Python* API Reference for Intel® Data Analytics Acceleration Library 2019 Update 4

kmeans_dense_batch.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: kmeans_dense_batch.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-KMEANS_DENSE_BATCH"></a>
17 ## \example kmeans_dense_batch.py
18 
19 import os
20 import sys
21 
22 import daal.algorithms.kmeans.init
23 from daal.algorithms import kmeans
24 from daal.data_management import FileDataSource, DataSourceIface
25 
26 utils_folder = os.path.realpath(os.path.abspath(os.path.dirname(os.path.dirname(__file__))))
27 if utils_folder not in sys.path:
28  sys.path.insert(0, utils_folder)
29 from utils import printNumericTable
30 
31 DAAL_PREFIX = os.path.join('..', 'data')
32 
33 # Input data set parameters
34 datasetFileName = os.path.join(DAAL_PREFIX, 'batch', 'kmeans_dense.csv')
35 
36 # K-Means algorithm parameters
37 nClusters = 20
38 nIterations = 5
39 
40 if __name__ == "__main__":
41 
42  # Initialize FileDataSource to retrieve the input data from a .csv file
43  dataSource = FileDataSource(
44  datasetFileName,
45  DataSourceIface.doAllocateNumericTable,
46  DataSourceIface.doDictionaryFromContext
47  )
48 
49  # Retrieve the data from the input file
50  dataSource.loadDataBlock()
51 
52  # Get initial clusters for the K-Means algorithm
53  initAlg = kmeans.init.Batch(nClusters, method=kmeans.init.randomDense)
54 
55  initAlg.input.set(kmeans.init.data, dataSource.getNumericTable())
56 
57  res = initAlg.compute()
58  centroidsResult = res.get(kmeans.init.centroids)
59 
60  # Create an algorithm object for the K-Means algorithm
61  algorithm = kmeans.Batch(nClusters, nIterations, method=kmeans.lloydDense)
62 
63  algorithm.input.set(kmeans.data, dataSource.getNumericTable())
64  algorithm.input.set(kmeans.inputCentroids, centroidsResult)
65 
66  res = algorithm.compute()
67 
68  # Print the clusterization results
69  printNumericTable(res.get(kmeans.assignments), "First 10 cluster assignments:", 10)
70  printNumericTable(res.get(kmeans.centroids), "First 10 dimensions of centroids:", 20, 10)
71  printNumericTable(res.get(kmeans.objectiveFunction), "Objective function value:")

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