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

datastructures_homogen.py

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

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