Python* API Reference for Intel® Data Analytics Acceleration Library 2019 Update 5

assoc_rules_apriori_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: assoc_rules_apriori_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-APRIORI_BATCH"></a>
17 ## \example assoc_rules_apriori_batch.py
18 
19 import os
20 import sys
21 
22 from daal.algorithms import association_rules
23 from daal.data_management import FileDataSource, DataSourceIface
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 printAprioriItemsets, printAprioriRules
29 
30 # Input data set parameters
31 datasetFileName = os.path.join('..','data','batch','apriori.csv')
32 
33 # Apriori algorithm parameters
34 minSupport = 0.001
35 minConfidence = 0.7
36 
37 # Initialize FileDataSource_CSVFeatureManager to retrieve the input data from a .csv file
38 dataSource = FileDataSource(
39  datasetFileName, DataSourceIface.doAllocateNumericTable, DataSourceIface.doDictionaryFromContext
40 )
41 
42 # Retrieve the data from the input file
43 dataSource.loadDataBlock()
44 
45 # Create an algorithm to mine association rules using the Apriori method
46 alg = association_rules.Batch()
47 alg.input.set(association_rules.data, dataSource.getNumericTable())
48 alg.parameter.minSupport = minSupport
49 alg.parameter.minConfidence = minConfidence
50 
51 # Find large item sets and construct association rules
52 res = alg.compute()
53 
54 # Get computed results of the Apriori algorithm
55 nt1 = res.get(association_rules.largeItemsets)
56 nt2 = res.get(association_rules.largeItemsetsSupport)
57 
58 nt3 = res.get(association_rules.antecedentItemsets)
59 nt4 = res.get(association_rules.consequentItemsets)
60 nt5 = res.get(association_rules.confidence)
61 
62 printAprioriItemsets(nt1, nt2)
63 printAprioriRules(nt3, nt4, nt5)

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