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

cov_dense_distr.py

1 # file: cov_dense_distr.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 import step1Local, step2Master
25 from daal.algorithms import covariance
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 nBlocks = 4
37 
38 datasetFileNames = [
39  os.path.join(DAAL_PREFIX, 'distributed', 'covcormoments_dense_1.csv'),
40  os.path.join(DAAL_PREFIX, 'distributed', 'covcormoments_dense_2.csv'),
41  os.path.join(DAAL_PREFIX, 'distributed', 'covcormoments_dense_3.csv'),
42  os.path.join(DAAL_PREFIX, 'distributed', 'covcormoments_dense_4.csv')
43 ]
44 
45 partialResult = [0] * nBlocks
46 result = None
47 
48 
49 def computestep1Local(block):
50  global partialResult
51 
52  # Initialize FileDataSource<CSVFeatureManager> to retrieve the input data from a .csv file
53  dataSource = FileDataSource(
54  datasetFileNames[block], DataSourceIface.doAllocateNumericTable,
55  DataSourceIface.doDictionaryFromContext
56  )
57 
58  # Retrieve the data from the input file
59  dataSource.loadDataBlock()
60 
61  # Create algorithm objects to compute a dense variance-covariance matrix in the distributed processing mode using the default method
62  algorithm = covariance.Distributed(step1Local)
63 
64  # Set input objects for the algorithm
65  algorithm.input.set(covariance.data, dataSource.getNumericTable())
66 
67  # Compute partial estimates on local nodes
68  partialResult[block] = algorithm.compute() # Get the computed partial estimates
69 
70 
71 def computeOnMasterNode():
72  global result
73 
74  # Create algorithm objects to compute a dense variance-covariance matrix in the distributed processing mode using the default method
75  algorithm = covariance.Distributed(step2Master)
76 
77  # Set input objects for the algorithm
78  for i in range(nBlocks):
79  algorithm.input.add(covariance.partialResults, partialResult[i])
80 
81  # Compute a partial estimate on the master node from the partial estimates on local nodes
82  algorithm.compute()
83 
84  # Finalize the result in the distributed processing mode
85  result = algorithm.finalizeCompute() # Get the computed dense variance-covariance matrix
86 
87 if __name__ == "__main__":
88 
89  for i in range(nBlocks):
90  computestep1Local(i)
91 
92  computeOnMasterNode()
93 
94  printNumericTable(result.get(covariance.covariance), "Covariance matrix:")
95  printNumericTable(result.get(covariance.mean), "Mean vector:")

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