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

pca_cor_dense_batch.py

1 # file: pca_cor_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 import numpy as np
24 
25 from daal.algorithms import pca
26 from daal.data_management import FileDataSource, DataSourceIface
27 
28 utils_folder = os.path.realpath(os.path.abspath(os.path.dirname(os.path.dirname(__file__))))
29 if utils_folder not in sys.path:
30  sys.path.insert(0, utils_folder)
31 from utils import printNumericTable
32 
33 DAAL_PREFIX = os.path.join('..', 'data')
34 
35 # Input data set parameters
36 dataFileName = os.path.join(DAAL_PREFIX, 'batch', 'pca_normalized.csv')
37 nVectors = 1000
38 
39 if __name__ == "__main__":
40  # Initialize FileDataSource<CSVFeatureManager> to retrieve the input data from a .csv file
41 
42  dataSource = FileDataSource(
43  dataFileName, DataSourceIface.doAllocateNumericTable, DataSourceIface.doDictionaryFromContext
44  )
45 
46  # Retrieve the data from the input file
47  dataSource.loadDataBlock(nVectors)
48 
49  # Create an algorithm for principal component analysis using the correlation method
50  algorithm = pca.Batch(fptype=np.float64)
51 
52  # Set the algorithm input data
53  algorithm.input.setDataset(pca.data, dataSource.getNumericTable())
54  algorithm.parameter.resultsToCompute = pca.mean | pca.variance | pca.eigenvalue;
55  algorithm.parameter.isDeterministic = True;
56 
57  # Compute results of the PCA algorithm
58  result = algorithm.compute()
59 
60  # Print the results
61  printNumericTable(result.get(pca.eigenvalues), "Eigenvalues:")
62  printNumericTable(result.get(pca.eigenvectors), "Eigenvectors:")
63  printNumericTable(result.get(pca.means), "Means:")
64  printNumericTable(result.get(pca.variances), "Variances:")

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