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

dt_cls_dense_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: dt_cls_dense_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-DT_CLS_DENSE_BATCH"></a>
17 ## \example dt_cls_dense_batch.py
18 
19 import os
20 import sys
21 
22 from daal.algorithms.decision_tree.classification import prediction, training
23 from daal.algorithms import classifier
24 from daal.data_management import (
25  FileDataSource, DataSourceIface, NumericTableIface, HomogenNumericTable, MergedNumericTable
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
31 
32 DAAL_PREFIX = os.path.join('..', 'data')
33 
34 # Input data set parameters
35 trainDatasetFileName = os.path.join(DAAL_PREFIX, 'batch', 'decision_tree_train.csv')
36 pruneDatasetFileName = os.path.join(DAAL_PREFIX, 'batch', 'decision_tree_prune.csv')
37 testDatasetFileName = os.path.join(DAAL_PREFIX, 'batch', 'decision_tree_test.csv')
38 
39 nFeatures = 5
40 nClasses = 5
41 
42 # Model object for the decision tree classification algorithm
43 model = None
44 predictionResult = None
45 testGroundTruth = None
46 
47 
48 def trainModel():
49  global model
50 
51  # Initialize FileDataSource<CSVFeatureManager> to retrieve the input data from a .csv file
52  trainDataSource = FileDataSource(
53  trainDatasetFileName,
54  DataSourceIface.notAllocateNumericTable,
55  DataSourceIface.doDictionaryFromContext
56  )
57 
58  # Create Numeric Tables for training data and labels
59  trainData = HomogenNumericTable(nFeatures, 0, NumericTableIface.notAllocate)
60  trainGroundTruth = HomogenNumericTable(1, 0, NumericTableIface.notAllocate)
61  mergedData = MergedNumericTable(trainData, trainGroundTruth)
62 
63  # Retrieve the data from the input file
64  trainDataSource.loadDataBlock(mergedData)
65 
66  # Initialize FileDataSource<CSVFeatureManager> to retrieve the input data from a .csv file
67  pruneDataSource = FileDataSource(
68  pruneDatasetFileName,
69  DataSourceIface.notAllocateNumericTable,
70  DataSourceIface.doDictionaryFromContext
71  )
72 
73  # Create Numeric Tables for pruning data and labels
74  pruneData = HomogenNumericTable(nFeatures, 0, NumericTableIface.notAllocate)
75  pruneGroundTruth = HomogenNumericTable(1, 0, NumericTableIface.notAllocate)
76  pruneMergedData = MergedNumericTable(pruneData, pruneGroundTruth)
77 
78  # Retrieve the data from the input file
79  pruneDataSource.loadDataBlock(pruneMergedData)
80 
81  # Create an algorithm object to train the decision tree classification model
82  algorithm = training.Batch(nClasses)
83 
84  # Pass the training data set and dependent values to the algorithm
85  algorithm.input.set(classifier.training.data, trainData)
86  algorithm.input.set(classifier.training.labels, trainGroundTruth)
87  algorithm.input.setTable(training.dataForPruning, pruneData)
88  algorithm.input.setTable(training.labelsForPruning, pruneGroundTruth)
89 
90  # Train the decision tree classification model and retrieve the results of the training algorithm
91  trainingResult = algorithm.compute()
92  model = trainingResult.get(classifier.training.model)
93 
94 def testModel():
95  global testGroundTruth, predictionResult
96 
97  # Initialize FileDataSource<CSVFeatureManager> to retrieve the test data from a .csv file
98  testDataSource = FileDataSource(
99  testDatasetFileName,
100  DataSourceIface.notAllocateNumericTable,
101  DataSourceIface.doDictionaryFromContext
102  )
103 
104  # Create Numeric Tables for testing data and labels
105  testData = HomogenNumericTable(nFeatures, 0, NumericTableIface.notAllocate)
106  testGroundTruth = HomogenNumericTable(1, 0, NumericTableIface.notAllocate)
107  mergedData = MergedNumericTable(testData, testGroundTruth)
108 
109  # Retrieve the data from input file
110  testDataSource.loadDataBlock(mergedData)
111 
112  # Create algorithm objects for decision tree classification prediction with the default method
113  algorithm = prediction.Batch()
114 
115  # Pass the testing data set and trained model to the algorithm
116  #print("Number of columns: {}".format(testData.getNumberOfColumns()))
117  algorithm.input.setTable(classifier.prediction.data, testData)
118  algorithm.input.setModel(classifier.prediction.model, model)
119 
120  # Compute prediction results and retrieve algorithm results
121  # (Result class from classifier.prediction)
122  predictionResult = algorithm.compute()
123 
124 
125 def printResults():
126 
127  printNumericTables(
128  testGroundTruth,
129  predictionResult.get(classifier.prediction.prediction),
130  "Ground truth", "Classification results",
131  "Decision tree classification results (first 20 observations):",
132  20, flt64=False
133  )
134 
135 if __name__ == "__main__":
136 
137  trainModel()
138  testModel()
139  printResults()

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