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

lin_reg_norm_eq_dense_online.py

1 # file: lin_reg_norm_eq_dense_online.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.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, 'online', 'linear_regression_train.csv')
36 testDatasetFileName = os.path.join(DAAL_PREFIX, 'online', 'linear_regression_test.csv')
37 
38 nTrainVectorsInBlock = 250
39 
40 nFeatures = 10 # Number of features in training and testing data sets
41 nDependentVariables = 2 # Number of dependent variables that correspond to each observation
42 
43 trainingResult = None
44 predictionResult = None
45 
46 
47 def trainModel():
48  global trainingResult
49 
50  # Initialize FileDataSource<CSVFeatureManager> to retrieve the input data from a .csv file
51  trainDataSource = FileDataSource(
52  trainDatasetFileName, DataSourceIface.notAllocateNumericTable,
53  DataSourceIface.doDictionaryFromContext
54  )
55 
56  # Create Numeric Tables for training data and dependent variables
57  trainData = HomogenNumericTable(nFeatures, 0, NumericTableIface.doNotAllocate)
58  trainDependentVariables = HomogenNumericTable(
59  nDependentVariables, 0, NumericTableIface.doNotAllocate
60  )
61  mergedData = MergedNumericTable(trainData, trainDependentVariables)
62 
63  # Create an algorithm object to train the multiple linear regression model
64  algorithm = training.Online()
65 
66  while(trainDataSource.loadDataBlock(nTrainVectorsInBlock, mergedData) == nTrainVectorsInBlock):
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  # Update the multiple linear regression model
72  algorithm.compute()
73 
74  # Finalize the multiple linear regression model and retrieve the results
75  trainingResult = algorithm.finalizeCompute()
76 
77  printNumericTable(trainingResult.get(training.model).getBeta(), "Linear Regression coefficients:")
78 
79 
80 def testModel():
81  global trainingResult, predictionResult
82 
83  # Initialize FileDataSource<CSVFeatureManager> to retrieve the input data from a .csv file
84  testDataSource = FileDataSource(
85  testDatasetFileName, DataSourceIface.doAllocateNumericTable,
86  DataSourceIface.doDictionaryFromContext
87  )
88 
89  # Create Numeric Tables for testing data and ground truth values
90  testData = HomogenNumericTable(nFeatures, 0, NumericTableIface.doNotAllocate)
91  testGroundTruth = HomogenNumericTable(nDependentVariables, 0, NumericTableIface.doNotAllocate)
92  mergedData = MergedNumericTable(testData, testGroundTruth)
93 
94  # Retrieve the data from the input file
95  testDataSource.loadDataBlock(mergedData)
96 
97  # Create an algorithm object to predict values of multiple linear regression
98  algorithm = prediction.Batch()
99 
100  # Pass a testing data set and the trained model to the algorithm
101  algorithm.input.setTable(prediction.data, testData)
102  algorithm.input.setModel(prediction.model, trainingResult.get(training.model))
103 
104  # Predict values of multiple linear regression and retrieve the algorithm results
105  predictionResult = algorithm.compute()
106  printNumericTable(predictionResult.get(prediction.prediction), "Linear Regression prediction results: (first 10 rows):", 10)
107  printNumericTable(testGroundTruth, "Ground truth (first 10 rows):", 10)
108 
109 if __name__ == "__main__":
110 
111  trainModel()
112  testModel()

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