Python* API Reference for Intel® Data Analytics Acceleration Library 2018 Update 3

kdtree_knn_dense_batch.py

1 # file: kdtree_knn_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 
17 
18 
19 import os
20 import sys
21 
22 from daal.algorithms.kdtree_knn_classification import training, prediction
23 from daal.algorithms import classifier
24 from daal.data_management import (
25  DataSourceIface, FileDataSource, 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', 'k_nearest_neighbors_train.csv')
37 testDatasetFileName = os.path.join(DAAL_PREFIX, 'batch', 'k_nearest_neighbors_test.csv')
38 
39 nFeatures = 5
40 
41 trainingResult = None
42 predictionResult = None
43 
44 
45 def trainModel():
46  global trainingResult
47 
48  # Initialize FileDataSource<CSVFeatureManager> to retrieve the input data from a .csv file
49  trainDataSource = FileDataSource(
50  trainDatasetFileName, DataSourceIface.notAllocateNumericTable,
51  DataSourceIface.doDictionaryFromContext
52  )
53 
54  # Create Numeric Tables for training data and dependent variables
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 input file
60  trainDataSource.loadDataBlock(mergedData)
61 
62  # Create an algorithm object to train the KD-tree based kNN 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  # Train the KD-tree based kNN model
70  trainingResult = algorithm.compute()
71 
72 
73 def testModel():
74  global trainingResult, predictionResult
75 
76  # Initialize FileDataSource<CSVFeatureManager> to retrieve the test data from a .csv file
77  testDataSource = FileDataSource(
78  testDatasetFileName, DataSourceIface.doAllocateNumericTable,
79  DataSourceIface.doDictionaryFromContext
80  )
81 
82  # Create Numeric Tables for testing data and ground truth values
83  testData = HomogenNumericTable(nFeatures, 0, NumericTableIface.doNotAllocate)
84  testGroundTruth = HomogenNumericTable(1, 0, NumericTableIface.doNotAllocate)
85  mergedData = MergedNumericTable(testData, testGroundTruth)
86 
87  # Load the data from the data file
88  testDataSource.loadDataBlock(mergedData)
89 
90  # Create algorithm objects for KD-tree based kNN prediction with the default method
91  algorithm = prediction.Batch()
92 
93  # Pass the testing data set and trained model to the algorithm
94  algorithm.input.setTable(classifier.prediction.data, testData)
95  algorithm.input.setModel(classifier.prediction.model, trainingResult.get(classifier.training.model))
96 
97  # Compute prediction results
98  predictionResult = algorithm.compute()
99  printNumericTables(
100  testGroundTruth, predictionResult.get(classifier.prediction.prediction),
101  "Ground truth", "Classification results",
102  "KD-tree based kNN classification results (first 20 observations):", 20, flt64=False
103  )
104 
105 if __name__ == "__main__":
106 
107  trainModel()
108  testModel()

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