Python* API Reference for Intel® Data Analytics Acceleration Library 2018 Update 1

assoc_rules_apriori_batch.py

1 #===============================================================================
2 # Copyright 2014-2017 Intel Corporation
3 # All Rights Reserved.
4 #
5 # If this software was obtained under the Intel Simplified Software License,
6 # the following terms apply:
7 #
8 # The source code, information and material ("Material") contained herein is
9 # owned by Intel Corporation or its suppliers or licensors, and title to such
10 # Material remains with Intel Corporation or its suppliers or licensors. The
11 # Material contains proprietary information of Intel or its suppliers and
12 # licensors. The Material is protected by worldwide copyright laws and treaty
13 # provisions. No part of the Material may be used, copied, reproduced,
14 # modified, published, uploaded, posted, transmitted, distributed or disclosed
15 # in any way without Intel's prior express written permission. No license under
16 # any patent, copyright or other intellectual property rights in the Material
17 # is granted to or conferred upon you, either expressly, by implication,
18 # inducement, estoppel or otherwise. Any license under such intellectual
19 # property rights must be express and approved by Intel in writing.
20 #
21 # Unless otherwise agreed by Intel in writing, you may not remove or alter this
22 # notice or any other notice embedded in Materials by Intel or Intel's
23 # suppliers or licensors in any way.
24 #
25 #
26 # If this software was obtained under the Apache License, Version 2.0 (the
27 # "License"), the following terms apply:
28 #
29 # You may not use this file except in compliance with the License. You may
30 # obtain a copy of the License at http://www.apache.org/licenses/LICENSE-2.0
31 #
32 #
33 # Unless required by applicable law or agreed to in writing, software
34 # distributed under the License is distributed on an "AS IS" BASIS, WITHOUT
35 # WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
36 #
37 # See the License for the specific language governing permissions and
38 # limitations under the License.
39 #===============================================================================
40 
41 
42 
43 
44 import os
45 import sys
46 
47 from daal.algorithms import association_rules
48 from daal.data_management import FileDataSource, DataSourceIface
49 
50 utils_folder = os.path.realpath(os.path.abspath(os.path.dirname(os.path.dirname(__file__))))
51 if utils_folder not in sys.path:
52  sys.path.insert(0, utils_folder)
53 from utils import printAprioriItemsets, printAprioriRules
54 
55 # Input data set parameters
56 datasetFileName = os.path.join('..','data','batch','apriori.csv')
57 
58 # Apriori algorithm parameters
59 minSupport = 0.001
60 minConfidence = 0.7
61 
62 # Initialize FileDataSource_CSVFeatureManager to retrieve the input data from a .csv file
63 dataSource = FileDataSource(
64  datasetFileName, DataSourceIface.doAllocateNumericTable, DataSourceIface.doDictionaryFromContext
65 )
66 
67 # Retrieve the data from the input file
68 dataSource.loadDataBlock()
69 
70 # Create an algorithm to mine association rules using the Apriori method
71 alg = association_rules.Batch()
72 alg.input.set(association_rules.data, dataSource.getNumericTable())
73 alg.parameter.minSupport = minSupport
74 alg.parameter.minConfidence = minConfidence
75 
76 # Find large item sets and construct association rules
77 res = alg.compute()
78 
79 # Get computed results of the Apriori algorithm
80 nt1 = res.get(association_rules.largeItemsets)
81 nt2 = res.get(association_rules.largeItemsetsSupport)
82 
83 nt3 = res.get(association_rules.antecedentItemsets)
84 nt4 = res.get(association_rules.consequentItemsets)
85 nt5 = res.get(association_rules.confidence)
86 
87 printAprioriItemsets(nt1, nt2)
88 printAprioriRules(nt3, nt4, nt5)

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