def test(classifierPath, testPath):
# Initialize
alphas, weakClassifierPaths = loadAlphaPaths(classifierPath)
# Get results so that each row corresponds to a weak classifier
classifierResults = [classifier.test(x, testPath) for x in weakClassifierPaths]
# Rearrange results so that each row corresponds to a sample
sampleResults = numpy.array(classifierResults).transpose()
# Decide labels
predictedLabels = [decideLabel(alphas, predictedLabels) for predictedLabels in sampleResults]
# Return
return numpy.array(predictedLabels)
def train(targetClassifierPath, trainingPath, testPath, parameterByName):
# Set paths
store.makeFolderSafely(targetClassifierPath)
# Count the number of training samples
trainingCount = classifier.getSampleCount(trainingPath)
# Initialize weights uniformly over training samples
sampleWeights = numpy.array([1 / float(trainingCount)] * trainingCount)
# Initialize
alphas = []; boostCount = parameterByName['boost count']
# For each boost,
for boostIndex in xrange(boostCount):
# Show feedback
print '--- Boosting %d/%d ---' % (boostIndex + 1, boostCount)
# Normalize sampleWeights
sampleWeights = sampleWeights / float(sum(sampleWeights))
# Weight samples
weightedTrainingPath, sampleMultipliers = weightSamples(trainingPath, sampleWeights)
# Train weak classifier
weakClassifierPath = os.path.join(targetClassifierPath, 'weak%d' % boostIndex)
weakResultByName = classifier.train(weakClassifierPath, weightedTrainingPath, testPath, parameterByName)
shutil.rmtree(os.path.split(weightedTrainingPath)[0])
# Test weak classifier on training set
predictedLabels = classifier.test(weakClassifierPath, trainingPath)
actualLabels = classifier.loadLabels(trainingPath)
errorDistribution = predictedLabels != actualLabels
# Compute training error weighted according to sampleWeights
weightedError = numpy.dot(sampleWeights, errorDistribution)
# Prevent zero division or zero log
if weightedError == 0: weightedError = 1e-9
elif weightedError == 1: weightedError = 1 - 1e-9
# Get alpha from training error
alpha = 0.5 * numpy.log(float(1 - weightedError) / weightedError)
coefficients = [numpy.exp(alpha) if isWrong else numpy.exp(-alpha) for isWrong in errorDistribution]
# Save weakClassifier performance
print 'weighted training error = %s' % (100 * weightedError)
print 'alpha = %s' % alpha
weakResultByName['alpha'] = alpha
weakResultByName['weighted training error'] = weightedError
weakResultByName['sample multipliers'] = ' '.join(str(x) for x in sampleMultipliers)
weakResultByName['error distribution'] = ''.join(str(int(x)) for x in errorDistribution)
saveWeakClassifierInformation(weakClassifierPath, trainingPath, testPath, parameterByName, {'performance': weakResultByName})
# Update sampleWeights
sampleWeights = coefficients * sampleWeights
# Append
alphas.append(alpha)
# Save classifier
save(targetClassifierPath, alphas)
# Return evaluation
return evaluate(targetClassifierPath, testPath)
