Coverage for python/lsst/meas/astrom/matcher_probabilistic.py: 27%
205 statements
« prev ^ index » next coverage.py v6.4.4, created at 2022-09-20 02:41 -0700
« prev ^ index » next coverage.py v6.4.4, created at 2022-09-20 02:41 -0700
1# This file is part of meas_astrom.
2#
3# Developed for the LSST Data Management System.
4# This product includes software developed by the LSST Project
5# (https://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 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 GNU General Public License
20# along with this program. If not, see <https://www.gnu.org/licenses/>.
22__all__ = ['ConvertCatalogCoordinatesConfig', 'MatchProbabilisticConfig', 'MatcherProbabilistic']
24import lsst.pex.config as pexConfig
26from dataclasses import dataclass
27import logging
28import numpy as np
29import pandas as pd
30from scipy.spatial import cKDTree
31import time
32from typing import Callable, Set
34logger_default = logging.getLogger(__name__)
37def _mul_column(column: np.array, value: float):
38 if value is not None and value != 1:
39 column *= value
40 return column
43def _radec_to_xyz(ra, dec):
44 """Convert input ra/dec coordinates to spherical unit vectors.
46 Parameters
47 ----------
48 ra, dec: `numpy.ndarray`
49 Arrays of right ascension/declination in degrees.
51 Returns
52 -------
53 vectors : `numpy.ndarray`, (N, 3)
54 Output unit vectors.
55 """
56 if ra.size != dec.size:
57 raise ValueError('ra and dec must be same size')
58 ras = np.radians(ra)
59 decs = np.radians(dec)
60 vectors = np.empty((ras.size, 3))
62 sin_dec = np.sin(np.pi / 2 - decs)
63 vectors[:, 0] = sin_dec * np.cos(ras)
64 vectors[:, 1] = sin_dec * np.sin(ras)
65 vectors[:, 2] = np.cos(np.pi / 2 - decs)
67 return vectors
70@dataclass
71class CatalogExtras:
72 """Store frequently-reference (meta)data relevant for matching a catalog.
74 Parameters
75 ----------
76 catalog : `pandas.DataFrame`
77 A pandas catalog to store extra information for.
78 select : `numpy.array`
79 A numpy boolean array of the same length as catalog to be used for
80 target selection.
81 """
82 n: int
83 indices: np.array
84 select: np.array
86 coordinate_factor: float = None
88 def __init__(self, catalog: pd.DataFrame, select: np.array = None, coordinate_factor: float = None):
89 self.n = len(catalog)
90 self.select = np.ones(self.n, dtype=bool) if select is None else select
91 self.indices = np.flatnonzero(select) if select is not None else np.arange(self.n)
92 self.coordinate_factor = coordinate_factor
95@dataclass(frozen=True)
96class ComparableCatalog:
97 """A catalog with sources with coordinate columns in some standard format/units.
99 catalog : `pandas.DataFrame`
100 A catalog with comparable coordinate columns.
101 column_coord1 : `str`
102 The first spatial coordinate column name.
103 column_coord2 : `str`
104 The second spatial coordinate column name.
105 coord1 : `numpy.array`
106 The first spatial coordinate values.
107 coord2 : `numpy.array`
108 The second spatial coordinate values.
109 extras : `CatalogExtras`
110 Extra cached (meta)data for the `catalog`.
111 """
112 catalog: pd.DataFrame
113 column_coord1: str
114 column_coord2: str
115 coord1: np.array
116 coord2: np.array
117 extras: CatalogExtras
120class ConvertCatalogCoordinatesConfig(pexConfig.Config):
121 """Configuration for the MatchProbabilistic matcher.
122 """
123 column_ref_coord1 = pexConfig.Field(
124 dtype=str,
125 default='ra',
126 doc='The reference table column for the first spatial coordinate (usually x or ra).',
127 )
128 column_ref_coord2 = pexConfig.Field(
129 dtype=str,
130 default='dec',
131 doc='The reference table column for the second spatial coordinate (usually y or dec).'
132 'Units must match column_ref_coord1.',
133 )
134 column_target_coord1 = pexConfig.Field(
135 dtype=str,
136 default='coord_ra',
137 doc='The target table column for the first spatial coordinate (usually x or ra).'
138 'Units must match column_ref_coord1.',
139 )
140 column_target_coord2 = pexConfig.Field(
141 dtype=str,
142 default='coord_dec',
143 doc='The target table column for the second spatial coordinate (usually y or dec).'
144 'Units must match column_ref_coord2.',
145 )
146 coords_spherical = pexConfig.Field(
147 dtype=bool,
148 default=True,
149 doc='Whether column_*_coord[12] are spherical coordinates (ra/dec) or not (pixel x/y)',
150 )
151 coords_ref_factor = pexConfig.Field(
152 dtype=float,
153 default=1.0,
154 doc='Multiplicative factor for reference catalog coordinates.'
155 'If coords_spherical is true, this must be the number of degrees per unit increment of '
156 'column_ref_coord[12]. Otherwise, it must convert the coordinate to the same units'
157 ' as the target coordinates.',
158 )
159 coords_target_factor = pexConfig.Field(
160 dtype=float,
161 default=1.0,
162 doc='Multiplicative factor for target catalog coordinates.'
163 'If coords_spherical is true, this must be the number of degrees per unit increment of '
164 'column_target_coord[12]. Otherwise, it must convert the coordinate to the same units'
165 ' as the reference coordinates.',
166 )
167 coords_ref_to_convert = pexConfig.DictField( 167 ↛ exitline 167 didn't jump to the function exit
168 default=None,
169 optional=True,
170 keytype=str,
171 itemtype=str,
172 dictCheck=lambda x: len(x) == 2,
173 doc='Dict mapping sky coordinate columns to be converted to pixel columns',
174 )
175 mag_zeropoint_ref = pexConfig.Field(
176 dtype=float,
177 default=31.4,
178 doc='Magnitude zeropoint for reference catalog.',
179 )
181 def format_catalogs(
182 self,
183 catalog_ref: pd.DataFrame,
184 catalog_target: pd.DataFrame,
185 select_ref: np.array = None,
186 select_target: np.array = None,
187 radec_to_xy_func: Callable = None,
188 return_converted_columns: bool = False,
189 **kwargs,
190 ):
191 """Format matched catalogs that may require coordinate conversions.
193 Parameters
194 ----------
195 catalog_ref : `pandas.DataFrame`
196 A reference catalog for comparison to `catalog_target`.
197 catalog_target : `pandas.DataFrame`
198 A target catalog with measurements for comparison to `catalog_ref`.
199 select_ref : `numpy.ndarray`, (Nref,)
200 A boolean array of len `catalog_ref`, True for valid match candidates.
201 select_target : `numpy.ndarray`, (Ntarget,)
202 A boolean array of len `catalog_target`, True for valid match candidates.
203 radec_to_xy_func : `typing.Callable`
204 Function taking equal-length ra, dec arrays and returning an ndarray of
205 - ``x``: current parameter (`float`).
206 - ``extra_args``: additional arguments (`dict`).
207 return_converted_columns : `bool`
208 Whether to return converted columns in the `coord1` and `coord2`
209 attributes, rather than keep the original values.
210 kwargs
212 Returns
213 -------
214 compcat_ref, compcat_target : `ComparableCatalog`
215 Comparable catalogs corresponding to the input reference and target.
217 """
218 convert_ref = self.coords_ref_to_convert
219 if convert_ref and not callable(radec_to_xy_func):
220 raise TypeError('radec_to_xy_func must be callable if converting ref coords')
222 # Set up objects with frequently-used attributes like selection bool array
223 extras_ref, extras_target = (
224 CatalogExtras(catalog, select=select, coordinate_factor=coord_factor)
225 for catalog, select, coord_factor in zip(
226 (catalog_ref, catalog_target),
227 (select_ref, select_target),
228 (self.coords_ref_factor, self.coords_target_factor),
229 )
230 )
232 compcats = []
234 # Retrieve coordinates and multiply them by scaling factors
235 for catalog, extras, (column1, column2), convert in (
236 (catalog_ref, extras_ref, (self.column_ref_coord1, self.column_ref_coord2), convert_ref),
237 (catalog_target, extras_target, (self.column_target_coord1, self.column_target_coord2), False),
238 ):
239 coord1, coord2 = (
240 _mul_column(catalog[column], extras.coordinate_factor)
241 for column in (column1, column2)
242 )
243 if convert:
244 xy_ref = radec_to_xy_func(coord1, coord2, self.coords_ref_factor, **kwargs)
245 for idx_coord, column_out in enumerate(self.coords_ref_to_convert.values()):
246 coord = np.array([xy[idx_coord] for xy in xy_ref])
247 catalog[column_out] = coord
248 if convert_ref and return_converted_columns:
249 column1, column2 = self.coords_ref_to_convert.values()
250 coord1, coord2 = catalog[column1], catalog[column2]
251 if isinstance(coord1, pd.Series):
252 coord1 = coord1.values
253 if isinstance(coord2, pd.Series):
254 coord2 = coord2.values
256 compcats.append(ComparableCatalog(
257 catalog=catalog, column_coord1=column1, column_coord2=column2,
258 coord1=coord1, coord2=coord2, extras=extras,
259 ))
261 return tuple(compcats)
264class MatchProbabilisticConfig(pexConfig.Config):
265 """Configuration for the MatchProbabilistic matcher.
266 """
267 column_ref_order = pexConfig.Field(
268 dtype=str,
269 default=None,
270 optional=True,
271 doc="Name of column in reference catalog specifying order for matching."
272 " Derived from columns_ref_flux if not set.",
273 )
275 @property
276 def columns_in_ref(self) -> Set[str]:
277 columns_all = [
278 self.coord_format.column_ref_coord1,
279 self.coord_format.column_ref_coord2,
280 ]
281 for columns in (
282 self.columns_ref_flux,
283 self.columns_ref_meas,
284 self.columns_ref_copy,
285 ):
286 columns_all.extend(columns)
288 return set(columns_all)
290 @property
291 def columns_in_target(self) -> Set[str]:
292 columns_all = [
293 self.coord_format.column_target_coord1,
294 self.coord_format.column_target_coord2,
295 ]
296 for columns in (
297 self.columns_target_meas,
298 self.columns_target_err,
299 self.columns_target_select_false,
300 self.columns_target_select_true,
301 self.columns_target_copy,
302 ):
303 columns_all.extend(columns)
304 return set(columns_all)
306 columns_ref_copy = pexConfig.ListField( 306 ↛ exitline 306 didn't jump to the function exit
307 dtype=str,
308 default=[],
309 listCheck=lambda x: len(set(x)) == len(x),
310 optional=True,
311 doc='Reference table columns to copy unchanged into both match tables',
312 )
313 columns_ref_flux = pexConfig.ListField( 313 ↛ exitline 313 didn't jump to the function exit
314 dtype=str,
315 default=[],
316 listCheck=lambda x: len(set(x)) == len(x),
317 optional=True,
318 doc="List of reference flux columns to nansum total magnitudes from if column_order is None",
319 )
320 columns_ref_meas = pexConfig.ListField(
321 dtype=str,
322 doc='The reference table columns to compute match likelihoods from '
323 '(usually centroids and fluxes/magnitudes)',
324 )
325 columns_target_copy = pexConfig.ListField( 325 ↛ exitline 325 didn't jump to the function exit
326 dtype=str,
327 default=[],
328 listCheck=lambda x: len(set(x)) == len(x),
329 optional=True,
330 doc='Target table columns to copy unchanged into both match tables',
331 )
332 columns_target_meas = pexConfig.ListField(
333 dtype=str,
334 doc='Target table columns with measurements corresponding to columns_ref_meas',
335 )
336 columns_target_err = pexConfig.ListField(
337 dtype=str,
338 doc='Target table columns with standard errors (sigma) corresponding to columns_ref_meas',
339 )
340 columns_target_select_true = pexConfig.ListField(
341 dtype=str,
342 default=('detect_isPrimary',),
343 doc='Target table columns to require to be True for selecting sources',
344 )
345 columns_target_select_false = pexConfig.ListField(
346 dtype=str,
347 default=('merge_peak_sky',),
348 doc='Target table columns to require to be False for selecting sources',
349 )
350 coord_format = pexConfig.ConfigField(
351 dtype=ConvertCatalogCoordinatesConfig,
352 doc="Configuration for coordinate conversion",
353 )
354 mag_brightest_ref = pexConfig.Field(
355 dtype=float,
356 default=-np.inf,
357 doc='Bright magnitude cutoff for selecting reference sources to match.'
358 ' Ignored if column_ref_order is None.'
359 )
360 mag_faintest_ref = pexConfig.Field(
361 dtype=float,
362 default=np.Inf,
363 doc='Faint magnitude cutoff for selecting reference sources to match.'
364 ' Ignored if column_ref_order is None.'
365 )
366 match_dist_max = pexConfig.Field(
367 dtype=float,
368 default=0.5,
369 doc='Maximum match distance. Units must be arcseconds if coords_spherical, '
370 'or else match those of column_*_coord[12] multiplied by coords_*_factor.',
371 )
372 match_n_max = pexConfig.Field(
373 dtype=int,
374 default=10,
375 optional=True,
376 doc='Maximum number of spatial matches to consider (in ascending distance order).',
377 )
378 match_n_finite_min = pexConfig.Field(
379 dtype=int,
380 default=3,
381 optional=True,
382 doc='Minimum number of columns with a finite value to measure match likelihood',
383 )
384 order_ascending = pexConfig.Field(
385 dtype=bool,
386 default=False,
387 optional=True,
388 doc='Whether to order reference match candidates in ascending order of column_ref_order '
389 '(should be False if the column is a flux and True if it is a magnitude.',
390 )
393def default_value(dtype):
394 if dtype == str:
395 return ''
396 elif dtype == np.signedinteger:
397 return np.Inf
398 elif dtype == np.unsignedinteger:
399 return -np.Inf
400 return None
403class MatcherProbabilistic:
404 """A probabilistic, greedy catalog matcher.
406 Parameters
407 ----------
408 config: `MatchProbabilisticConfig`
409 A configuration instance.
410 """
411 config: MatchProbabilisticConfig
413 def __init__(
414 self,
415 config: MatchProbabilisticConfig,
416 ):
417 self.config = config
419 def match(
420 self,
421 catalog_ref: pd.DataFrame,
422 catalog_target: pd.DataFrame,
423 select_ref: np.array = None,
424 select_target: np.array = None,
425 logger: logging.Logger = None,
426 logging_n_rows: int = None,
427 **kwargs
428 ):
429 """Match catalogs.
431 Parameters
432 ----------
433 catalog_ref : `pandas.DataFrame`
434 A reference catalog to match in order of a given column (i.e. greedily).
435 catalog_target : `pandas.DataFrame`
436 A target catalog for matching sources from `catalog_ref`. Must contain measurements with errors.
437 select_ref : `numpy.array`
438 A boolean array of the same length as `catalog_ref` selecting the sources that can be matched.
439 select_target : `numpy.array`
440 A boolean array of the same length as `catalog_target` selecting the sources that can be matched.
441 logger : `logging.Logger`
442 A Logger for logging.
443 logging_n_rows : `int`
444 The number of sources to match before printing a log message.
445 kwargs
446 Additional keyword arguments to pass to `format_catalogs`.
448 Returns
449 -------
450 catalog_out_ref : `pandas.DataFrame`
451 A catalog of identical length to `catalog_ref`, containing match information for rows selected by
452 `select_ref` (including the matching row index in `catalog_target`).
453 catalog_out_target : `pandas.DataFrame`
454 A catalog of identical length to `catalog_target`, containing the indices of matching rows in
455 `catalog_ref`.
456 exceptions : `dict` [`int`, `Exception`]
457 A dictionary keyed by `catalog_target` row number of the first exception caught when matching.
458 """
459 if logger is None:
460 logger = logger_default
462 config = self.config
464 # Transform any coordinates, if required
465 # Note: The returned objects contain the original catalogs, as well as
466 # transformed coordinates, and the selection of sources for matching.
467 # These might be identical to the arrays passed as kwargs, but that
468 # depends on config settings.
469 # For the rest of this function, the selection arrays will be used,
470 # but the indices of the original, unfiltered catalog will also be
471 # output, so some further indexing steps are needed.
472 ref, target = config.coord_format.format_catalogs(
473 catalog_ref=catalog_ref, catalog_target=catalog_target,
474 select_ref=select_ref, select_target=select_target,
475 **kwargs
476 )
478 # If no order is specified, take nansum of all flux columns for a 'total flux'
479 # Note: it won't actually be a total flux if bands overlap significantly
480 # (or it might define a filter with >100% efficiency
481 # Also, this is done on the original dataframe as it's harder to accomplish
482 # just with a recarray
483 column_order = (
484 catalog_ref.loc[ref.extras.select, config.column_ref_order]
485 if config.column_ref_order is not None else
486 np.nansum(catalog_ref.loc[ref.extras.select, config.columns_ref_flux], axis=1)
487 )
488 order = np.argsort(column_order if config.order_ascending else -column_order)
490 n_ref_select = len(ref.extras.indices)
492 match_dist_max = config.match_dist_max
493 coords_spherical = config.coord_format.coords_spherical
494 if coords_spherical:
495 match_dist_max = np.radians(match_dist_max / 3600.)
497 # Convert ra/dec sky coordinates to spherical vectors for accurate distances
498 func_convert = _radec_to_xyz if coords_spherical else np.vstack
499 vec_ref, vec_target = (
500 func_convert(cat.coord1[cat.extras.select], cat.coord2[cat.extras.select])
501 for cat in (ref, target)
502 )
504 # Generate K-d tree to compute distances
505 logger.info('Generating cKDTree with match_n_max=%d', config.match_n_max)
506 tree_obj = cKDTree(vec_target)
508 scores, idxs_target_select = tree_obj.query(
509 vec_ref,
510 distance_upper_bound=match_dist_max,
511 k=config.match_n_max,
512 )
514 n_target_select = len(target.extras.indices)
515 n_matches = np.sum(idxs_target_select != n_target_select, axis=1)
516 n_matched_max = np.sum(n_matches == config.match_n_max)
517 if n_matched_max > 0:
518 logger.warning(
519 '%d/%d (%.2f%%) selected true objects have n_matches=n_match_max(%d)',
520 n_matched_max, n_ref_select, 100.*n_matched_max/n_ref_select, config.match_n_max
521 )
523 # Pre-allocate outputs
524 target_row_match = np.full(target.extras.n, np.nan, dtype=np.int64)
525 ref_candidate_match = np.zeros(ref.extras.n, dtype=bool)
526 ref_row_match = np.full(ref.extras.n, np.nan, dtype=np.int64)
527 ref_match_count = np.zeros(ref.extras.n, dtype=np.int32)
528 ref_match_meas_finite = np.zeros(ref.extras.n, dtype=np.int32)
529 ref_chisq = np.full(ref.extras.n, np.nan, dtype=float)
531 # Need the original reference row indices for output
532 idx_orig_ref, idx_orig_target = (np.argwhere(cat.extras.select) for cat in (ref, target))
534 # Retrieve required columns, including any converted ones (default to original column name)
535 columns_convert = config.coord_format.coords_ref_to_convert
536 if columns_convert is None:
537 columns_convert = {}
538 data_ref = ref.catalog[
539 [columns_convert.get(column, column) for column in config.columns_ref_meas]
540 ].iloc[ref.extras.indices[order]]
541 data_target = target.catalog[config.columns_target_meas][target.extras.select]
542 errors_target = target.catalog[config.columns_target_err][target.extras.select]
544 exceptions = {}
545 # The kdTree uses len(inputs) as a sentinel value for no match
546 matched_target = {n_target_select, }
548 t_begin = time.process_time()
550 logger.info('Matching n_indices=%d/%d', len(order), len(ref.catalog))
551 for index_n, index_row_select in enumerate(order):
552 index_row = idx_orig_ref[index_row_select]
553 ref_candidate_match[index_row] = True
554 found = idxs_target_select[index_row_select, :]
555 # Select match candidates from nearby sources not already matched
556 # Note: set lookup is apparently fast enough that this is a few percent faster than:
557 # found = [x for x in found[found != n_target_select] if x not in matched_target]
558 # ... at least for ~1M sources
559 found = [x for x in found if x not in matched_target]
560 n_found = len(found)
561 if n_found > 0:
562 # This is an ndarray of n_found rows x len(data_ref/target) columns
563 chi = (
564 (data_target.iloc[found].values - data_ref.iloc[index_n].values)
565 / errors_target.iloc[found].values
566 )
567 finite = np.isfinite(chi)
568 n_finite = np.sum(finite, axis=1)
569 # Require some number of finite chi_sq to match
570 chisq_good = n_finite >= config.match_n_finite_min
571 if np.any(chisq_good):
572 try:
573 chisq_sum = np.zeros(n_found, dtype=float)
574 chisq_sum[chisq_good] = np.nansum(chi[chisq_good, :] ** 2, axis=1)
575 idx_chisq_min = np.nanargmin(chisq_sum / n_finite)
576 ref_match_meas_finite[index_row] = n_finite[idx_chisq_min]
577 ref_match_count[index_row] = len(chisq_good)
578 ref_chisq[index_row] = chisq_sum[idx_chisq_min]
579 idx_match_select = found[idx_chisq_min]
580 row_target = target.extras.indices[idx_match_select]
581 ref_row_match[index_row] = row_target
583 target_row_match[row_target] = index_row
584 matched_target.add(idx_match_select)
585 except Exception as error:
586 # Can't foresee any exceptions, but they shouldn't prevent
587 # matching subsequent sources
588 exceptions[index_row] = error
590 if logging_n_rows and ((index_n + 1) % logging_n_rows == 0):
591 t_elapsed = time.process_time() - t_begin
592 logger.info(
593 'Processed %d/%d in %.2fs at sort value=%.3f',
594 index_n + 1, n_ref_select, t_elapsed, column_order[order[index_n]],
595 )
597 data_ref = {
598 'match_candidate': ref_candidate_match,
599 'match_row': ref_row_match,
600 'match_count': ref_match_count,
601 'match_chisq': ref_chisq,
602 'match_n_chisq_finite': ref_match_meas_finite,
603 }
604 data_target = {
605 'match_candidate': target.extras.select if target.extras.select is not None else (
606 np.ones(target.extras.n, dtype=bool)),
607 'match_row': target_row_match,
608 }
610 for (columns, out_original, out_matched, in_original, in_matched, matches) in (
611 (
612 self.config.columns_ref_copy,
613 data_ref,
614 data_target,
615 ref,
616 target,
617 target_row_match,
618 ),
619 (
620 self.config.columns_target_copy,
621 data_target,
622 data_ref,
623 target,
624 ref,
625 ref_row_match,
626 ),
627 ):
628 matched = matches >= 0
629 idx_matched = matches[matched]
631 for column in columns:
632 values = in_original.catalog[column]
633 out_original[column] = values
634 dtype = in_original.catalog[column].dtype
635 if dtype == object:
636 types = list(set((type(x) for x in values)))
637 if len(types) != 1:
638 raise RuntimeError(f'Column {column} dtype={dtype} has multiple types={types}')
639 dtype = types[0]
641 column_match = np.full(in_matched.extras.n, default_value(dtype), dtype=dtype)
642 column_match[matched] = in_original.catalog[column][idx_matched]
643 out_matched[f'match_{column}'] = column_match
645 catalog_out_ref = pd.DataFrame(data_ref)
646 catalog_out_target = pd.DataFrame(data_target)
648 return catalog_out_ref, catalog_out_target, exceptions