Python* API Reference for Intel® Data Analytics Acceleration Library 2019 Update 5

cor_csr_distr.py

Deprecation Notice: With the introduction of daal4py, a package that supersedes PyDAAL, Intel is deprecating PyDAAL and will discontinue support starting with Intel® DAAL 2021 and Intel® Distribution for Python 2021. Until then Intel will continue to provide compatible pyDAAL pip and conda packages for newer releases of Intel DAAL and make it available in open source. However, Intel will not add the new features of Intel DAAL to pyDAAL. Intel recommends developers switch to and use daal4py.

Note: To find daal4py examples, refer to daal4py documentation or browse github repository.

1 # file: cor_csr_distr.py
2 #===============================================================================
3 # Copyright 2014-2019 Intel Corporation.
4 #
5 # This software and the related documents are Intel copyrighted materials, and
6 # your use of them is governed by the express license under which they were
7 # provided to you (License). Unless the License provides otherwise, you may not
8 # use, modify, copy, publish, distribute, disclose or transmit this software or
9 # the related documents without Intel's prior written permission.
10 #
11 # This software and the related documents are provided as is, with no express
12 # or implied warranties, other than those that are expressly stated in the
13 # License.
14 #===============================================================================
15 
16 ## <a name="DAAL-EXAMPLE-PY-CORRELATION_CSR_DISTRIBUTED"></a>
17 ## \example cor_csr_distr.py
18 
19 import os
20 import sys
21 
22 from daal import step1Local, step2Master
23 from daal.algorithms import covariance
24 
25 utils_folder = os.path.realpath(os.path.abspath(os.path.dirname(os.path.dirname(__file__))))
26 if utils_folder not in sys.path:
27  sys.path.insert(0, utils_folder)
28 from utils import printNumericTable, createSparseTable
29 
30 DAAL_PREFIX = os.path.join('..', 'data')
31 
32 # Input data set parameters
33 nBlocks = 4
34 
35 datasetFileNames = [
36  os.path.join(DAAL_PREFIX, 'distributed', 'covcormoments_csr_1.csv'),
37  os.path.join(DAAL_PREFIX, 'distributed', 'covcormoments_csr_2.csv'),
38  os.path.join(DAAL_PREFIX, 'distributed', 'covcormoments_csr_3.csv'),
39  os.path.join(DAAL_PREFIX, 'distributed', 'covcormoments_csr_4.csv')
40 ]
41 
42 partialResult = [0] * nBlocks
43 result = None
44 
45 
46 def computestep1Local(block):
47  global partialResult
48 
49  dataTable = createSparseTable(datasetFileNames[block])
50 
51  # Create algorithm objects to compute a correlation matrix in the distributed processing mode using the default method
52  algorithm = covariance.Distributed(step1Local, method=covariance.fastCSR)
53 
54  # Set input objects for the algorithm
55  algorithm.input.set(covariance.data, dataTable)
56 
57  # Compute partial estimates on local nodes
58  partialResult[block] = algorithm.compute() # Get the computed partial estimates
59 
60 
61 def computeOnMasterNode():
62  global result
63 
64  # Create algorithm objects to compute a correlation matrix in the distributed processing mode using the default method
65  algorithm = covariance.Distributed(step2Master, method=covariance.fastCSR)
66 
67  # Set input objects for the algorithm
68  for i in range(nBlocks):
69  algorithm.input.add(covariance.partialResults, partialResult[i])
70 
71  # Set the parameter to choose the type of the output matrix
72  algorithm.parameter.outputMatrixType = covariance.correlationMatrix
73 
74  # Compute a partial estimate on the master node from the partial estimates on local nodes
75  algorithm.compute()
76 
77  # Finalize the result in the distributed processing mode and get the computed correlation matrix
78  result = algorithm.finalizeCompute()
79 
80 if __name__ == "__main__":
81 
82  for i in range(nBlocks):
83  computestep1Local(i)
84 
85  computeOnMasterNode()
86 
87  printNumericTable(result.get(covariance.correlation), "Correlation matrix (upper left square 10*10) :", 10, 10)
88  printNumericTable(result.get(covariance.mean), "Mean vector:", 1, 10)

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