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

pca_cor_dense_online.py

1 # file: pca_cor_dense_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 pca
27 from daal.data_management import FileDataSource, DataSourceIface
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
33 
34 DAAL_PREFIX = os.path.join('..', 'data')
35 
36 # Input data set parameters
37 nVectorsInBlock = 250
38 dataFileName = os.path.join(DAAL_PREFIX, 'online', 'pca_normalized.csv')
39 
40 if __name__ == "__main__":
41 
42  # Initialize FileDataSource<CSVFeatureManager> to retrieve the input data from a .csv file
43  dataSource = FileDataSource(
44  dataFileName, DataSourceIface.doAllocateNumericTable,
45  DataSourceIface.doDictionaryFromContext
46  )
47 
48  # Create an algorithm for principal component analysis using the correlation method
49  algorithm = pca.Online(fptype=np.float64)
50 
51  while(dataSource.loadDataBlock(nVectorsInBlock) == nVectorsInBlock):
52  # Set the input data to the algorithm
53  algorithm.input.setDataset(pca.data, dataSource.getNumericTable())
54 
55  # Update PCA decomposition
56  algorithm.compute()
57 
58  result = algorithm.finalizeCompute()
59 
60  # Print the results
61  printNumericTable(result.get(pca.eigenvalues), "Eigenvalues:")
62  printNumericTable(result.get(pca.eigenvectors), "Eigenvectors:")

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