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

pca_svd_dense_batch.py

1 # file: pca_svd_dense_batch.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 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 dataFileName = os.path.join(DAAL_PREFIX, 'batch', 'pca_normalized.csv')
36 nVectors = 1000
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, DataSourceIface.doDictionaryFromContext
43  )
44 
45  # Retrieve the data from the input file
46  dataSource.loadDataBlock(nVectors)
47 
48  # Create an algorithm for principal component analysis using the SVD method
49  algorithm = pca.Batch(method=pca.svdDense)
50 
51  # Set the algorithm input data
52  algorithm.input.setDataset(pca.data, dataSource.getNumericTable())
53  algorithm.parameter.resultsToCompute = pca.mean | pca.variance | pca.eigenvalue;
54  algorithm.parameter.isDeterministic = True;
55 
56  # Compute results of the PCA algorithm
57  result = algorithm.compute()
58 
59  # Print the results
60  printNumericTable(result.get(pca.eigenvalues), "Eigenvalues:")
61  printNumericTable(result.get(pca.eigenvectors), "Eigenvectors:")
62  printNumericTable(result.get(pca.means), "Means:")
63  printNumericTable(result.get(pca.variances), "Variances:")

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