Python* API Reference for Intel® Data Analytics Acceleration Library 2019 Update 4

pca_svd_dense_batch.py

1 # file: pca_svd_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 
17 
18 
19 import os
20 import sys
21 
22 from daal.algorithms import pca
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 dataFileName = os.path.join(DAAL_PREFIX, 'batch', 'pca_normalized.csv')
34 nVectors = 1000
35 
36 if __name__ == "__main__":
37 
38  # Initialize FileDataSource<CSVFeatureManager> to retrieve the input data from a .csv file
39  dataSource = FileDataSource(
40  dataFileName, DataSourceIface.doAllocateNumericTable, DataSourceIface.doDictionaryFromContext
41  )
42 
43  # Retrieve the data from the input file
44  dataSource.loadDataBlock(nVectors)
45 
46  # Create an algorithm for principal component analysis using the SVD method
47  algorithm = pca.Batch(method=pca.svdDense)
48 
49  # Set the algorithm input data
50  algorithm.input.setDataset(pca.data, dataSource.getNumericTable())
51  algorithm.parameter.resultsToCompute = pca.mean | pca.variance | pca.eigenvalue;
52  algorithm.parameter.isDeterministic = True;
53 
54  # Compute results of the PCA algorithm
55  result = algorithm.compute()
56 
57  # Print the results
58  printNumericTable(result.get(pca.eigenvalues), "Eigenvalues:")
59  printNumericTable(result.get(pca.eigenvectors), "Eigenvectors:")
60  printNumericTable(result.get(pca.means), "Means:")
61  printNumericTable(result.get(pca.variances), "Variances:")

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