def createLearningCurve(C = 1.0, gamma=0.0):
trainFiles = deepcopy(TRAIN_FILES)
# classifier konfigurieren
learner = getSVM(C=C, gamma=gamma)
domain = getDomain(orange.EnumVariable(name="Shot", values=SHOT_NAMES))
means, vars = getNormalizationTerms(domain)
trainData = getTrainingExamples(domain, trainFiles, True)
a, c, w = trainData.to_numpy()
# train normalisieren
a = (a-means)/vars
A = np.hstack((a,c.reshape(-1,1)))
np.random.shuffle(A)
performance = []
wPerformance = []
for j in range(100, A.shape[0],100):
print("============= TrainingFiles %d ================"%j)
print("training classifier...")
trainData = orange.ExampleTable(domain, A[:j,:])
# train classifier
classifier = learner(trainData)
# training performance
print("testing classifier...")
perf, perfW = getPerformance(classifier, domain, TRAIN_FILES, means, vars)
print("Performance \t: %04f (weighted: %f)"%(perf, perfW))
performance.append(perf)
wPerformance.append(perfW)
return performance, wPerformance
def runExampleForDifferentParams(gammas = (0.0, ), Cs = (1.0, ), i = 5):
domain = getDomain(orange.EnumVariable(name="Shot", values=SHOT_NAMES))
means, vars = getNormalizationTerms(domain)
trainData, testData , trainFiles, testFile = createCrossValidationSet(i, domain)
# train normalisieren
a, c, w = trainData.to_numpy()
a = (a-means)/vars
A = np.hstack((a,c.reshape(-1,1)))
trainData = orange.ExampleTable(domain, A)
for gamma in gammas:
for C in Cs:
print("========== Params (C = %f, gamma = %f) ============"%(C, gamma))
# classifier konfigurieren
learner = getSVM(gamma=gamma, C=C)
# trainingsdaten und testdaten zusammenstellen
print("training classifier...")
# train classifier
classifier = learner(trainData)
print("evaluating test-set performance")
# test set performance
testPerf, testW = getPerformance(classifier, domain, [testFile], means, vars)
print("evaluating train-set performance")
# training performance
trainPerf, trainW = getPerformance(classifier, domain, trainFiles, means, vars)
print("Training Performance \t: %04f (weighted: %f)"%(trainPerf, trainW))
print("Test Performance \t: %04f (weighted: %f)"%(testPerf, testW))
def doAFullRun(C = 1.0, gamma=0.0):
# classifier konfigurieren
learner = getSVM(C=C, gamma=gamma)
domain = getDomain(orange.EnumVariable(name="Shot", values=SHOT_NAMES))
reference_data, _ = getDataMatrix(TRAIN_FILES, True)
means, vars = getNpNormalizationTerms(reference_data)
# trainingsdaten und testdaten zusammenstellen
totalTest = 0.0
totalTrain = 0.0
totalTestW = 0.0
totalTrainW = 0.0
for i in range(len(TRAIN_FILES)):
print("============= Round %d ================" %i)
print("training classifier...")
train_vectors, train_classes, test_vectors, test_classes, train_files, test_file = createCrossValidationSet(i)
# train normalisieren
train_vectors = normalizeNpData(train_vectors, means, vars)
train_data = convertToExampleTable(domain, train_vectors, train_classes)
# train classifier
classifier = learner(train_data)
print("evaluating test-set performance")
# test set performance
testPerf, testW = getPerformance(classifier, domain, [test_file], means, vars)
print("evaluating train-set performance")
# training performance
trainPerf, trainW = getPerformance(classifier, domain, train_files, means, vars)
print("Training Performance \t: %04f (weighted: %f)"%(trainPerf, trainW))
print("Test Performance \t: %04f (weighted: %f)"%(testPerf, testW))
totalTest += testPerf
totalTrain += trainPerf
totalTestW += testW
totalTrainW += trainW
# perfomance bestimmen auf train und testdaten
totalTest /= len(TRAIN_FILES)
totalTrain /= len(TRAIN_FILES)
totalTestW /= len(TRAIN_FILES)
totalTrainW /= len(TRAIN_FILES)
print ("Average Training Performance: %04f (weighted: %f)"%(totalTrain, totalTrainW))
print ("Average Test Performance : %04f (weighted: %f)"%(totalTest, totalTestW))
