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

assoc_rules_apriori_batch.py

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

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