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

stump_dense_batch.py

1 # file: stump_dense_batch.py
2 #===============================================================================
3 # Copyright 2014-2018 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-STUMP_BATCH"></a>
17 ## \example stump_dense_batch.py
18 
19 import os
20 import sys
21 
22 from daal.algorithms import classifier
23 from daal.algorithms.stump import training, prediction
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 nFeatures = 20
37 trainDatasetFileName = os.path.join(DAAL_PREFIX, 'batch', 'stump_train.csv')
38 testDatasetFileName = os.path.join(DAAL_PREFIX, 'batch', 'stump_test.csv')
39 
40 trainingResult = None
41 predictionResult = None
42 testGroundTruth = None
43 
44 
45 def trainModel():
46  global trainingResult
47  # Initialize FileDataSource<CSVFeatureManager> to retrieve the input data from a .csv file
48  trainDataSource = FileDataSource(
49  trainDatasetFileName,
50  DataSourceIface.notAllocateNumericTable,
51  DataSourceIface.doDictionaryFromContext
52  )
53 
54  # Create Numeric Tables for training data and labels
55  trainData = HomogenNumericTable(nFeatures, 0, NumericTableIface.doNotAllocate)
56  trainGroundTruth = HomogenNumericTable(1, 0, NumericTableIface.doNotAllocate)
57  mergedData = MergedNumericTable(trainData, trainGroundTruth)
58 
59  # Retrieve the data from the input file
60  trainDataSource.loadDataBlock(mergedData)
61 
62  # Create an algorithm object to train the stump model
63  algorithm = training.Batch()
64 
65  # Pass a training data set and dependent values to the algorithm
66  algorithm.input.set(classifier.training.data, trainData)
67  algorithm.input.set(classifier.training.labels, trainGroundTruth)
68 
69  # Compute and retrieve the algorithm results
70  trainingResult = algorithm.compute()
71 
72 
73 def testModel():
74  global predictionResult, testGroundTruth
75 
76  # Initialize FileDataSource<CSVFeatureManager> to retrieve the test data from a .csv file
77  testDataSource = FileDataSource(
78  testDatasetFileName,
79  DataSourceIface.notAllocateNumericTable,
80  DataSourceIface.doDictionaryFromContext
81  )
82 
83  # Create Numeric Tables for training data and labels
84  testData = HomogenNumericTable(nFeatures, 0, NumericTableIface.doNotAllocate)
85  testGroundTruth = HomogenNumericTable(1, 0, NumericTableIface.doNotAllocate)
86  mergedData = MergedNumericTable(testData, testGroundTruth)
87 
88  # Retrieve the data from the input file
89  testDataSource.loadDataBlock(mergedData)
90 
91  # Create an algorithm object to train the stump model
92  algorithm = prediction.Batch()
93 
94  # Pass a training data set and dependent values to the algorithm
95  algorithm.input.setTable(classifier.prediction.data, testData)
96  algorithm.input.setModel(classifier.prediction.model,
97  trainingResult.get(classifier.training.model))
98 
99  # Compute and retrieve the algorithm Result class from classifier.prediction
100  predictionResult = algorithm.compute()
101 
102 
103 def printResults():
104  printNumericTables(
105  testGroundTruth,
106  predictionResult.get(classifier.prediction.prediction),
107  "Ground truth", "Classification results",
108  "Stump classification results (first 20 observations):", 20, flt64=False)
109 
110 if __name__ == "__main__":
111  trainModel()
112  testModel()
113  printResults()

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