Python* API Reference for Intel® Data Analytics Acceleration Library 2018 Update 3

kmeans_csr_batch.py

1 # file: kmeans_csr_batch.py
2 #===============================================================================
3 # Copyright 2014-2018 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_CSR_BATCH"></a>
17 ## \example kmeans_csr_batch.py
18 
19 import os
20 import sys
21 
22 import daal.algorithms.kmeans.init
23 from daal.algorithms import kmeans
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 datasetFileName = os.path.join(DAAL_PREFIX, 'batch', 'kmeans_csr.csv')
34 
35 # K-Means algorithm parameters
36 nClusters = 20
37 nIterations = 5
38 
39 if __name__ == "__main__":
40 
41  # Retrieve the data from the input file
42  dataTable = createSparseTable(datasetFileName)
43 
44  # Get initial clusters for the K-Means algorithm
45  init = kmeans.init.Batch(nClusters, method=kmeans.init.randomDense)
46 
47  init.input.set(kmeans.init.data, dataTable)
48  res = init.compute()
49 
50  centroids = res.get(kmeans.init.centroids)
51 
52  # Create an algorithm object for the K-Means algorithm
53  algorithm = kmeans.Batch(nClusters, nIterations, method=kmeans.lloydCSR)
54 
55  algorithm.input.set(kmeans.data, dataTable)
56  algorithm.input.set(kmeans.inputCentroids, centroids)
57 
58  res = algorithm.compute()
59 
60  # Print the clusterization results
61  printNumericTable(res.get(kmeans.assignments), "First 10 cluster assignments:", 10)
62  printNumericTable(res.get(kmeans.centroids), "First 10 dimensions of centroids:", 20, 10)
63  printNumericTable(res.get(kmeans.objectiveFunction), "Objective function value:")

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