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 daal.algorithms.kmeans as kmeans
 import daal.algorithms.kmeans.init as init
 from daal.data_management import FileDataSource, DataSourceIface
 from import Environment
 # Input data set parameters
 datasetFileName = os.path.join('..', 'data', 'batch', 'kmeans_dense.csv')
 # K-Means algorithm parameters
 nClusters = 20
 nIterations = 5
 nThreads = 2
 nThreadsInit = None
 nThreadsNew = None
 if __name__ == "__main__":
     # Get the number of threads that is used by the library by default
     nThreadsInit = Environment.getInstance().getNumberOfThreads()
     # Set the maximum number of threads to be used by the library
     # Get the number of threads that is used by the library after changing
     nThreadsNew = Environment.getInstance().getNumberOfThreads()
     # Initialize FileDataSource to retrieve the input data from a .csv file
     dataSource = FileDataSource(
         datasetFileName, DataSourceIface.doAllocateNumericTable,
     # Retrieve the data from the input file
     # Get initial clusters for the K-Means algorithm
     initAlg = init.Batch(nClusters)
     initAlg.input.set(, dataSource.getNumericTable())
     res = initAlg.compute()
     centroids = res.get(init.centroids)
     # Create an algorithm object for the K-Means algorithm
     algorithm = kmeans.Batch(nClusters, nIterations)
     algorithm.input.set(, dataSource.getNumericTable())
     algorithm.input.set(kmeans.inputCentroids, centroids)
     # Run computations
     unused_result = algorithm.compute()
     print("Initial number of threads:        {}".format(nThreadsInit))
     print("Number of threads to set:         {}".format(nThreads))
     print("Number of threads after setting:  {}".format(nThreadsNew))
For more complete information about compiler optimizations, see our Optimization Notice.
Select sticky button color: 
Orange (only for download buttons)