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

pca_cor_dense_batch.py

1 # file: pca_cor_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 import numpy as np
22 
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 dataFileName = os.path.join(DAAL_PREFIX, 'batch', 'pca_normalized.csv')
35 nVectors = 1000
36 
37 if __name__ == "__main__":
38  # Initialize FileDataSource<CSVFeatureManager> to retrieve the input data from a .csv file
39 
40  dataSource = FileDataSource(
41  dataFileName, DataSourceIface.doAllocateNumericTable, DataSourceIface.doDictionaryFromContext
42  )
43 
44  # Retrieve the data from the input file
45  dataSource.loadDataBlock(nVectors)
46 
47  # Create an algorithm for principal component analysis using the correlation method
48  algorithm = pca.Batch(fptype=np.float64)
49 
50  # Set the algorithm input data
51  algorithm.input.setDataset(pca.data, dataSource.getNumericTable())
52  algorithm.parameter.resultsToCompute = pca.mean | pca.variance | pca.eigenvalue;
53  algorithm.parameter.isDeterministic = True;
54 
55  # Compute results of the PCA algorithm
56  result = algorithm.compute()
57 
58  # Print the results
59  printNumericTable(result.get(pca.eigenvalues), "Eigenvalues:")
60  printNumericTable(result.get(pca.eigenvectors), "Eigenvectors:")
61  printNumericTable(result.get(pca.means), "Means:")
62  printNumericTable(result.get(pca.variances), "Variances:")

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