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

mn_naive_bayes_dense_online.py

1 # file: mn_naive_bayes_dense_online.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 
17 
18 
19 import os
20 import sys
21 
22 from daal.algorithms.multinomial_naive_bayes import prediction, training
23 from daal.algorithms import classifier
24 from daal.data_management import (
25  FileDataSource, DataSourceIface, HomogenNumericTable, MergedNumericTable, NumericTableIface
26 )
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 printNumericTables
32 
33 DAAL_PREFIX = os.path.join('..', 'data')
34 
35 # Input data set parameters
36 trainDatasetFileName = os.path.join(DAAL_PREFIX, 'batch', 'naivebayes_train_dense.csv')
37 testDatasetFileName = os.path.join(DAAL_PREFIX, 'batch', 'naivebayes_test_dense.csv')
38 
39 nFeatures = 20
40 nTrainVectorsInBlock = 2000
41 nClasses = 20
42 
43 trainingResult = None
44 predictionResult = None
45 testGroundTruth = None
46 
47 
48 def trainModel():
49  global trainingResult
50 
51  # Initialize FileDataSource<CSVFeatureManager> to retrieve the input data from a .csv file
52  trainDataSource = FileDataSource(
53  trainDatasetFileName, DataSourceIface.notAllocateNumericTable,
54  DataSourceIface.doDictionaryFromContext
55  )
56 
57  # Create Numeric Tables for training data and labels
58  trainData = HomogenNumericTable(nFeatures, 0, NumericTableIface.doNotAllocate)
59  trainGroundTruth = HomogenNumericTable(1, 0, NumericTableIface.doNotAllocate)
60  mergedData = MergedNumericTable(trainData, trainGroundTruth)
61 
62  # Create an algorithm object to train the Naive Bayes model
63  algorithm = training.Online(nClasses)
64 
65  while(trainDataSource.loadDataBlock(nTrainVectorsInBlock, mergedData) == nTrainVectorsInBlock):
66  # Pass a training data set and dependent values to the algorithm
67  algorithm.input.set(classifier.training.data, trainData)
68  algorithm.input.set(classifier.training.labels, trainGroundTruth)
69 
70  # Build the Naive Bayes model
71  algorithm.compute()
72 
73  # Finalize the Naive Bayes model
74  trainingResult = algorithm.finalizeCompute() # Retrieve the algorithm results
75 
76 
77 def testModel():
78  global predictionResult, testGroundTruth
79 
80  # Initialize FileDataSource<CSVFeatureManager> to retrieve the test data from a .csv file
81  testDataSource = FileDataSource(
82  testDatasetFileName, DataSourceIface.notAllocateNumericTable,
83  DataSourceIface.doDictionaryFromContext
84  )
85 
86  # Create Numeric Tables for testing data and labels
87  testData = HomogenNumericTable(nFeatures, 0, NumericTableIface.doNotAllocate)
88  testGroundTruth = HomogenNumericTable(1, 0, NumericTableIface.doNotAllocate)
89  mergedData = MergedNumericTable(testData, testGroundTruth)
90 
91  # Retrieve the data from input file
92  testDataSource.loadDataBlock(mergedData)
93 
94  # Create an algorithm object to predict Naive Bayes values
95  algorithm = prediction.Batch(nClasses)
96 
97  # Pass a testing data set and the trained model to the algorithm
98  algorithm.input.setTable(classifier.prediction.data, testData)
99  algorithm.input.setModel(classifier.prediction.model, trainingResult.get(classifier.training.model))
100 
101  # Predict Naive Bayes values (Result class from classifier.prediction)
102  predictionResult = algorithm.compute() # Retrieve the algorithm results
103 
104 
105 def printResults():
106 
107  printNumericTables(
108  testGroundTruth, predictionResult.get(classifier.prediction.prediction),
109  "Ground truth", "Classification results",
110  "NaiveBayes classification results (first 20 observations):", 20, flt64=False
111  )
112 
113 if __name__ == "__main__":
114 
115  trainModel()
116  testModel()
117  printResults()

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