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

kmeans_dense_batch.py

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

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