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

pca_cor_csr_batch.py

1 # file: pca_cor_csr_batch.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_BATCH"></a>
17 ## \example pca_cor_csr_batch.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 dataFileName = os.path.join(DAAL_PREFIX, 'batch', 'covcormoments_csr.csv')
36 
37 if __name__ == "__main__":
38 
39  # Read data from a file and create a numeric table to store input data
40  dataTable = createSparseTable(dataFileName)
41 
42  # Create an algorithm for principal component analysis using the correlation method
43  algorithm = pca.Batch(fptype=np.float64, method=pca.correlationDense)
44 
45  # Use covariance algorithm for sparse data inside the PCA algorithm
46  algorithm.parameter.covariance = covariance.Batch(fptype=np.float64, method=covariance.fastCSR)
47 
48  # Set the algorithm input data
49  algorithm.input.setDataset(pca.data, dataTable)
50  algorithm.parameter.resultsToCompute = pca.mean | pca.variance | pca.eigenvalue;
51  algorithm.parameter.isDeterministic = True;
52  # Compute results of the PCA algorithm
53  result = algorithm.compute()
54 
55  # Print the results
56  printNumericTable(result.get(pca.eigenvalues), "Eigenvalues:")
57  printNumericTable(result.get(pca.eigenvectors), "Eigenvectors:")
58  printNumericTable(result.get(pca.means), "Means:")
59  printNumericTable(result.get(pca.variances), "Variances:")

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