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

simple_csv_feature_modifiers.py

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.

1 # file: simple_csv_feature_modifiers.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 # ! Content:
17 # ! Python example of modifiers usage with file data source
18 # !*****************************************************************************
19 
20 #
21 ## <a name="DAAL-EXAMPLE-PY-DATASOURCE_SIMPLE_CSV_FEATURE_MODIFIERS">
22 ## \example simple_csv_feature_modifiers.py
23 #
24 
25 from daal.data_management import FileDataSource, CsvDataSourceOptions, modifiers, features
26 from daal.data_management.modifiers import csv
27 
28 import os, sys
29 utils_folder = os.path.realpath(os.path.abspath(os.path.dirname(os.path.dirname(__file__))))
30 if utils_folder not in sys.path:
31  sys.path.insert(0, utils_folder)
32 from utils import printNumericTable
33 
34 # Path to the CSV to be read
35 csvFileName = "../data/batch/mixed_text_and_numbers.csv"
36 
37 # Define options for CSV data source
38 csvOptions = CsvDataSourceOptions(CsvDataSourceOptions.allocateNumericTable |\
39  CsvDataSourceOptions.createDictionaryFromContext |\
40  CsvDataSourceOptions.parseHeader)
41 
42 # Read CSV using default data source behavior
43 def readDefault():
44  ds = FileDataSource(csvFileName, csvOptions)
45  # By default all numeric columns will be parsed as continuous
46  # features and other columns as categorical
47  ds.loadDataBlock()
48  printNumericTable(ds.getNumericTable(), "readDefault function result:")
49 
50 
51 # Read CSV and do basic filtering using columns indices
52 def readOnlySpecifiedColumnIndices():
53  ds = FileDataSource(csvFileName, csvOptions)
54  # This means that columns with indices 0, 1, 5 will be included to the output numeric
55  # table and other columns will be ignored. The first argument of method 'include' specifies
56  # the set of columns and the second one specifies modifier. in this case we use predefined
57  # automatic modifier that automatically decides how to parse column in the best way
58  print(modifiers.csv.automatic())
59  ds.getFeatureManager().addModifier([0,1,5], modifiers.csv.automatic())
60  ds.loadDataBlock()
61  printNumericTable(ds.getNumericTable(), "readOnlySpecifiedColumnIndices function result:")
62 
63 
64 # Read CSV and do basic filtering using columns names
65 def readOnlySpecifiedColumnNames():
66  ds = FileDataSource(csvFileName, csvOptions)
67  # The same as readOnlySpecifiedColumnIndices but uses column names instead of indices
68  ds.getFeatureManager().addModifier(["Numeric1", "Categorical0"], modifiers.csv.automatic())
69  ds.loadDataBlock()
70  printNumericTable(ds.getNumericTable(), "readOnlySpecifiedColumnNames function result:")
71 
72 
73 # Read CSV using multiple modifiers
74 def readUsingMultipleModifiers():
75  ds = FileDataSource(csvFileName, csvOptions)
76 
77  fm = ds.getFeatureManager()
78  fm.addModifier(["Numeric1"], modifiers.csv.continuous())
79  # let's mix position and names
80  fm.addModifier([6, "Categorical1"], modifiers.csv.categorical())
81 
82  ds.loadDataBlock()
83  printNumericTable(ds.getNumericTable(), "readUsingMultipleModifiers function result:")
84 
85 
86 if __name__ == "__main__":
87  # Read CSV using default data source behavior
88  readDefault()
89 
90  # Read CSV and do basic filtering using columns indices
91  readOnlySpecifiedColumnIndices()
92 
93  # Read CSV and do basic filtering using columns names
94  readOnlySpecifiedColumnNames()
95 
96  # Read CSV using multiple modifiers
97  readUsingMultipleModifiers()

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