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,
'batch',
'linear_regression_train.csv')
36 testDatasetFileName = os.path.join(DAAL_PREFIX,
'batch',
'linear_regression_test.csv')
39 nDependentVariables = 2
42 predictionResult =
None
49 trainDataSource = FileDataSource(
50 trainDatasetFileName, DataSourceIface.notAllocateNumericTable,
51 DataSourceIface.doDictionaryFromContext
55 trainData = HomogenNumericTable(nFeatures, 0, NumericTableIface.doNotAllocate)
56 trainDependentVariables = HomogenNumericTable(nDependentVariables, 0, NumericTableIface.doNotAllocate)
57 mergedData = MergedNumericTable(trainData, trainDependentVariables)
60 trainDataSource.loadDataBlock(mergedData)
63 algorithm = training.Batch()
66 algorithm.input.set(training.data, trainData)
67 algorithm.input.set(training.dependentVariables, trainDependentVariables)
70 trainingResult = algorithm.compute()
71 printNumericTable(trainingResult.get(training.model).getBeta(),
"Linear Regression coefficients:")
75 global trainingResult, predictionResult
78 testDataSource = FileDataSource(
79 testDatasetFileName, DataSourceIface.doAllocateNumericTable,
80 DataSourceIface.doDictionaryFromContext
84 testData = HomogenNumericTable(nFeatures, 0, NumericTableIface.doNotAllocate)
85 testGroundTruth = HomogenNumericTable(nDependentVariables, 0, NumericTableIface.doNotAllocate)
86 mergedData = MergedNumericTable(testData, testGroundTruth)
89 testDataSource.loadDataBlock(mergedData)
92 algorithm = prediction.Batch()
95 algorithm.input.setTable(prediction.data, testData)
96 algorithm.input.setModel(prediction.model, trainingResult.get(training.model))
99 predictionResult = algorithm.compute()
100 printNumericTable(predictionResult.get(prediction.prediction),
"Linear Regression prediction results: (first 10 rows):", 10)
101 printNumericTable(testGroundTruth,
"Ground truth (first 10 rows):", 10)
103 if __name__ ==
"__main__":