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
 import daal.algorithms.pca as pca
 import daal.algorithms.pca.quality_metric_set as quality_metric_set
 from daal.algorithms.pca.quality_metric import explained_variance
 from daal.data_management import (
     DataSourceIface, FileDataSource, HomogenNumericTable, MergedNumericTable,
     NumericTableIface, BlockDescriptor, readWrite
 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
 datasetFileName = os.path.join('..', 'data', 'batch', 'pca_normalized.csv')
 nVectors = 1000
 nComponents = 5
 qmsResult = None
 eigenData = None
 def trainModel():
     global eigenData
     # Initialize FileDataSource to retrieve the input data from a .csv file
     dataSource = FileDataSource(
     # Retrieve the data from the input file
     # Create an algorithm for principal component analysis using the SVD method
     algorithm = pca.Batch(method=pca.svdDense)
     # Set the algorithm input data
     algorithm.input.setDataset(, dataSource.getNumericTable())
     # Compute results of the PCA algorithm
     result = algorithm.compute()
     eigenData = result.get(pca.eigenvalues)
 def testPcaQuality():
     global qmsResult
     # Create a quality metric set object to compute quality metrics of the PCA algorithm
     qualityMetricSet = quality_metric_set.Batch(nComponents)
     explainedVariances = explained_variance.Input.downCast(qualityMetricSet.getInputDataCollection().getInput(quality_metric_set.explainedVariancesMetrics))
     explainedVariances.setInput(explained_variance.eigenvalues, eigenData)
     # Compute quality metrics
     # Retrieve the quality metrics
     qmsResult = qualityMetricSet.getResultCollection()
 def printResults():
     print ("Quality metrics for PCA")
     result = explained_variance.Result.downCast(qmsResult.getResult(quality_metric_set.explainedVariancesMetrics))
     printNumericTable(result.getResult(explained_variance.explainedVariances), "Explained variances:")
     printNumericTable(result.getResult(explained_variance.explainedVariancesRatios), "Explained variances ratios:")
     printNumericTable(result.getResult(explained_variance.noiseVariance), "Noise variance:")
 if __name__ == "__main__":
Orange (only for download buttons)