Python* API Reference for Intel® Data Analytics Acceleration Library 2018 Update 3

datastructures_homogen.py

1 # file: datastructures_homogen.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 import numpy as np
23 
24 from daal.data_management import HomogenNumericTable, BlockDescriptor, readOnly
25 
26 utils_folder = os.path.realpath(os.path.abspath(os.path.dirname(os.path.dirname(__file__))))
27 if utils_folder not in sys.path:
28  sys.path.insert(0, utils_folder)
29 from utils import printArray
30 
31 
32 if __name__ == "__main__":
33 
34  print("Homogeneous numeric table example\n")
35 
36  data = np.array([(0.0, 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1),
37  (1.0, 1.1, 1.2, 1.3, 1.4, 1.5, 1.6, 1.7, 1.8, 1.9, 2),
38  (2.0, 2.1, 2.2, 2.3, 2.4, 2.5, 2.6, 2.7, 2.8, 2.9, 3),
39  (3.0, 3.1, 3.2, 3.3, 3.4, 3.5, 3.6, 3.7, 3.8, 3.9, 4),
40  (4.0, 4.1, 4.2, 4.3, 4.4, 4.5, 4.6, 4.7, 4.8, 4.9, 5),
41  (5.0, 5.1, 5.2, 5.3, 5.4, 5.5, 5.6, 5.7, 5.8, 5.9, 1),
42  (6.0, 6.1, 6.2, 6.3, 6.4, 6.5, 6.6, 6.7, 6.8, 6.9, 2),
43  (7.0, 7.1, 7.2, 7.3, 7.4, 7.5, 7.6, 7.7, 7.8, 7.9, 3),
44  (8.0, 8.1, 8.2, 8.3, 8.4, 8.5, 8.6, 8.7, 8.8, 8.9, 4),
45  (9.0, 9.1, 9.2, 9.3, 9.4, 9.5, 9.6, 9.7, 9.8, 9.9, 5),])
46 
47  nObservations = len(data)
48  nFeatures = len(data[0])
49  firstReadRow = 0
50  nRead = 3
51  # Construct AOS numericTable for a data array with nFeatures fields and nObservations elements
52  # Dictionary will be initialized with type information from ndarray
53  dataTable = HomogenNumericTable(data)
54  block = BlockDescriptor()
55  num_cols = block.getNumberOfColumns()
56  dataTable.getBlockOfRows(firstReadRow, nRead, readOnly, block)
57  print("%s rows are read" % (block.getNumberOfRows()))
58  printArray(
59  block.getArray(), nFeatures, block.getNumberOfRows(), 11,
60  "Print 3 rows from homogeneous data array as double:"
61  )
62  dataTable.releaseBlockOfRows(block)
63 
64  readFeatureIdx = 2
65  dataTable.getBlockOfColumnValues(readFeatureIdx, firstReadRow, nObservations, readOnly, block)
66  printArray(block.getArray(), 1, 10, 1, "Print the third feature of homogeneous data:")
67  dataTable.releaseBlockOfColumnValues(block)
68 
69  data[0][0] = 999
70  dataFromNumericTable = dataTable.getArray()
71  printArray(dataFromNumericTable, nFeatures, nObservations, 11, "Data from getArray:")
72 
73  newData = np.array([(1.0, 2.0),
74  (3.0, 4.0),
75  (5.0, 6.0),])
76 
77  nNewVectors = len(newData)
78  nNewFeatures = len(newData[0])
79 
80  # Set new data to HomogenNumericTable. It mush have the same type as the numeric table.
81  dataTable = HomogenNumericTable(newData)
82 
83  # Set a new number of columns and rows
84  dataTable.setNumberOfColumns(nNewFeatures)
85  dataTable.setNumberOfRows(nNewVectors)
86 
87  # Ensure the data has changed
88  readFeatureIdx = 1
89  dataTable.getBlockOfColumnValues(readFeatureIdx, firstReadRow, nNewVectors, readOnly, block)
90  printArray(block.getArray(), 1, 3, 1, "Print the second feature of new data:")
91  dataTable.releaseBlockOfColumnValues(block)

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