Python* API Reference for Intel® Data Analytics Acceleration Library 2018 Update 3

pca_cor_csr_online.py

1 # file: pca_cor_csr_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_CSR_ONLINE"></a>
17 ## \example pca_cor_csr_online.py
18 
19 import os
20 import sys
21 
22 import numpy as np
23 
24 from daal.algorithms import covariance
25 from daal.algorithms import pca
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, createSparseTable
31 
32 DAAL_PREFIX = os.path.join('..', 'data')
33 
34 # Input data set parameters
35 nBlocks = 4
36 datasetFileNames = [
37  os.path.join(DAAL_PREFIX, 'distributed', 'covcormoments_csr_1.csv'),
38  os.path.join(DAAL_PREFIX, 'distributed', 'covcormoments_csr_2.csv'),
39  os.path.join(DAAL_PREFIX, 'distributed', 'covcormoments_csr_3.csv'),
40  os.path.join(DAAL_PREFIX, 'distributed', 'covcormoments_csr_4.csv')
41 ]
42 
43 if __name__ == "__main__":
44 
45  # Create an algorithm for principal component analysis using the correlation method
46  algorithm = pca.Online(fptype=np.float64)
47 
48  # Use covariance algorithm for sparse data inside the PCA algorithm
49  algorithm.parameter.covariance = covariance.Online(fptype=np.float64,method=covariance.fastCSR)
50 
51  for i in range(nBlocks):
52  # Read data from a file and create a numeric table to store input data
53  dataTable = createSparseTable(datasetFileNames[i])
54 
55  # Set input objects for the algorithm
56  algorithm.input.setDataset(pca.data, dataTable)
57 
58  # Update PCA decomposition
59  algorithm.compute()
60 
61  # Finalize computations
62  result = algorithm.finalizeCompute()
63 
64  printNumericTable(result.get(pca.eigenvalues), "Eigenvalues:")
65  printNumericTable(result.get(pca.eigenvectors), "Eigenvectors:")

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