Python* API Reference for Intel® Data Analytics Acceleration Library 2020 Update 1

pca_cor_csr_online.py

1 # file: pca_cor_csr_online.py
2 #===============================================================================
3 # Copyright 2014-2020 Intel Corporation
4 #
5 # Licensed under the Apache License, Version 2.0 (the "License");
6 # you may not use this file except in compliance with the License.
7 # You may obtain a copy of the License at
8 #
9 # http://www.apache.org/licenses/LICENSE-2.0
10 #
11 # Unless required by applicable law or agreed to in writing, software
12 # distributed under the License is distributed on an "AS IS" BASIS,
13 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14 # See the License for the specific language governing permissions and
15 # limitations under the License.
16 #===============================================================================
17 
18 
19 
20 
21 import os
22 import sys
23 
24 import numpy as np
25 
26 from daal.algorithms import covariance
27 from daal.algorithms import pca
28 
29 utils_folder = os.path.realpath(os.path.abspath(os.path.dirname(os.path.dirname(__file__))))
30 if utils_folder not in sys.path:
31  sys.path.insert(0, utils_folder)
32 from utils import printNumericTable, createSparseTable
33 
34 DAAL_PREFIX = os.path.join('..', 'data')
35 
36 # Input data set parameters
37 nBlocks = 4
38 datasetFileNames = [
39  os.path.join(DAAL_PREFIX, 'distributed', 'covcormoments_csr_1.csv'),
40  os.path.join(DAAL_PREFIX, 'distributed', 'covcormoments_csr_2.csv'),
41  os.path.join(DAAL_PREFIX, 'distributed', 'covcormoments_csr_3.csv'),
42  os.path.join(DAAL_PREFIX, 'distributed', 'covcormoments_csr_4.csv')
43 ]
44 
45 if __name__ == "__main__":
46 
47  # Create an algorithm for principal component analysis using the correlation method
48  algorithm = pca.Online(fptype=np.float64)
49 
50  # Use covariance algorithm for sparse data inside the PCA algorithm
51  algorithm.parameter.covariance = covariance.Online(fptype=np.float64,method=covariance.fastCSR)
52 
53  for i in range(nBlocks):
54  # Read data from a file and create a numeric table to store input data
55  dataTable = createSparseTable(datasetFileNames[i])
56 
57  # Set input objects for the algorithm
58  algorithm.input.setDataset(pca.data, dataTable)
59 
60  # Update PCA decomposition
61  algorithm.compute()
62 
63  # Finalize computations
64  result = algorithm.finalizeCompute()
65 
66  printNumericTable(result.get(pca.eigenvalues), "Eigenvalues:")
67  printNumericTable(result.get(pca.eigenvectors), "Eigenvectors:")

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