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

pca_svd_dense_distr.py

1 # file: pca_svd_dense_distr.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 
17 
18 
19 import os
20 import sys
21 
22 import daal
23 from daal.algorithms import pca
24 from daal.data_management import FileDataSource, DataSourceIface
25 
26 utils_folder = os.path.realpath(os.path.abspath(os.path.dirname(os.path.dirname(__file__))))
27 if utils_folder not in sys.path:
28  sys.path.insert(0, utils_folder)
29 from utils import printNumericTable
30 
31 DAAL_PREFIX = os.path.join('..', 'data')
32 
33 # Input data set parameters
34 nBlocks = 4
35 nVectorsInBlock = 250
36 
37 dataFileNames = [
38  os.path.join(DAAL_PREFIX, 'distributed', 'pca_normalized_1.csv'),
39  os.path.join(DAAL_PREFIX, 'distributed', 'pca_normalized_2.csv'),
40  os.path.join(DAAL_PREFIX, 'distributed', 'pca_normalized_3.csv'),
41  os.path.join(DAAL_PREFIX, 'distributed', 'pca_normalized_4.csv')
42 ]
43 
44 if __name__ == "__main__":
45 
46  # Create an algorithm for principal component analysis using the SVD method on the master node
47  masterAlgorithm = pca.Distributed(step=daal.step2Master, method=pca.svdDense)
48 
49  for i in range(nBlocks):
50  # Initialize FileDataSource<CSVFeatureManager> to retrieve the input data from a .csv file
51  dataSource = FileDataSource(
52  dataFileNames[i], DataSourceIface.doAllocateNumericTable,
53  DataSourceIface.doDictionaryFromContext
54  )
55 
56  # Retrieve the input data
57  dataSource.loadDataBlock(nVectorsInBlock)
58 
59  # Create an algorithm for principal component analysis using the SVD method on the local node
60  localAlgorithm = pca.Distributed(step=daal.step1Local, method=pca.svdDense)
61 
62  # Set the input data to the algorithm
63  localAlgorithm.input.setDataset(pca.data, dataSource.getNumericTable())
64 
65  # Compute PCA decomposition
66  # Set local partial results as input for the master-node algorithm
67  masterAlgorithm.input.add(pca.partialResults, localAlgorithm.compute())
68 
69  # Merge and finalize PCA decomposition on the master node
70  masterAlgorithm.compute()
71  result = masterAlgorithm.finalizeCompute()
72 
73  # Print the results
74  printNumericTable(result.get(pca.eigenvalues), "Eigenvalues:")
75  printNumericTable(result.get(pca.eigenvectors), "Eigenvectors:")

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