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

lin_reg_qr_dense_batch.py

1 # file: lin_reg_qr_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 
17 
18 
19 import os
20 import sys
21 
22 from daal.algorithms.linear_regression import training, prediction
23 from daal.data_management import (
24  DataSourceIface, FileDataSource, HomogenNumericTable, MergedNumericTable, NumericTableIface
25 )
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 printNumericTable
31 
32 DAAL_PREFIX = os.path.join('..', 'data')
33 
34 # Input data set parameters
35 trainDatasetFileName = os.path.join(DAAL_PREFIX, 'batch', 'linear_regression_train.csv')
36 testDatasetFileName = os.path.join(DAAL_PREFIX, 'batch', 'linear_regression_test.csv')
37 
38 nFeatures = 10 # Number of features in training and testing data sets
39 nDependentVariables = 2 # Number of dependent variables that correspond to each observation
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  trainDependentVariables = HomogenNumericTable(
57  nDependentVariables, 0, NumericTableIface.doNotAllocate
58  )
59  mergedData = MergedNumericTable(trainData, trainDependentVariables)
60 
61  # Retrieve the data from input file
62  trainDataSource.loadDataBlock(mergedData)
63 
64  # Create an algorithm object to train the multiple linear regression model with a QR decomposition-based method
65  algorithm = training.Batch(method=training.qrDense)
66 
67  # Pass a training data set and dependent values to the algorithm
68  algorithm.input.set(training.data, trainData)
69  algorithm.input.set(training.dependentVariables, trainDependentVariables)
70 
71  # Build the multiple linear regression model and retrieve the algorithm results
72  trainingResult = algorithm.compute()
73  printNumericTable(trainingResult.get(training.model).getBeta(), "Linear Regression coefficients:")
74 
75 
76 def testModel():
77  global predictionResult
78 
79  # Initialize FileDataSource<CSVFeatureManager> to retrieve the test data from a .csv file
80  testDataSource = FileDataSource(
81  testDatasetFileName, DataSourceIface.doAllocateNumericTable,
82  DataSourceIface.doDictionaryFromContext
83  )
84 
85  # Create Numeric Tables for testing data and ground truth values
86  testData = HomogenNumericTable(nFeatures, 0, NumericTableIface.doNotAllocate)
87  testGroundTruth = HomogenNumericTable(nDependentVariables, 0, NumericTableIface.doNotAllocate)
88  mergedData = MergedNumericTable(testData, testGroundTruth)
89 
90  testDataSource.loadDataBlock(mergedData)
91 
92  # Create an algorithm object to predict values of multiple linear regression
93  algorithm = prediction.Batch()
94 
95  # Pass a testing data set and the trained model to the algorithm
96  algorithm.input.setTable(prediction.data, testData)
97  algorithm.input.setModel(prediction.model, trainingResult.get(training.model))
98 
99  # Predict values of multiple linear regression and retrieve the algorithm results
100  predictionResult = algorithm.compute()
101  printNumericTable(predictionResult.get(prediction.prediction), "Linear Regression prediction results: (first 10 rows):", 10)
102  printNumericTable(testGroundTruth, "Ground truth (first 10 rows):", 10)
103 
104 if __name__ == "__main__":
105 
106  trainModel()
107  testModel()

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