Coverage for python/lsst/meas/algorithms/readTextCatalogTask.py: 40%
30 statements
« prev ^ index » next coverage.py v7.2.7, created at 2023-07-27 09:28 +0000
« prev ^ index » next coverage.py v7.2.7, created at 2023-07-27 09:28 +0000
1#
2# LSST Data Management System
3#
4# Copyright 2008-2017 AURA/LSST.
5#
6# This product includes software developed by the
7# LSST Project (http://www.lsst.org/).
8#
9# This program is free software: you can redistribute it and/or modify
10# it under the terms of the GNU General Public License as published by
11# the Free Software Foundation, either version 3 of the License, or
12# (at your option) any later version.
13#
14# This program is distributed in the hope that it will be useful,
15# but WITHOUT ANY WARRANTY; without even the implied warranty of
16# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
17# GNU General Public License for more details.
18#
19# You should have received a copy of the LSST License Statement and
20# the GNU General Public License along with this program. If not,
21# see <https://www.lsstcorp.org/LegalNotices/>.
22#
24__all__ = ["ReadTextCatalogConfig", "ReadTextCatalogTask"]
26import numpy as np
27from astropy.table import Table
29import lsst.pex.config as pexConfig
30import lsst.pipe.base as pipeBase
33class ReadTextCatalogConfig(pexConfig.Config):
34 header_lines = pexConfig.Field(
35 dtype=int,
36 default=0,
37 doc='Number of lines to skip when reading the text reference file.'
38 )
39 colnames = pexConfig.ListField(
40 dtype=str,
41 default=[],
42 doc="An ordered list of column names to use in ingesting the catalog. "
43 "With an empty list, column names will be discovered from the first line "
44 "after the skipped header lines."
45 )
46 delimiter = pexConfig.Field(
47 dtype=str,
48 default=',',
49 doc='Delimiter to use when reading text reference files. Comma is default.'
50 )
51 format = pexConfig.Field(
52 dtype=str,
53 default='csv',
54 doc=("Format of files to read, from the astropy.table I/O list here:"
55 "http://docs.astropy.org/en/stable/io/unified.html#built-in-table-readers-writers")
56 )
57 fill_values = pexConfig.ListField(
58 dtype=str,
59 default=None,
60 optional=True,
61 doc=("A list giving [<match_string>, <fill_value>], which is used to mask"
62 " the given values in the input file. '0' is suggested for the fill value in order to prevent"
63 " changing the column datatype. The default behavior is to fill empty data with zeros. See "
64 "https://docs.astropy.org/en/stable/io/ascii/read.html#bad-or-missing-values for more details."
65 "Use `replace_missing_floats_with_nan` to change floats to NaN instead of <fill_value>.")
66 )
67 replace_missing_floats_with_nan = pexConfig.Field(
68 dtype=bool,
69 default=False,
70 doc="If True, replace missing data in float columns with NaN instead of zero. If `fill_values` is "
71 "set, this parameter with replace the floats identified as missing by `fill_values`, and the fill"
72 " value from `fill_values` will be overridden with NaN for floats."
73 )
76class ReadTextCatalogTask(pipeBase.Task):
77 """Read an object catalog from a text file
78 """
79 _DefaultName = 'readCatalog'
80 ConfigClass = ReadTextCatalogConfig
82 def run(self, filename):
83 """Read an object catalog from the specified text file
85 Parameters
86 ----------
87 filename : `string`
88 Path to specified text file
90 Returns
91 -------
92 A numpy structured array containing the specified columns
93 """
94 kwargs = {}
95 if self.config.colnames:
96 # Wrap in list() to avoid transferring a pex_config proxy object.
97 kwargs['names'] = list(self.config.colnames)
98 # if we specify the column names, then we need to just ignore the header lines.
99 kwargs['data_start'] = self.config.header_lines
100 else:
101 # if we don't specify column names, start the header at this line.
102 kwargs['header_start'] = self.config.header_lines
104 if self.config.fill_values:
105 kwargs['fill_values'] = [list(self.config.fill_values)]
107 table = Table.read(filename, format=self.config.format,
108 delimiter=self.config.delimiter,
109 **kwargs)
111 # convert to a numpy array for backwards compatibility with other readers
112 arr = np.array(table.as_array())
114 if self.config.replace_missing_floats_with_nan:
115 for column in table.columns:
116 if (table.dtype[column] == np.float32) or (table.dtype[column] == np.float64):
117 arr[column][table.mask[column]] = np.nan
119 return arr