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

pca_cor_dense_online.py

1 # file: pca_cor_dense_online.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_ONLINE"></a>
17 ## \example pca_cor_dense_online.py
18 
19 import os
20 import sys
21 
22 import numpy as np
23 
24 from daal.algorithms import pca
25 from daal.data_management import FileDataSource, DataSourceIface
26 
27 utils_folder = os.path.realpath(os.path.abspath(os.path.dirname(os.path.dirname(__file__))))
28 if utils_folder not in sys.path:
29  sys.path.insert(0, utils_folder)
30 from utils import printNumericTable
31 
32 DAAL_PREFIX = os.path.join('..', 'data')
33 
34 # Input data set parameters
35 nVectorsInBlock = 250
36 dataFileName = os.path.join(DAAL_PREFIX, 'online', 'pca_normalized.csv')
37 
38 if __name__ == "__main__":
39 
40  # Initialize FileDataSource<CSVFeatureManager> to retrieve the input data from a .csv file
41  dataSource = FileDataSource(
42  dataFileName, DataSourceIface.doAllocateNumericTable,
43  DataSourceIface.doDictionaryFromContext
44  )
45 
46  # Create an algorithm for principal component analysis using the correlation method
47  algorithm = pca.Online(fptype=np.float64)
48 
49  while(dataSource.loadDataBlock(nVectorsInBlock) == nVectorsInBlock):
50  # Set the input data to the algorithm
51  algorithm.input.setDataset(pca.data, dataSource.getNumericTable())
52 
53  # Update PCA decomposition
54  algorithm.compute()
55 
56  result = algorithm.finalizeCompute()
57 
58  # Print the results
59  printNumericTable(result.get(pca.eigenvalues), "Eigenvalues:")
60  printNumericTable(result.get(pca.eigenvectors), "Eigenvectors:")

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