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

pca_cor_dense_distr.py

1 # file: pca_cor_dense_distr.py
2 #===============================================================================
3 # Copyright 2014-2018 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-PCA_CORRELATION_DENSE_DISTRIBUTED"></a>
17 ## \example pca_cor_dense_distr.py
18 
19 import os
20 import sys
21 
22 import numpy as np
23 
24 from daal import step1Local, step2Master
25 from daal.algorithms import pca
26 from daal.data_management import FileDataSource, DataSourceIface
27 
28 utils_folder = os.path.realpath(os.path.abspath(os.path.dirname(os.path.dirname(__file__))))
29 if utils_folder not in sys.path:
30  sys.path.insert(0, utils_folder)
31 from utils import printNumericTable
32 
33 DAAL_PREFIX = os.path.join('..', 'data')
34 
35 # Input data set parameters
36 nBlocks = 4
37 nVectorsInBlock = 250
38 nFeatures = None
39 
40 dataFileNames = [
41  os.path.join(DAAL_PREFIX, 'distributed', 'pca_normalized_1.csv'),
42  os.path.join(DAAL_PREFIX, 'distributed', 'pca_normalized_2.csv'),
43  os.path.join(DAAL_PREFIX, 'distributed', 'pca_normalized_3.csv'),
44  os.path.join(DAAL_PREFIX, 'distributed', 'pca_normalized_4.csv')
45 ]
46 
47 if __name__ == "__main__":
48 
49  # Create an algorithm for principal component analysis using the correlation method on the master node
50  masterAlgorithm = pca.Distributed(step2Master,fptype=np.float64)
51 
52  for i in range(nBlocks):
53  # Initialize FileDataSource<CSVFeatureManager> to retrieve the input data from a .csv file
54  dataSource = FileDataSource(
55  dataFileNames[i], DataSourceIface.doAllocateNumericTable,
56  DataSourceIface.doDictionaryFromContext
57  )
58 
59  # Retrieve the input data
60  dataSource.loadDataBlock(nVectorsInBlock)
61 
62  # Create an algorithm for principal component analysis using the correlation method on the local node
63  localAlgorithm = pca.Distributed(step1Local,fptype=np.float64)
64 
65  # Set the input data to the algorithm
66  localAlgorithm.input.setDataset(pca.data, dataSource.getNumericTable())
67 
68  # Compute PCA decomposition
69  # Set local partial results as input for the master-node algorithm
70  masterAlgorithm.input.add(pca.partialResults, localAlgorithm.compute())
71 
72  # Merge and finalize PCA decomposition on the master node
73  masterAlgorithm.compute()
74  result = masterAlgorithm.finalizeCompute()
75 
76  # Print the results
77  printNumericTable(result.get(pca.eigenvalues), "Eigenvalues:")
78  printNumericTable(result.get(pca.eigenvectors), "Eigenvectors:")

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