Python* API Reference for Intel® Data Analytics Acceleration Library 2019 Update 4

mn_naive_bayes_csr_distr.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: mn_naive_bayes_csr_distr.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-MULTINOMIAL_NAIVE_BAYES_CSR_DISTRIBUTED"></a>
17 ## \example mn_naive_bayes_csr_distr.py
18 
19 import os
20 import sys
21 
22 from daal import step1Local, step2Master
23 from daal.algorithms import classifier
24 from daal.algorithms.multinomial_naive_bayes import training, prediction
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 printNumericTables, createSparseTable
31 
32 DAAL_PREFIX = os.path.join('..', 'data')
33 
34 # Input data set parameters
35 trainDatasetFileNames = [
36  os.path.join(DAAL_PREFIX, 'batch', 'naivebayes_train_csr.csv'),
37  os.path.join(DAAL_PREFIX, 'batch', 'naivebayes_train_csr.csv'),
38  os.path.join(DAAL_PREFIX, 'batch', 'naivebayes_train_csr.csv'),
39  os.path.join(DAAL_PREFIX, 'batch', 'naivebayes_train_csr.csv')
40 ]
41 
42 trainGroundTruthFileNames = [
43  os.path.join(DAAL_PREFIX, 'batch', 'naivebayes_train_labels.csv'),
44  os.path.join(DAAL_PREFIX, 'batch', 'naivebayes_train_labels.csv'),
45  os.path.join(DAAL_PREFIX, 'batch', 'naivebayes_train_labels.csv'),
46  os.path.join(DAAL_PREFIX, 'batch', 'naivebayes_train_labels.csv')
47 ]
48 
49 testDatasetFileName = os.path.join(DAAL_PREFIX, 'batch', 'naivebayes_test_csr.csv')
50 testGroundTruthFileName = os.path.join(DAAL_PREFIX, 'batch', 'naivebayes_test_labels.csv')
51 
52 nClasses = 20
53 nBlocks = 4
54 nTrainVectorsInBlock = 8000
55 nTestObservations = 2000
56 
57 trainingResult = None
58 predictionResult = None
59 trainData = [0] * nBlocks
60 testData = None
61 
62 
63 def trainModel():
64  global trainData, trainingResult
65 
66  masterAlgorithm = training.Distributed(step2Master, nClasses, method=training.fastCSR)
67 
68  for i in range(nBlocks):
69  # Read trainDatasetFileNames and create a numeric table to store the input data
70  trainData[i] = createSparseTable(trainDatasetFileNames[i])
71 
72  # Initialize FileDataSource<CSVFeatureManager> to retrieve the input data from a .csv file
73  trainLabelsSource = FileDataSource(
74  trainGroundTruthFileNames[i], DataSourceIface.doAllocateNumericTable,
75  DataSourceIface.doDictionaryFromContext
76  )
77 
78  # Retrieve the data from an input file
79  trainLabelsSource.loadDataBlock(nTrainVectorsInBlock)
80 
81  # Create an algorithm object to train the Naive Bayes model on the local-node data
82  localAlgorithm = training.Distributed(step1Local, nClasses, method=training.fastCSR)
83 
84  # Pass a training data set and dependent values to the algorithm
85  localAlgorithm.input.set(classifier.training.data, trainData[i])
86  localAlgorithm.input.set(classifier.training.labels, trainLabelsSource.getNumericTable())
87 
88  # Build the Naive Bayes model on the local node
89  # Set the local Naive Bayes model as input for the master-node algorithm
90  masterAlgorithm.input.add(training.partialModels, localAlgorithm.compute())
91 
92  # Merge and finalize the Naive Bayes model on the master node
93  masterAlgorithm.compute()
94  trainingResult = masterAlgorithm.finalizeCompute() # Retrieve the algorithm results
95 
96 
97 def testModel():
98  global predictionResult, testData
99 
100  # Read testDatasetFileName and create a numeric table to store the input data
101  testData = createSparseTable(testDatasetFileName)
102 
103  # Create an algorithm object to predict Naive Bayes values
104  algorithm = prediction.Batch(nClasses, method=prediction.fastCSR)
105 
106  # Pass a testing data set and the trained model to the algorithm
107  algorithm.input.setTable(classifier.prediction.data, testData)
108  algorithm.input.setModel(classifier.prediction.model, trainingResult.get(classifier.training.model))
109 
110  # Predict Naive Bayes values (Result class from classifier.prediction)
111  predictionResult = algorithm.compute() # Retrieve the algorithm results
112 
113 
114 def printResults():
115 
116  testGroundTruth = FileDataSource(
117  testGroundTruthFileName, DataSourceIface.doAllocateNumericTable,
118  DataSourceIface.doDictionaryFromContext
119  )
120  testGroundTruth.loadDataBlock(nTestObservations)
121 
122  printNumericTables(
123  testGroundTruth.getNumericTable(),
124  predictionResult.get(classifier.prediction.prediction),
125  "Ground truth", "Classification results",
126  "NaiveBayes classification results (first 20 observations):", 20, 15, flt64=False
127  )
128 
129 if __name__ == "__main__":
130 
131  trainModel()
132  testModel()
133  printResults()

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