How to use daal - 10 common examples

def get_daal_prediction(x=np.array([1,2,3]), y=np.array([1,2,3])):
        ntX = HomogenNumericTable(x)
        ntY = HomogenNumericTable(y)

        lr_train = linear_training.Batch()
        lr_train.input.set(linear_training.data, ntX)
        lr_train.input.set(linear_training.dependentVariables, ntY)
        result = lr_train.compute()
        model = result.get(linear_training.model)

        lr_predict = linear_prediction.Batch()
        lr_predict.input.setModel(linear_prediction.model, model)
        lr_predict.input.setTable(linear_prediction.data, ntX)
        result = lr_predict.compute()

        np_predicted = getNumpyArray(result.get(linear_prediction.prediction))
        # assert the same as the initial dependent variable
        assert_array_almost_equal(y, np_predicted)

def testModel():
    global testGroundTruth, predictionResult

    # Initialize FileDataSource to retrieve the test data from a .csv file
    testDataSource = FileDataSource(
        testDatasetFileName,
        DataSourceIface.notAllocateNumericTable,
        DataSourceIface.doDictionaryFromContext
    )

    # Create Numeric Tables for testing data and labels
    testData = HomogenNumericTable(nFeatures, 0, NumericTableIface.notAllocate)
    testGroundTruth = HomogenNumericTable(1, 0, NumericTableIface.notAllocate)
    mergedData = MergedNumericTable(testData, testGroundTruth)

    # Retrieve the data from input file
    testDataSource.loadDataBlock(mergedData)

    #  Get the dictionary and update it with additional information about data
    dict = testData.getDictionary()

    #  Add a feature type to the dictionary
    dict[0].featureType = features.DAAL_CONTINUOUS
    dict[1].featureType = features.DAAL_CONTINUOUS
    dict[2].featureType = features.DAAL_CATEGORICAL

    # Create algorithm objects for decision forest classification prediction with the default method
    algorithm = prediction.Batch(nClasses)

for j in range(int(rowOffsets[i] - 1), int(rowOffsets[i + 1] - 1)):
            for k in range(1, nBlocks + 1):
                if dataBlockPartition[k -
                                      1] <= colIndices[j] - 1 and colIndices[j] - 1 < dataBlockPartition[k]:
                    blockIdFlags[(k - 1) * nRows + i] = 1

    nNotNull = [0] * nBlocks
    for i in range(nBlocks):
        nNotNull[i] = 0
        for j in range(nRows):
            nNotNull[i] += blockIdFlags[i * nRows + j]

    result = KeyValueDataCollection()

    for i in range(nBlocks):
        indicesTable = HomogenNumericTable(
            1, int(nNotNull[i]), NumericTableIface.doAllocate, ntype=np.intc)
        indices = indicesTable.getArray()
        indexId = 0

        for j in range(nRows):
            if blockIdFlags[i * nRows + j]:
                indices[indexId] = int(j)
                indexId += 1
        result[i] = indicesTable

    return result

def testModel():
    global predictionResult, groundTruthLabels

    # Initialize FileDataSource to retrieve the input data from a .csv file
    testDataSource = FileDataSource(
        testDatasetFileName, DataSourceIface.doAllocateNumericTable,
        DataSourceIface.doDictionaryFromContext
    )

    # Create Numeric Tables for testing data and labels
    testData = HomogenNumericTable(nFeatures, 0, NumericTableIface.doNotAllocate)
    groundTruthLabels = HomogenNumericTable(1, 0, NumericTableIface.doNotAllocate)
    mergedData = MergedNumericTable(testData, groundTruthLabels)

    # Retrieve the data from input file
    testDataSource.loadDataBlock(mergedData)

    # Create an algorithm object to predict SVM values
    algorithm = svm.prediction.Batch()

    algorithm.parameter.kernel = kernel

    # Pass a testing data set and the trained model to the algorithm
    algorithm.input.setTable(classifier.prediction.data, testData)
    algorithm.input.setModel(classifier.prediction.model, trainingResult.get(classifier.training.model))

    # Predict SVM values

def trainModel():
    global trainingResult

    # Initialize FileDataSource to retrieve the input data from a .csv file
    trainDataSource = FileDataSource(
        trainDatasetFileName, DataSourceIface.notAllocateNumericTable,
        DataSourceIface.doDictionaryFromContext
    )

    # Create Numeric Tables for training data and labels
    trainData = HomogenNumericTable(nFeatures, 0, NumericTableIface.doNotAllocate)
    trainGroundTruth = HomogenNumericTable(1, 0, NumericTableIface.doNotAllocate)
    mergedData = MergedNumericTable(trainData, trainGroundTruth)

    # Retrieve the data from the input file
    trainDataSource.loadDataBlock(mergedData)

    # Create an algorithm object to train the AdaBoost model
    algorithm = training.Batch()

    # Pass the training data set and dependent values to the algorithm
    algorithm.input.set(classifier.training.data, trainData)
    algorithm.input.set(classifier.training.labels, trainGroundTruth)

    # Train the AdaBoost model and retrieve the results of the training algorithm
    trainingResult = algorithm.compute()

trainGroundTruth = HomogenNumericTable(1, 0, NumericTableIface.notAllocate)
    mergedData = MergedNumericTable(trainData, trainGroundTruth)

    # Retrieve the data from the input file
    trainDataSource.loadDataBlock(mergedData)

    # Initialize FileDataSource to retrieve the input data from a .csv file
    pruneDataSource = FileDataSource(
        pruneDatasetFileName,
        DataSourceIface.notAllocateNumericTable,
        DataSourceIface.doDictionaryFromContext
    )

    # Create Numeric Tables for pruning data and labels
    pruneData = HomogenNumericTable(nFeatures, 0, NumericTableIface.notAllocate)
    pruneGroundTruth = HomogenNumericTable(1, 0, NumericTableIface.notAllocate)
    pruneMergedData = MergedNumericTable(pruneData, pruneGroundTruth)

    # Retrieve the data from the input file
    pruneDataSource.loadDataBlock(pruneMergedData)

    # Create an algorithm object to train the decision tree classification model
    algorithm = training.Batch(nClasses)

    # Pass the training data set and dependent values to the algorithm
    algorithm.input.set(classifier.training.data, trainData)
    algorithm.input.set(classifier.training.labels, trainGroundTruth)
    algorithm.input.setTable(training.dataForPruning, pruneData)
    algorithm.input.setTable(training.labelsForPruning, pruneGroundTruth)

    # Train the decision tree classification model and retrieve the results of the training algorithm
    trainingResult = algorithm.compute()

def testModel():
    global testGroundTruth, predictionResult

    # Initialize FileDataSource to retrieve the test data from a .csv file
    testDataSource = FileDataSource(
        testDatasetFileName,
        DataSourceIface.notAllocateNumericTable,
        DataSourceIface.doDictionaryFromContext
    )

    # Create Numeric Tables for testing data and labels
    testData = HomogenNumericTable(nFeatures, 0, NumericTableIface.doNotAllocate)
    testGroundTruth = HomogenNumericTable(1, 0, NumericTableIface.doNotAllocate)
    mergedData = MergedNumericTable(testData, testGroundTruth)

    # Retrieve the data from input file
    testDataSource.loadDataBlock(mergedData)

    # Create algorithm objects for LogitBoost prediction with the default method
    algorithm = prediction.Batch(nClasses)

    # Pass the testing data set and trained model to the algorithm
    algorithm.input.setTable(classifier.prediction.data,  testData)
    algorithm.input.setModel(classifier.prediction.model, model)

    # Compute prediction results and retrieve algorithm results
    # (Result class from classifier.prediction)
    predictionResult = algorithm.compute()

def trainModel():
    # Read training data set from a .csv file and create a tensor to store input data
    trainingData = readTensorFromCSV(trainDatasetFile)
    trainingGroundTruth = readTensorFromCSV(trainGroundTruthFile, True)

    sgdAlgorithm = optimization_solver.sgd.Batch(fptype=np.float32)

    # Set learning rate for the optimization solver used in the neural network
    learningRate = 0.001
    sgdAlgorithm.parameter.learningRateSequence = HomogenNumericTable(1, 1, NumericTable.doAllocate, learningRate)
    # Set the batch size for the neural network training
    sgdAlgorithm.parameter.batchSize = batchSize
    sgdAlgorithm.parameter.nIterations = int(trainingData.getDimensionSize(0) / sgdAlgorithm.parameter.batchSize)

    # Create an algorithm to train neural network
    net = training.Batch(sgdAlgorithm)

    sampleSize = trainingData.getDimensions()
    sampleSize[0] = batchSize

    # Configure the neural network
    topology = configureNet()
    net.initialize(sampleSize, topology)

    # Pass a training data set and dependent values to the algorithm
    net.input.setInput(training.data, trainingData)

def testModel():
    global predictionResult, testGroundTruth

    # Initialize FileDataSource to retrieve the test data from a .csv file
    testDataSource = FileDataSource(
        testDatasetFileName, DataSourceIface.notAllocateNumericTable,
        DataSourceIface.doDictionaryFromContext
    )

    # Create Numeric Tables for testing data and labels
    testData = HomogenNumericTable(nFeatures, 0, NumericTableIface.doNotAllocate)
    testGroundTruth = HomogenNumericTable(1, 0, NumericTableIface.doNotAllocate)
    mergedData = MergedNumericTable(testData, testGroundTruth)

    # Retrieve the data from input file
    testDataSource.loadDataBlock(mergedData)

    # Create algorithm objects for AdaBoost prediction with the default method
    algorithm = prediction.Batch()

    # Pass the testing data set and trained model to the algorithm
    algorithm.input.setTable(classifier.prediction.data,  testData)
    algorithm.input.setModel(classifier.prediction.model, trainingResult.get(classifier.training.model))

    # Compute prediction results and retrieve algorithm results
    # (Result class from classifier.prediction)
    predictionResult = algorithm.compute()

def loadData(fileName):

    # Initialize FileDataSource to retrieve the input data from a .csv file
    trainDataSource = FileDataSource(
        fileName, DataSourceIface.notAllocateNumericTable, DataSourceIface.doDictionaryFromContext
    )

    # Create Numeric Tables for training data and dependent variables
    data = HomogenNumericTable(nFeatures, 0, NumericTableIface.notAllocate)
    dependentVar = HomogenNumericTable(1, 0, NumericTableIface.notAllocate)
    mergedData = MergedNumericTable(data, dependentVar)

    # Retrieve the data from input file
    trainDataSource.loadDataBlock(mergedData)

    dictionary = data.getDictionary()
    for i in range(len(categoricalFeaturesIndices)):
        dictionary[categoricalFeaturesIndices[i]].featureType = features.DAAL_CATEGORICAL

    return data, dependentVar