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.linear_regression import training, prediction
 from daal.data_management import (
     DataSourceIface, FileDataSource, HomogenNumericTable, MergedNumericTable, NumericTableIface
 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 printNumericTable
 DAAL_PREFIX = os.path.join('..', 'data')
 # Input data set parameters
 trainDatasetFileNames = [
     os.path.join(DAAL_PREFIX, 'distributed', 'linear_regression_train_1.csv'),
     os.path.join(DAAL_PREFIX, 'distributed', 'linear_regression_train_2.csv'),
     os.path.join(DAAL_PREFIX, 'distributed', 'linear_regression_train_3.csv'),
     os.path.join(DAAL_PREFIX, 'distributed', 'linear_regression_train_4.csv')
 testDatasetFileName = os.path.join(DAAL_PREFIX, 'distributed', 'linear_regression_test.csv')
 nBlocks = 4
 nFeatures           = 10    # Number of features in training and testing data sets
 nDependentVariables = 2     # Number of dependent variables that correspond to each observation
 trainingResult = None
 predictionResult = None
 def trainModel():
     global trainingResult
     # Create an algorithm object to build the final multiple linear regression model on the master node
     masterAlgorithm = training.Distributed(step2Master, method=training.qrDense)
     for i in range(nBlocks):
         # Initialize FileDataSource<CSVFeatureManager> to retrieve the input data from a .csv file
         trainDataSource = FileDataSource(
             trainDatasetFileNames[i], DataSourceIface.notAllocateNumericTable,
         # Create Numeric Tables for training data and dependent variables
         trainData = HomogenNumericTable(nFeatures, 0, NumericTableIface.doNotAllocate)
         trainDependentVariables = HomogenNumericTable(
             nDependentVariables, 0, NumericTableIface.doNotAllocate
         mergedData = MergedNumericTable(trainData, trainDependentVariables)
         # Retrieve the data from input file
         # Create an algorithm object to train the multiple linear regression model based on the local-node data
         localAlgorithm = training.Distributed(step1Local, method=training.qrDense)
         # Pass a training data set and dependent values to the algorithm
         localAlgorithm.input.set(, trainData)
         localAlgorithm.input.set(training.dependentVariables, trainDependentVariables)
         # Train the multiple linear regression model on the local-node data
         # Set the local multiple linear regression model as input for the master-node algorithm
         masterAlgorithm.input.add(training.partialModels, localAlgorithm.compute())
     # Merge and finalize the multiple linear regression model on the master node
     # Retrieve the algorithm results
     trainingResult = masterAlgorithm.finalizeCompute()
     printNumericTable(trainingResult.get(training.model).getBeta(), "Linear Regression coefficients:")
 def testModel():
     # Initialize FileDataSource<CSVFeatureManager> to retrieve the input data from a .csv file
     testDataSource = FileDataSource(
         testDatasetFileName, DataSourceIface.doAllocateNumericTable,
     # Create Numeric Tables for testing data and ground truth values
     testData = HomogenNumericTable(nFeatures, 0, NumericTableIface.doNotAllocate)
     testGroundTruth = HomogenNumericTable(nDependentVariables, 0, NumericTableIface.doNotAllocate)
     mergedData = MergedNumericTable(testData, testGroundTruth)
     # Retrieve the data from the input file
     # Create an algorithm object to predict values of multiple linear regression
     algorithm = prediction.Batch()
     # Pass a testing data set and the trained model to the algorithm
     algorithm.input.setTable(, testData)
     algorithm.input.setModel(prediction.model, trainingResult.get(training.model))
     # Predict values of multiple linear regression and retrieve the algorithm results
     predictionResult = algorithm.compute()
     printNumericTable(predictionResult.get(prediction.prediction), "Linear Regression prediction results: (first 10 rows):", 10)
     printNumericTable(testGroundTruth, "Ground truth (first 10 rows):", 10)
 if __name__ == "__main__":
For more complete information about compiler optimizations, see our Optimization Notice.
Select sticky button color: 
Orange (only for download buttons)