def testBayes(training, test, labels, targetPath):
if targetPath.endswith('/') == False:
targetPath += '/'
if not os.path.exists(os.path.dirname(targetPath)):
os.makedirs(os.path.dirname(targetPath))
labelCount = len(labels)
neurons = training.shape[1] - labelCount
minTraining = np.min(training[:, 0:neurons])
minTest = np.min(test[:, 0:neurons])
absoluteMin = 0
if minTraining < minTest:
absoluteMin = minTraining
else:
absoluteMin = minTest
training[:, 0:neurons] = training[:, 0:neurons] + np.abs(absoluteMin)
test[:, 0:neurons] = test[:, 0:neurons] + np.abs(absoluteMin)
PLog = tb.trainBayes(training, labelCount)
overallCorrect = 0
overallWrong = 0
meanAveragePrecision = 0
featuresByLabel = utility.splitTestFeaturesByLabel(test, len(labels))
confusionMatrix = np.zeros((labelCount, labelCount))
for labelIndex, activations in enumerate(featuresByLabel):
counter = 0
while counter < activations.shape[0]:
currentActivation = activations[counter, 0:neurons]
searchedLabel = np.argmax(activations[counter, neurons:])
predictions = currentActivation * PLog
predictions = np.sum(predictions, axis=1)
if np.argmax(predictions) == searchedLabel:
overallCorrect += 1
else:
overallWrong += 1
confusionMatrix[labelIndex, np.argmax(predictions)] += 1
averagePrecision = 0
relevant = 0
predictedLabelsSorted = np.argsort(predictions)[::-1]
for idx, value in enumerate(predictedLabelsSorted):
indicator = 0
if (value == searchedLabel):
indicator = 1
relevant += 1
precision = float(relevant) / (idx + 1)
averagePrecision += (precision * indicator)
if relevant != 0:
averagePrecision = float(averagePrecision) / relevant
meanAveragePrecision += averagePrecision
counter += 1
meanAveragePrecision = float(meanAveragePrecision) / test.shape[0]
logger.info(' Accuracy: ' +
str(float(overallCorrect) / (overallWrong + overallCorrect)))
logger.info(' Mean average precision: ' + str(meanAveragePrecision))
utility.plotConfusionMatrix(confusionMatrix, labels,
targetPath + "confusion.pdf")
results = [0, meanAveragePrecision, overallCorrect, overallWrong]
logger.info('Writing file ' + targetPath + "overview.csv")
np.savetxt(targetPath + "overview.csv", results, delimiter=',')
def runTest(clusters, testFeatures, labels, perLabel):
labelCount = len(labels)
neurons = activations.shape[1] - labelCount
confusionMatrix = np.zeros((labelCount,labelCount))
# split activations by label
activationsByLabel = utility.splitTestFeaturesByLabel(testFeatures, labelCount)
overallCorrect = 0
overallWrong = 0
meanAveragePrecision = 0
# evaluate
for labelIndex, values in enumerate(activationsByLabel):
confusion = np.zeros((1,len(labels)))
activationCounter = 0
while activationCounter < values.shape[0]:
currentActivation = values[activationCounter]
clusterRanking = kMeans_core.predictSimple(clusters, currentActivation, neurons)
bestCluster = clusters[clusterRanking[0]]
confusion[0,np.argmax(bestCluster[neurons:])] += 1
if np.argmax(bestCluster[neurons:]) == np.argwhere(currentActivation[neurons:] == 1):
overallCorrect += 1
else:
overallWrong += 1
averagePrecision = 0
relevant = 0
sortedPredictions = None
if perLabel == False:
sortedPredictions = np.argsort(bestCluster[neurons:])[::-1].tolist()
else:
sortedPredictions = np.argmax(clusters[clusterRanking][:,neurons:], axis=1)
# logger.debug(sortedPredictions)
for idx, value in enumerate(sortedPredictions):
indicator = 0
if(value == np.argwhere(currentActivation[neurons:] == 1)):
if perLabel == False and bestCluster[neurons + value] == 0: # ingore if 0 in histogram
continue
indicator = 1
relevant += 1
precision = float(relevant) / (idx + 1)
averagePrecision += (precision * indicator)
if relevant != 0:
averagePrecision = float(averagePrecision) / relevant
meanAveragePrecision += averagePrecision
activationCounter += 1
confusionMatrix[labelIndex,:] = confusion
meanAveragePrecision = float(meanAveragePrecision) / activations.shape[0]
logger.info(' Accuracy: ' + str(float(overallCorrect)/(overallWrong + overallCorrect)))
logger.info(' Mean average precision: '+str(meanAveragePrecision))
return [confusionMatrix, meanAveragePrecision, overallCorrect, overallWrong]
def testBayes(training, test, labels, targetPath):
if targetPath.endswith('/') == False:
targetPath += '/'
if not os.path.exists(os.path.dirname(targetPath)):
os.makedirs(os.path.dirname(targetPath))
labelCount = len(labels)
neurons = training.shape[1] - labelCount
minTraining = np.min(training[:,0:neurons])
minTest = np.min(test[:,0:neurons])
absoluteMin = 0
if minTraining < minTest:
absoluteMin = minTraining
else:
absoluteMin = minTest
training[:,0:neurons] = training[:,0:neurons] + np.abs(absoluteMin)
test[:,0:neurons] = test[:,0:neurons] + np.abs(absoluteMin)
PLog = tb.trainBayes(training, labelCount)
overallCorrect = 0
overallWrong = 0
meanAveragePrecision = 0
featuresByLabel = utility.splitTestFeaturesByLabel(test, len(labels))
confusionMatrix = np.zeros((labelCount,labelCount))
for labelIndex, activations in enumerate(featuresByLabel):
counter = 0
while counter < activations.shape[0]:
currentActivation = activations[counter,0:neurons]
searchedLabel = np.argmax(activations[counter,neurons:])
predictions = currentActivation * PLog
predictions = np.sum(predictions, axis=1)
if np.argmax(predictions) == searchedLabel:
overallCorrect += 1
else:
overallWrong += 1
confusionMatrix[labelIndex,np.argmax(predictions)] += 1
averagePrecision = 0
relevant = 0
predictedLabelsSorted = np.argsort(predictions)[::-1]
for idx, value in enumerate(predictedLabelsSorted):
indicator = 0
if(value == searchedLabel):
indicator = 1
relevant += 1
precision = float(relevant) / (idx + 1)
averagePrecision += (precision * indicator)
if relevant != 0:
averagePrecision = float(averagePrecision) / relevant
meanAveragePrecision += averagePrecision
counter += 1
meanAveragePrecision = float(meanAveragePrecision) / test.shape[0]
logger.info(' Accuracy: ' + str(float(overallCorrect)/(overallWrong + overallCorrect)))
logger.info(' Mean average precision: '+str(meanAveragePrecision))
utility.plotConfusionMatrix(confusionMatrix, labels, targetPath + "confusion.pdf")
results = [0, meanAveragePrecision, overallCorrect, overallWrong]
logger.info('Writing file ' + targetPath + "overview.csv")
np.savetxt( targetPath + "overview.csv", results, delimiter=',')
