Python* API Reference for Intel® Data Analytics Acceleration Library 2020 Update 1

pca_svd_dense_distr.py

1 # file: pca_svd_dense_distr.py
2 #===============================================================================
3 # Copyright 2014-2020 Intel Corporation
4 #
5 # Licensed under the Apache License, Version 2.0 (the "License");
6 # you may not use this file except in compliance with the License.
7 # You may obtain a copy of the License at
8 #
9 # http://www.apache.org/licenses/LICENSE-2.0
10 #
11 # Unless required by applicable law or agreed to in writing, software
12 # distributed under the License is distributed on an "AS IS" BASIS,
13 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14 # See the License for the specific language governing permissions and
15 # limitations under the License.
16 #===============================================================================
17 
18 
19 
20 
21 import os
22 import sys
23 
24 import daal
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 
39 dataFileNames = [
40  os.path.join(DAAL_PREFIX, 'distributed', 'pca_normalized_1.csv'),
41  os.path.join(DAAL_PREFIX, 'distributed', 'pca_normalized_2.csv'),
42  os.path.join(DAAL_PREFIX, 'distributed', 'pca_normalized_3.csv'),
43  os.path.join(DAAL_PREFIX, 'distributed', 'pca_normalized_4.csv')
44 ]
45 
46 if __name__ == "__main__":
47 
48  # Create an algorithm for principal component analysis using the SVD method on the master node
49  masterAlgorithm = pca.Distributed(step=daal.step2Master, method=pca.svdDense)
50 
51  for i in range(nBlocks):
52  # Initialize FileDataSource<CSVFeatureManager> to retrieve the input data from a .csv file
53  dataSource = FileDataSource(
54  dataFileNames[i], DataSourceIface.doAllocateNumericTable,
55  DataSourceIface.doDictionaryFromContext
56  )
57 
58  # Retrieve the input data
59  dataSource.loadDataBlock(nVectorsInBlock)
60 
61  # Create an algorithm for principal component analysis using the SVD method on the local node
62  localAlgorithm = pca.Distributed(step=daal.step1Local, method=pca.svdDense)
63 
64  # Set the input data to the algorithm
65  localAlgorithm.input.setDataset(pca.data, dataSource.getNumericTable())
66 
67  # Compute PCA decomposition
68  # Set local partial results as input for the master-node algorithm
69  masterAlgorithm.input.add(pca.partialResults, localAlgorithm.compute())
70 
71  # Merge and finalize PCA decomposition on the master node
72  masterAlgorithm.compute()
73  result = masterAlgorithm.finalizeCompute()
74 
75  # Print the results
76  printNumericTable(result.get(pca.eigenvalues), "Eigenvalues:")
77  printNumericTable(result.get(pca.eigenvectors), "Eigenvectors:")

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