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

logitboost_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: logitboost_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-LOGITBOOST_BATCH"></a>
17 ## \example logitboost_dense_batch.py
18 
19 import os
20 import sys
21 
22 from daal.algorithms.logitboost import prediction, training
23 from daal.algorithms import classifier
24 from daal.data_management import (
25  FileDataSource, DataSourceIface, NumericTableIface, HomogenNumericTable, MergedNumericTable
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', 'logitboost_train.csv')
37 testDatasetFileName = os.path.join(DAAL_PREFIX, 'batch', 'logitboost_test.csv')
38 
39 nFeatures = 20
40 nClasses = 5
41 
42 # LogitBoost algorithm parameters
43 maxIterations = 100 # Maximum number of terms in additive regression
44 accuracyThreshold = 0.01 # Training accuracy
45 
46 # Model object for the LogitBoost algorithm
47 model = None
48 predictionResult = None
49 testGroundTruth = None
50 
51 
52 def trainModel():
53  global model
54 
55  # Initialize FileDataSource<CSVFeatureManager> to retrieve the input data from a .csv file
56  trainDataSource = FileDataSource(
57  trainDatasetFileName,
58  DataSourceIface.notAllocateNumericTable,
59  DataSourceIface.doDictionaryFromContext
60  )
61 
62  # Create Numeric Tables for training data and labels
63  trainData = HomogenNumericTable(nFeatures, 0, NumericTableIface.doNotAllocate)
64  trainGroundTruth = HomogenNumericTable(1, 0, NumericTableIface.doNotAllocate)
65  mergedData = MergedNumericTable(trainData, trainGroundTruth)
66 
67  # Retrieve the data from the input file
68  trainDataSource.loadDataBlock(mergedData)
69 
70  # Create an algorithm object to train the LogitBoost model
71  algorithm = training.Batch(nClasses)
72  algorithm.parameter.maxIterations = maxIterations
73  algorithm.parameter.accuracyThreshold = accuracyThreshold
74 
75  # Pass the training data set and dependent values to the algorithm
76  algorithm.input.set(classifier.training.data, trainData)
77  algorithm.input.set(classifier.training.labels, trainGroundTruth)
78 
79  # Train the LogitBoost model and retrieve the results of the training algorithm
80  trainingResult = algorithm.compute()
81  model = trainingResult.get(classifier.training.model)
82 
83 
84 def testModel():
85  global testGroundTruth, predictionResult
86 
87  # Initialize FileDataSource<CSVFeatureManager> to retrieve the test data from a .csv file
88  testDataSource = FileDataSource(
89  testDatasetFileName,
90  DataSourceIface.notAllocateNumericTable,
91  DataSourceIface.doDictionaryFromContext
92  )
93 
94  # Create Numeric Tables for testing data and labels
95  testData = HomogenNumericTable(nFeatures, 0, NumericTableIface.doNotAllocate)
96  testGroundTruth = HomogenNumericTable(1, 0, NumericTableIface.doNotAllocate)
97  mergedData = MergedNumericTable(testData, testGroundTruth)
98 
99  # Retrieve the data from input file
100  testDataSource.loadDataBlock(mergedData)
101 
102  # Create algorithm objects for LogitBoost prediction with the default method
103  algorithm = prediction.Batch(nClasses)
104 
105  # Pass the testing data set and trained model to the algorithm
106  algorithm.input.setTable(classifier.prediction.data, testData)
107  algorithm.input.setModel(classifier.prediction.model, model)
108 
109  # Compute prediction results and retrieve algorithm results
110  # (Result class from classifier.prediction)
111  predictionResult = algorithm.compute()
112 
113 
114 def printResults():
115 
116  printNumericTables(
117  testGroundTruth,
118  predictionResult.get(classifier.prediction.prediction),
119  "Ground truth", "Classification results",
120  "LogitBoost classification results (first 20 observations):", 20, flt64=False
121  )
122 
123 if __name__ == "__main__":
124 
125  trainModel()
126  testModel()
127  printResults()

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