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

kmeans_csr_batch_assign.py

1 # file: kmeans_csr_batch_assign.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 
17 
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 
38 if __name__ == "__main__":
39 
40  # Retrieve the data from the input file
41  dataTable = createSparseTable(datasetFileName)
42 
43  # Get initial clusters for the K-Means algorithm
44  init = kmeans.init.Batch(nClusters, method=kmeans.init.randomDense)
45 
46  init.input.set(kmeans.init.data, dataTable)
47  res = init.compute()
48 
49  centroids = res.get(kmeans.init.centroids)
50 
51  # Create an algorithm object for the K-Means algorithm
52  algorithm = kmeans.Batch(nClusters, 0, method=kmeans.lloydCSR)
53 
54  algorithm.input.set(kmeans.data, dataTable)
55  algorithm.input.set(kmeans.inputCentroids, centroids)
56 
57  res = algorithm.compute()
58 
59  # Print the clusterization results
60  printNumericTable(res.get(kmeans.assignments), "First 10 cluster assignments:", 10)

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