Coverage for python/lsst/daf/butler/delegates/arrownumpydict.py: 94%

24 statements  

« prev     ^ index     » next       coverage.py v7.4.1, created at 2024-02-13 10:56 +0000

1# This file is part of daf_butler. 

2# 

3# Developed for the LSST Data Management System. 

4# This product includes software developed by the LSST Project 

5# (http://www.lsst.org). 

6# See the COPYRIGHT file at the top-level directory of this distribution 

7# for details of code ownership. 

8# 

9# This software is dual licensed under the GNU General Public License and also 

10# under a 3-clause BSD license. Recipients may choose which of these licenses 

11# to use; please see the files gpl-3.0.txt and/or bsd_license.txt, 

12# respectively. If you choose the GPL option then the following text applies 

13# (but note that there is still no warranty even if you opt for BSD instead): 

14# 

15# This program is free software: you can redistribute it and/or modify 

16# it under the terms of the GNU General Public License as published by 

17# the Free Software Foundation, either version 3 of the License, or 

18# (at your option) any later version. 

19# 

20# This program is distributed in the hope that it will be useful, 

21# but WITHOUT ANY WARRANTY; without even the implied warranty of 

22# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 

23# GNU General Public License for more details. 

24# 

25# You should have received a copy of the GNU General Public License 

26# along with this program. If not, see <http://www.gnu.org/licenses/>. 

27 

28"""Support for reading dictionaries of numpy arrays with the Arrow 

29formatter. 

30""" 

31from __future__ import annotations 

32 

33from typing import Any 

34 

35import numpy as np 

36from lsst.daf.butler.formatters.parquet import ArrowNumpySchema, _numpy_dict_to_dtype 

37from lsst.utils.introspection import get_full_type_name 

38 

39from .arrowtable import ArrowTableDelegate 

40 

41__all__ = ["ArrowNumpyDictDelegate"] 

42 

43 

44class ArrowNumpyDictDelegate(ArrowTableDelegate): 

45 """Delegate that understands the ``ArrowNumpyDict`` storage class.""" 

46 

47 _datasetType = dict 

48 

49 def getComponent(self, composite: dict[str, np.ndarray], componentName: str) -> Any: 

50 """Get a component from a dict of numpy arrays stored via 

51 ArrowNumpyDict. 

52 

53 Parameters 

54 ---------- 

55 composite : `~numpy.ndarray` 

56 Numpy table to access component. 

57 componentName : `str` 

58 Name of component to retrieve. 

59 

60 Returns 

61 ------- 

62 component : `object` 

63 The component. 

64 

65 Raises 

66 ------ 

67 AttributeError 

68 The component can not be found. 

69 """ 

70 match componentName: 

71 case "columns": 

72 return list(composite.keys()) 

73 case "schema": 

74 dtype, _ = _numpy_dict_to_dtype(composite) 

75 return ArrowNumpySchema(dtype) 

76 case "rowcount": 76 ↛ 79line 76 didn't jump to line 79, because the pattern on line 76 never matched

77 return len(composite[list(composite.keys())[0]]) 

78 

79 raise AttributeError( 

80 f"Do not know how to retrieve component {componentName} from {get_full_type_name(composite)}" 

81 ) 

82 

83 def _getColumns(self, inMemoryDataset: dict[str, np.ndarray]) -> list[str]: 

84 return list(inMemoryDataset.keys()) 

85 

86 def _selectColumns( 

87 self, inMemoryDataset: dict[str, np.ndarray], columns: list[str] 

88 ) -> dict[str, np.ndarray]: 

89 return {column: inMemoryDataset[column] for column in columns}