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.
22 from daal.algorithms.linear_regression
import training, prediction
23 from daal.data_management
import (
24 DataSourceIface, FileDataSource, HomogenNumericTable, MergedNumericTable, NumericTableIface
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
32 DAAL_PREFIX = os.path.join(
'..',
'data')
35 trainDatasetFileName = os.path.join(DAAL_PREFIX,
'online',
'linear_regression_train.csv')
36 testDatasetFileName = os.path.join(DAAL_PREFIX,
'online',
'linear_regression_test.csv')
38 nTrainVectorsInBlock = 250
41 nDependentVariables = 2
44 predictionResult =
None
51 trainDataSource = FileDataSource(
52 trainDatasetFileName, DataSourceIface.notAllocateNumericTable,
53 DataSourceIface.doDictionaryFromContext
57 trainData = HomogenNumericTable(nFeatures, 0, NumericTableIface.doNotAllocate)
58 trainDependentVariables = HomogenNumericTable(
59 nDependentVariables, 0, NumericTableIface.doNotAllocate
61 mergedData = MergedNumericTable(trainData, trainDependentVariables)
64 algorithm = training.Online()
66 while(trainDataSource.loadDataBlock(nTrainVectorsInBlock, mergedData) == nTrainVectorsInBlock):
68 algorithm.input.set(training.data, trainData)
69 algorithm.input.set(training.dependentVariables, trainDependentVariables)
75 trainingResult = algorithm.finalizeCompute()
77 printNumericTable(trainingResult.get(training.model).getBeta(),
"Linear Regression coefficients:")
81 global trainingResult, predictionResult
84 testDataSource = FileDataSource(
85 testDatasetFileName, DataSourceIface.doAllocateNumericTable,
86 DataSourceIface.doDictionaryFromContext
90 testData = HomogenNumericTable(nFeatures, 0, NumericTableIface.doNotAllocate)
91 testGroundTruth = HomogenNumericTable(nDependentVariables, 0, NumericTableIface.doNotAllocate)
92 mergedData = MergedNumericTable(testData, testGroundTruth)
95 testDataSource.loadDataBlock(mergedData)
98 algorithm = prediction.Batch()
101 algorithm.input.setTable(prediction.data, testData)
102 algorithm.input.setModel(prediction.model, trainingResult.get(training.model))
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)
109 if __name__ ==
"__main__":