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

kmeans_csr_batch.py

1 # file: kmeans_csr_batch.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 import daal.algorithms.kmeans.init
25 from daal.algorithms import kmeans
26 
27 utils_folder = os.path.realpath(os.path.abspath(os.path.dirname(os.path.dirname(__file__))))
28 if utils_folder not in sys.path:
29  sys.path.insert(0, utils_folder)
30 from utils import printNumericTable, createSparseTable
31 
32 DAAL_PREFIX = os.path.join('..', 'data')
33 
34 # Input data set parameters
35 datasetFileName = os.path.join(DAAL_PREFIX, 'batch', 'kmeans_csr.csv')
36 
37 # K-Means algorithm parameters
38 nClusters = 20
39 nIterations = 5
40 
41 if __name__ == "__main__":
42 
43  # Retrieve the data from the input file
44  dataTable = createSparseTable(datasetFileName)
45 
46  # Get initial clusters for the K-Means algorithm
47  init = kmeans.init.Batch(nClusters, method=kmeans.init.randomDense)
48 
49  init.input.set(kmeans.init.data, dataTable)
50  res = init.compute()
51 
52  centroids = res.get(kmeans.init.centroids)
53 
54  # Create an algorithm object for the K-Means algorithm
55  algorithm = kmeans.Batch(nClusters, nIterations, method=kmeans.lloydCSR)
56 
57  algorithm.input.set(kmeans.data, dataTable)
58  algorithm.input.set(kmeans.inputCentroids, centroids)
59 
60  res = algorithm.compute()
61 
62  # Print the clusterization results
63  printNumericTable(res.get(kmeans.assignments), "First 10 cluster assignments:", 10)
64  printNumericTable(res.get(kmeans.centroids), "First 10 dimensions of centroids:", 20, 10)
65  printNumericTable(res.get(kmeans.objectiveFunction), "Objective function value:")

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