# compute
result = pca_alg.compute()
self.eigenvalues_ = result.get(pca.eigenvalues)
self.eigenvectors_ = result.get(pca.eigenvectors)
data = np.genfromtxt("cs-data.csv",
delimiter=',',
dtype=np.double,
skip_header=1,
usecols=list(range(1, 11)))
data = data[~np.isnan(data).any(axis=1)]
data = scale(data)
data_nt = HomogenNumericTable(data)
print(data_nt.getNumberOfRows(), data_nt.getNumberOfColumns())
# PCA via SVD
pr = PCA(method='svd')
pr.compute(data_nt)
loadings = getArrayFromNT(pr.eigenvectors_)
ev = getArrayFromNT(pr.eigenvalues_)
print(ev / np.sum(ev))
# PCA via covariances
cov_data = np.cov(data.transpose())
cov_nt = HomogenNumericTable(cov_data)
pr = PCA(method='correlation')
pr.compute(cov_nt)
loadings = getArrayFromNT(pr.eigenvectors_)
ev = getArrayFromNT(pr.eigenvalues_)
def testModel():
thresholdValues = np.linspace(-25.0, 25.0, num=101)
numberOfCorrectlyClassifiedObjects = np.zeros(len(thresholdValues))
numberOfObjectsInTestFiles = 0
numberOfNonzeroObjectsInTestFiles = 0
for filenameIndex in range(0, len(testDatasetFileNames)):
testDataSource = FileDataSource(
testDatasetFileNames[filenameIndex],
DataSourceIface.doAllocateNumericTable,
DataSourceIface.doDictionaryFromContext)
testData = HomogenNumericTable(nFeatures, 0,
NumericTableIface.notAllocate)
testGroundTruth = HomogenNumericTable(nDependentVariables, 0,
NumericTableIface.notAllocate)
mergedData = MergedNumericTable(testData, testGroundTruth)
testDataSource.loadDataBlock(mergedData)
algorithm = prediction.Batch_Float64DefaultDense()
algorithm.input.setNumericTableInput(prediction.data, testData)
algorithm.input.setModelInput(prediction.model,
trainingResult.get(training.model))
predictionResult = algorithm.compute()
block1 = BlockDescriptor()
block2 = BlockDescriptor()
testGroundTruth.getBlockOfRows(0, testGroundTruth.getNumberOfRows(),
readOnly, block1)
predictionResult.get(prediction.prediction).getBlockOfRows(
0, testGroundTruth.getNumberOfRows(), readOnly, block2)
y_true = getClassVector(block1.getArray(), 0.000000000000)
predictionRegression = block2.getArray()
for thresholdIndex in range(0, len(thresholdValues)):
y_pred = getClassVector(predictionRegression,
thresholdValues[thresholdIndex])
numberOfCorrectlyClassifiedObjects[
thresholdIndex] += accuracy_score(y_true,
y_pred,
normalize=False)
numberOfObjectsInTestFiles += len(y_true)
numberOfNonzeroObjectsInTestFiles += np.count_nonzero(y_true)
mergedData.freeDataMemory()
testData.freeDataMemory()
testGroundTruth.freeDataMemory()
classificationAccuracyResult = np.zeros(len(thresholdValues))
best_threshold = None
best_accuracy = -1
for thresholdIndex in range(0, len(thresholdValues)):
classificationAccuracyResult[
thresholdIndex] = numberOfCorrectlyClassifiedObjects[
thresholdIndex] / numberOfObjectsInTestFiles
if (classificationAccuracyResult[thresholdIndex] > best_accuracy):
best_threshold = thresholdValues[thresholdIndex]
best_accuracy = classificationAccuracyResult[thresholdIndex]
print('Best threshold:{:.4f}. Best accuracy:{:.4f}'.format(
best_threshold, best_accuracy))
print(
'Test set. Number of objects of 0 class:{:.4f}.Number of objects of 1 class:{:.4f}. '
'Frequency of 1 class:{:.4f}'.format(
numberOfObjectsInTestFiles - numberOfNonzeroObjectsInTestFiles,
numberOfNonzeroObjectsInTestFiles,
numberOfNonzeroObjectsInTestFiles / numberOfObjectsInTestFiles))
indexOfZeroThreshold = np.where(thresholdValues == 0.0)[0][0]
print('Threshold=0. Classification accuracy:{:.4f}'.format(
classificationAccuracyResult[indexOfZeroThreshold]))