Python* API Reference for Intel® Data Analytics Acceleration Library 2020 Update 1

out_detect_mult_dense_batch.py

1 # file: out_detect_mult_dense_batch.py
2 #===============================================================================
3 # Copyright 2014-2020 Intel Corporation
4 #
5 # Licensed under the Apache License, Version 2.0 (the "License");
6 # you may not use this file except in compliance with the License.
7 # You may obtain a copy of the License at
8 #
9 # http://www.apache.org/licenses/LICENSE-2.0
10 #
11 # Unless required by applicable law or agreed to in writing, software
12 # distributed under the License is distributed on an "AS IS" BASIS,
13 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14 # See the License for the specific language governing permissions and
15 # limitations under the License.
16 #===============================================================================
17 
18 
19 
20 
21 import os
22 import sys
23 
24 from daal.algorithms import multivariate_outlier_detection
25 from daal.data_management import FileDataSource, DataSourceIface
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 printNumericTables
31 
32 DAAL_PREFIX = os.path.join('..', 'data')
33 
34 # Input data set parameters
35 datasetFileName = os.path.join(DAAL_PREFIX, 'batch', 'outlierdetection.csv')
36 
37 if __name__ == "__main__":
38 
39  # Initialize FileDataSource<CSVFeatureManager> to retrieve the test data from a .csv file
40  dataSource = FileDataSource(
41  datasetFileName, DataSourceIface.doAllocateNumericTable,
42  DataSourceIface.doDictionaryFromContext
43  )
44 
45  # Retrieve the data from the input file
46  dataSource.loadDataBlock()
47 
48  # Create an algorithm to detect outliers using the default method
49  algorithm = multivariate_outlier_detection.Batch()
50 
51  algorithm.input.set(multivariate_outlier_detection.data, dataSource.getNumericTable())
52 
53  # Compute outliers and get the computed results
54  res = algorithm.compute()
55 
56  printNumericTables(
57  dataSource.getNumericTable(),
58  res.get(multivariate_outlier_detection.weights),
59  "Input data", "Weights",
60  "Outlier detection result (Default method)"
61  )

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