Python* API Reference for Intel® Data Analytics Acceleration Library 2018 Update 2

datastructures_homogen.py

1 # file: datastructures_homogen.py
2 #===============================================================================
3 # Copyright 2014-2018 Intel Corporation
4 # All Rights Reserved.
5 #
6 # If this software was obtained under the Intel Simplified Software License,
7 # the following terms apply:
8 #
9 # The source code, information and material ("Material") contained herein is
10 # owned by Intel Corporation or its suppliers or licensors, and title to such
11 # Material remains with Intel Corporation or its suppliers or licensors. The
12 # Material contains proprietary information of Intel or its suppliers and
13 # licensors. The Material is protected by worldwide copyright laws and treaty
14 # provisions. No part of the Material may be used, copied, reproduced,
15 # modified, published, uploaded, posted, transmitted, distributed or disclosed
16 # in any way without Intel's prior express written permission. No license under
17 # any patent, copyright or other intellectual property rights in the Material
18 # is granted to or conferred upon you, either expressly, by implication,
19 # inducement, estoppel or otherwise. Any license under such intellectual
20 # property rights must be express and approved by Intel in writing.
21 #
22 # Unless otherwise agreed by Intel in writing, you may not remove or alter this
23 # notice or any other notice embedded in Materials by Intel or Intel's
24 # suppliers or licensors in any way.
25 #
26 #
27 # If this software was obtained under the Apache License, Version 2.0 (the
28 # "License"), the following terms apply:
29 #
30 # You may not use this file except in compliance with the License. You may
31 # obtain a copy of the License at http://www.apache.org/licenses/LICENSE-2.0
32 #
33 #
34 # Unless required by applicable law or agreed to in writing, software
35 # distributed under the License is distributed on an "AS IS" BASIS, WITHOUT
36 # WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
37 #
38 # See the License for the specific language governing permissions and
39 # limitations under the License.
40 #===============================================================================
41 
42 
44 
45 import os
46 import sys
47 
48 import numpy as np
49 
50 from daal.data_management import HomogenNumericTable, BlockDescriptor, readOnly
51 
52 utils_folder = os.path.realpath(os.path.abspath(os.path.dirname(os.path.dirname(__file__))))
53 if utils_folder not in sys.path:
54  sys.path.insert(0, utils_folder)
55 from utils import printArray
56 
57 
58 if __name__ == "__main__":
59 
60  print("Homogeneous numeric table example\n")
61 
62  data = np.array([(0.0, 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1),
63  (1.0, 1.1, 1.2, 1.3, 1.4, 1.5, 1.6, 1.7, 1.8, 1.9, 2),
64  (2.0, 2.1, 2.2, 2.3, 2.4, 2.5, 2.6, 2.7, 2.8, 2.9, 3),
65  (3.0, 3.1, 3.2, 3.3, 3.4, 3.5, 3.6, 3.7, 3.8, 3.9, 4),
66  (4.0, 4.1, 4.2, 4.3, 4.4, 4.5, 4.6, 4.7, 4.8, 4.9, 5),
67  (5.0, 5.1, 5.2, 5.3, 5.4, 5.5, 5.6, 5.7, 5.8, 5.9, 1),
68  (6.0, 6.1, 6.2, 6.3, 6.4, 6.5, 6.6, 6.7, 6.8, 6.9, 2),
69  (7.0, 7.1, 7.2, 7.3, 7.4, 7.5, 7.6, 7.7, 7.8, 7.9, 3),
70  (8.0, 8.1, 8.2, 8.3, 8.4, 8.5, 8.6, 8.7, 8.8, 8.9, 4),
71  (9.0, 9.1, 9.2, 9.3, 9.4, 9.5, 9.6, 9.7, 9.8, 9.9, 5),])
72 
73  nObservations = len(data)
74  nFeatures = len(data[0])
75  firstReadRow = 0
76  nRead = 3
77  # Construct AOS numericTable for a data array with nFeatures fields and nObservations elements
78  # Dictionary will be initialized with type information from ndarray
79  dataTable = HomogenNumericTable(data)
80  block = BlockDescriptor()
81  num_cols = block.getNumberOfColumns()
82  dataTable.getBlockOfRows(firstReadRow, nRead, readOnly, block)
83  print("%s rows are read" % (block.getNumberOfRows()))
84  printArray(
85  block.getArray(), nFeatures, block.getNumberOfRows(), 11,
86  "Print 3 rows from homogeneous data array as double:"
87  )
88  dataTable.releaseBlockOfRows(block)
89 
90  readFeatureIdx = 2
91  dataTable.getBlockOfColumnValues(readFeatureIdx, firstReadRow, nObservations, readOnly, block)
92  printArray(block.getArray(), 1, 10, 1, "Print the third feature of homogeneous data:")
93  dataTable.releaseBlockOfColumnValues(block)
94 
95  data[0][0] = 999
96  dataFromNumericTable = dataTable.getArray()
97  printArray(dataFromNumericTable, nFeatures, nObservations, 11, "Data from getArray:")
98 
99  newData = np.array([(1.0, 2.0),
100  (3.0, 4.0),
101  (5.0, 6.0),])
102 
103  nNewVectors = len(newData)
104  nNewFeatures = len(newData[0])
105 
106  # Set new data to HomogenNumericTable. It mush have the same type as the numeric table.
107  dataTable = HomogenNumericTable(newData)
108 
109  # Set a new number of columns and rows
110  dataTable.setNumberOfColumns(nNewFeatures)
111  dataTable.setNumberOfRows(nNewVectors)
112 
113  # Ensure the data has changed
114  readFeatureIdx = 1
115  dataTable.getBlockOfColumnValues(readFeatureIdx, firstReadRow, nNewVectors, readOnly, block)
116  printArray(block.getArray(), 1, 3, 1, "Print the second feature of new data:")
117  dataTable.releaseBlockOfColumnValues(block)

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