSVM(kernel='gaussian', type="Epsilon_SVR") paramDict = {} paramDict["setC"] = 2.0**numpy.arange(-10, 14, 2, dtype=numpy.float) paramDict["setGamma"] = 2.0**numpy.arange(-10, 4, 2, dtype=numpy.float) paramDict["setEpsilon"] = learner2.getEpsilons() idx = Sampling.crossValidation(folds, trainX.shape[0]) bestSVM, cvGrid = learner2.parallelModelSelect(trainX, trainY, idx, paramDict) predY = bestSVM.predict(testX) error = Evaluator.rootMeanSqError(testY, predY) print(error)
minAlpha = alpha if alpha > maxAlpha: maxAlpha = alpha numAlphas = 100 alphas = numpy.linspace(maxAlpha+0.1, minAlpha, numAlphas) errors = numpy.zeros(numAlphas) for i in range(alphas.shape[0]): #learner.learnModel(trainX, trainY) learner.setAlphaThreshold(alphas[i]) learner.cvPrune(trainX, trainY) #learner.cvPrune(validX, validY, alphas[numpy.argmin(errors)]) #learner.prune(validX, validY, alphas[i]) predY = learner.predict(testX) errors[i] = Evaluator.rootMeanSqError(predY, testY) plt.figure(3) plt.scatter(alphas, errors) #Now plot best tree plt.figure(4) learner.learnModel(trainX, trainY) #learner.cvPrune(validX, validY, alphas[numpy.argmin(errors)]) learner.setAlphaThreshold(alphas[numpy.argmin(errors)]) learner.cvPrune(trainX, trainY) rootId = learner.tree.getRootId() displayTree(learner, rootId, 0, 1, 0, 1, colormap) plt.show()