Python* API Reference for Intel® Data Analytics Acceleration Library 2019 Update 5

em_gmm_dense_batch.py

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.

1 # file: em_gmm_dense_batch.py
2 #===============================================================================
3 # Copyright 2014-2019 Intel Corporation.
4 #
5 # This software and the related documents are Intel copyrighted materials, and
6 # your use of them is governed by the express license under which they were
7 # provided to you (License). Unless the License provides otherwise, you may not
8 # use, modify, copy, publish, distribute, disclose or transmit this software or
9 # the related documents without Intel's prior written permission.
10 #
11 # This software and the related documents are provided as is, with no express
12 # or implied warranties, other than those that are expressly stated in the
13 # License.
14 #===============================================================================
15 
16 ## <a name="DAAL-EXAMPLE-PY-EM_GMM_BATCH"></a>
17 ## \example em_gmm_dense_batch.py
18 
19 import os
20 import sys
21 
22 from daal.algorithms import em_gmm
23 from daal.data_management import FileDataSource, DataSourceIface
24 
25 utils_folder = os.path.realpath(os.path.abspath(os.path.dirname(os.path.dirname(__file__))))
26 if utils_folder not in sys.path:
27  sys.path.insert(0, utils_folder)
28 from utils import printNumericTable
29 
30 DAAL_PREFIX = os.path.join('..', 'data')
31 
32 # Input data set parameters
33 datasetFileName = os.path.join(DAAL_PREFIX, 'batch', 'em_gmm.csv')
34 nComponents = 2
35 
36 if __name__ == "__main__":
37 
38  # Initialize FileDataSource<CSVFeatureManager> to retrieve the input data from a .csv file
39  dataSource = FileDataSource(
40  datasetFileName,
41  DataSourceIface.doAllocateNumericTable,
42  DataSourceIface.doDictionaryFromContext
43  )
44  nFeatures = dataSource.getNumberOfColumns()
45 
46  # Retrieve the data from the input file
47  dataSource.loadDataBlock()
48 
49  # Create algorithm objects to initialize the EM algorithm for the GMM
50  # computing the number of components using the default method
51  initAlgorithm = em_gmm.init.Batch(nComponents)
52 
53  # Set an input data table for the initialization algorithm
54  initAlgorithm.input.set(em_gmm.init.data, dataSource.getNumericTable())
55 
56  # Compute initial values for the EM algorithm for the GMM with the default parameters
57  resultInit = initAlgorithm.compute()
58 
59  # Create algorithm objects for the EM algorithm for the GMM computing the number of components using the default method
60  algorithm = em_gmm.Batch(nComponents)
61 
62  # Set an input data table for the algorithm
63  algorithm.input.setTable(em_gmm.data, dataSource.getNumericTable())
64  algorithm.input.setValues(em_gmm.inputValues, resultInit)
65 
66  # Compute the results of the EM algorithm for the GMM with the default parameters
67  result = algorithm.compute()
68 
69  # Print the results
70  printNumericTable(result.getResult(em_gmm.weights), "Weights")
71  printNumericTable(result.getResult(em_gmm.means), "Means")
72  for i in range(nComponents):
73  printNumericTable(result.getCovariances(em_gmm.covariances, i), "Covariance")

For more complete information about compiler optimizations, see our Optimization Notice.