Deprecation Notice: With the introduction of daal4py, a package that supersedes PyDAAL, Intel is deprecating PyDAAL and will discontinue support starting with Intel® DAAL 2021 and Intel® Distribution for Python 2021. Until then Intel will continue to provide compatible pyDAAL pip and conda packages for newer releases of Intel DAAL and make it available in open source. However, Intel will not add the new features of Intel DAAL to pyDAAL. Intel recommends developers switch to and use daal4py.

Note: To find daal4py examples, refer to daal4py documentation or browse github repository.

 # file:
 # Copyright 2014-2019 Intel Corporation.
 # This software and the related documents are Intel copyrighted  materials,  and
 # your use of  them is  governed by the  express license  under which  they were
 # provided to you (License).  Unless the License provides otherwise, you may not
 # use, modify, copy, publish, distribute,  disclose or transmit this software or
 # the related documents without Intel's prior written permission.
 # This software and the related documents  are provided as  is,  with no express
 # or implied  warranties,  other  than those  that are  expressly stated  in the
 # License.
 ## \example
 import os
 import sys
 from daal import step1Local, step2Master
 from daal.algorithms import classifier
 from daal.algorithms.multinomial_naive_bayes import training, prediction
 from daal.data_management import FileDataSource, DataSourceIface
 utils_folder = os.path.realpath(os.path.abspath(os.path.dirname(os.path.dirname(__file__))))
 if utils_folder not in sys.path:
     sys.path.insert(0, utils_folder)
 from utils import printNumericTables, createSparseTable
 DAAL_PREFIX = os.path.join('..', 'data')
 # Input data set parameters
 trainDatasetFileNames = [
     os.path.join(DAAL_PREFIX, 'batch', 'naivebayes_train_csr.csv'),
     os.path.join(DAAL_PREFIX, 'batch', 'naivebayes_train_csr.csv'),
     os.path.join(DAAL_PREFIX, 'batch', 'naivebayes_train_csr.csv'),
     os.path.join(DAAL_PREFIX, 'batch', 'naivebayes_train_csr.csv')
 trainGroundTruthFileNames = [
     os.path.join(DAAL_PREFIX, 'batch', 'naivebayes_train_labels.csv'),
     os.path.join(DAAL_PREFIX, 'batch', 'naivebayes_train_labels.csv'),
     os.path.join(DAAL_PREFIX, 'batch', 'naivebayes_train_labels.csv'),
     os.path.join(DAAL_PREFIX, 'batch', 'naivebayes_train_labels.csv')
 testDatasetFileName = os.path.join(DAAL_PREFIX, 'batch', 'naivebayes_test_csr.csv')
 testGroundTruthFileName = os.path.join(DAAL_PREFIX, 'batch', 'naivebayes_test_labels.csv')
 nClasses = 20
 nBlocks = 4
 nTrainVectorsInBlock = 8000
 nTestObservations = 2000
 trainingResult = None
 predictionResult = None
 trainData = [0] * nBlocks
 testData = None
 def trainModel():
     global trainData, trainingResult
     masterAlgorithm = training.Distributed(step2Master, nClasses, method=training.fastCSR)
     for i in range(nBlocks):
         # Read trainDatasetFileNames and create a numeric table to store the input data
         trainData[i] = createSparseTable(trainDatasetFileNames[i])
         # Initialize FileDataSource<CSVFeatureManager> to retrieve the input data from a .csv file
         trainLabelsSource = FileDataSource(
             trainGroundTruthFileNames[i], DataSourceIface.doAllocateNumericTable,
         # Retrieve the data from an input file
         # Create an algorithm object to train the Naive Bayes model on the local-node data
         localAlgorithm = training.Distributed(step1Local, nClasses, method=training.fastCSR)
         # Pass a training data set and dependent values to the algorithm
         localAlgorithm.input.set(,   trainData[i])
         localAlgorithm.input.set(, trainLabelsSource.getNumericTable())
         # Build the Naive Bayes model on the local node
         # Set the local Naive Bayes model as input for the master-node algorithm
         masterAlgorithm.input.add(training.partialModels, localAlgorithm.compute())
     # Merge and finalize the Naive Bayes model on the master node
     trainingResult = masterAlgorithm.finalizeCompute()  # Retrieve the algorithm results
 def testModel():
     global predictionResult, testData
     # Read testDatasetFileName and create a numeric table to store the input data
     testData = createSparseTable(testDatasetFileName)
     # Create an algorithm object to predict Naive Bayes values
     algorithm = prediction.Batch(nClasses, method=prediction.fastCSR)
     # Pass a testing data set and the trained model to the algorithm
     algorithm.input.setTable(,  testData)
     algorithm.input.setModel(classifier.prediction.model, trainingResult.get(
     # Predict Naive Bayes values (Result class from classifier.prediction)
     predictionResult = algorithm.compute()  # Retrieve the algorithm results
 def printResults():
     testGroundTruth = FileDataSource(
         testGroundTruthFileName, DataSourceIface.doAllocateNumericTable,
         "Ground truth", "Classification results",
         "NaiveBayes classification results (first 20 observations):", 20, 15, flt64=False
 if __name__ == "__main__":
For more complete information about compiler optimizations, see our Optimization Notice.
Select sticky button color: 
Orange (only for download buttons)