Coverage for python/lsst/ap/association/diaPipe.py: 28%

159 statements  

« prev     ^ index     » next       coverage.py v7.3.2, created at 2023-12-09 13:44 +0000

1# 

2# LSST Data Management System 

3# Copyright 2008-2016 AURA/LSST. 

4# 

5# This product includes software developed by the 

6# LSST Project (http://www.lsst.org/). 

7# 

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

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

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

11# (at your option) any later version. 

12# 

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

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

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

16# GNU General Public License for more details. 

17# 

18# You should have received a copy of the LSST License Statement and 

19# the GNU General Public License along with this program. If not, 

20# see <https://www.lsstcorp.org/LegalNotices/>. 

21# 

22 

23"""PipelineTask for associating DiaSources with previous DiaObjects. 

24 

25Additionally performs forced photometry on the calibrated and difference 

26images at the updated locations of DiaObjects. 

27 

28Currently loads directly from the Apdb rather than pre-loading. 

29""" 

30 

31__all__ = ("DiaPipelineConfig", 

32 "DiaPipelineTask", 

33 "DiaPipelineConnections") 

34 

35import numpy as np 

36import pandas as pd 

37 

38from lsst.daf.base import DateTime 

39import lsst.dax.apdb as daxApdb 

40from lsst.meas.base import DetectorVisitIdGeneratorConfig, DiaObjectCalculationTask 

41import lsst.pex.config as pexConfig 

42import lsst.pipe.base as pipeBase 

43import lsst.pipe.base.connectionTypes as connTypes 

44from lsst.utils.timer import timeMethod 

45 

46from lsst.ap.association import ( 

47 AssociationTask, 

48 DiaForcedSourceTask, 

49 LoadDiaCatalogsTask, 

50 PackageAlertsTask) 

51from lsst.ap.association.ssoAssociation import SolarSystemAssociationTask 

52 

53 

54class DiaPipelineConnections( 

55 pipeBase.PipelineTaskConnections, 

56 dimensions=("instrument", "visit", "detector"), 

57 defaultTemplates={"coaddName": "deep", "fakesType": ""}): 

58 """Butler connections for DiaPipelineTask. 

59 """ 

60 diaSourceTable = connTypes.Input( 

61 doc="Catalog of calibrated DiaSources.", 

62 name="{fakesType}{coaddName}Diff_diaSrcTable", 

63 storageClass="DataFrame", 

64 dimensions=("instrument", "visit", "detector"), 

65 ) 

66 solarSystemObjectTable = connTypes.Input( 

67 doc="Catalog of SolarSolarSystem objects expected to be observable in " 

68 "this detectorVisit.", 

69 name="visitSsObjects", 

70 storageClass="DataFrame", 

71 dimensions=("instrument", "visit"), 

72 ) 

73 diffIm = connTypes.Input( 

74 doc="Difference image on which the DiaSources were detected.", 

75 name="{fakesType}{coaddName}Diff_differenceExp", 

76 storageClass="ExposureF", 

77 dimensions=("instrument", "visit", "detector"), 

78 ) 

79 exposure = connTypes.Input( 

80 doc="Calibrated exposure differenced with a template image during " 

81 "image differencing.", 

82 name="{fakesType}calexp", 

83 storageClass="ExposureF", 

84 dimensions=("instrument", "visit", "detector"), 

85 ) 

86 template = connTypes.Input( 

87 doc="Warped template used to create `subtractedExposure`. Not PSF " 

88 "matched.", 

89 dimensions=("instrument", "visit", "detector"), 

90 storageClass="ExposureF", 

91 name="{fakesType}{coaddName}Diff_templateExp", 

92 ) 

93 apdbMarker = connTypes.Output( 

94 doc="Marker dataset storing the configuration of the Apdb for each " 

95 "visit/detector. Used to signal the completion of the pipeline.", 

96 name="apdb_marker", 

97 storageClass="Config", 

98 dimensions=("instrument", "visit", "detector"), 

99 ) 

100 associatedDiaSources = connTypes.Output( 

101 doc="Optional output storing the DiaSource catalog after matching, " 

102 "calibration, and standardization for insertion into the Apdb.", 

103 name="{fakesType}{coaddName}Diff_assocDiaSrc", 

104 storageClass="DataFrame", 

105 dimensions=("instrument", "visit", "detector"), 

106 ) 

107 diaForcedSources = connTypes.Output( 

108 doc="Optional output storing the forced sources computed at the diaObject positions.", 

109 name="{fakesType}{coaddName}Diff_diaForcedSrc", 

110 storageClass="DataFrame", 

111 dimensions=("instrument", "visit", "detector"), 

112 ) 

113 diaObjects = connTypes.Output( 

114 doc="Optional output storing the updated diaObjects associated to these sources.", 

115 name="{fakesType}{coaddName}Diff_diaObject", 

116 storageClass="DataFrame", 

117 dimensions=("instrument", "visit", "detector"), 

118 ) 

119 longTrailedSources = pipeBase.connectionTypes.Output( 

120 doc="Optional output temporarily storing long trailed diaSources.", 

121 dimensions=("instrument", "visit", "detector"), 

122 storageClass="DataFrame", 

123 name="{fakesType}{coaddName}Diff_longTrailedSrc", 

124 ) 

125 

126 def __init__(self, *, config=None): 

127 super().__init__(config=config) 

128 

129 if not config.doWriteAssociatedSources: 

130 self.outputs.remove("associatedDiaSources") 

131 self.outputs.remove("diaForcedSources") 

132 self.outputs.remove("diaObjects") 

133 if not config.doSolarSystemAssociation: 

134 self.inputs.remove("solarSystemObjectTable") 

135 if not config.associator.doTrailedSourceFilter: 

136 self.outputs.remove("longTrailedSources") 

137 

138 def adjustQuantum(self, inputs, outputs, label, dataId): 

139 """Override to make adjustments to `lsst.daf.butler.DatasetRef` objects 

140 in the `lsst.daf.butler.core.Quantum` during the graph generation stage 

141 of the activator. 

142 

143 This implementation checks to make sure that the filters in the dataset 

144 are compatible with AP processing as set by the Apdb/DPDD schema. 

145 

146 Parameters 

147 ---------- 

148 inputs : `dict` 

149 Dictionary whose keys are an input (regular or prerequisite) 

150 connection name and whose values are a tuple of the connection 

151 instance and a collection of associated `DatasetRef` objects. 

152 The exact type of the nested collections is unspecified; it can be 

153 assumed to be multi-pass iterable and support `len` and ``in``, but 

154 it should not be mutated in place. In contrast, the outer 

155 dictionaries are guaranteed to be temporary copies that are true 

156 `dict` instances, and hence may be modified and even returned; this 

157 is especially useful for delegating to `super` (see notes below). 

158 outputs : `dict` 

159 Dict of output datasets, with the same structure as ``inputs``. 

160 label : `str` 

161 Label for this task in the pipeline (should be used in all 

162 diagnostic messages). 

163 data_id : `lsst.daf.butler.DataCoordinate` 

164 Data ID for this quantum in the pipeline (should be used in all 

165 diagnostic messages). 

166 

167 Returns 

168 ------- 

169 adjusted_inputs : `dict` 

170 Dict of the same form as ``inputs`` with updated containers of 

171 input `DatasetRef` objects. Connections that are not changed 

172 should not be returned at all. Datasets may only be removed, not 

173 added. Nested collections may be of any multi-pass iterable type, 

174 and the order of iteration will set the order of iteration within 

175 `PipelineTask.runQuantum`. 

176 adjusted_outputs : `dict` 

177 Dict of updated output datasets, with the same structure and 

178 interpretation as ``adjusted_inputs``. 

179 

180 Raises 

181 ------ 

182 ScalarError 

183 Raised if any `Input` or `PrerequisiteInput` connection has 

184 ``multiple`` set to `False`, but multiple datasets. 

185 NoWorkFound 

186 Raised to indicate that this quantum should not be run; not enough 

187 datasets were found for a regular `Input` connection, and the 

188 quantum should be pruned or skipped. 

189 FileNotFoundError 

190 Raised to cause QuantumGraph generation to fail (with the message 

191 included in this exception); not enough datasets were found for a 

192 `PrerequisiteInput` connection. 

193 """ 

194 _, refs = inputs["diffIm"] 

195 for ref in refs: 

196 if ref.dataId["band"] not in self.config.validBands: 

197 raise ValueError( 

198 f"Requested '{ref.dataId['band']}' not in " 

199 "DiaPipelineConfig.validBands. To process bands not in " 

200 "the standard Rubin set (ugrizy) you must add the band to " 

201 "the validBands list in DiaPipelineConfig and add the " 

202 "appropriate columns to the Apdb schema.") 

203 return super().adjustQuantum(inputs, outputs, label, dataId) 

204 

205 

206class DiaPipelineConfig(pipeBase.PipelineTaskConfig, 

207 pipelineConnections=DiaPipelineConnections): 

208 """Config for DiaPipelineTask. 

209 """ 

210 coaddName = pexConfig.Field( 

211 doc="coadd name: typically one of deep, goodSeeing, or dcr", 

212 dtype=str, 

213 default="deep", 

214 ) 

215 apdb = daxApdb.ApdbSql.makeField( 

216 doc="Database connection for storing associated DiaSources and " 

217 "DiaObjects. Must already be initialized.", 

218 ) 

219 validBands = pexConfig.ListField( 

220 dtype=str, 

221 default=["u", "g", "r", "i", "z", "y"], 

222 doc="List of bands that are valid for AP processing. To process a " 

223 "band not on this list, the appropriate band specific columns " 

224 "must be added to the Apdb schema in dax_apdb.", 

225 ) 

226 diaCatalogLoader = pexConfig.ConfigurableField( 

227 target=LoadDiaCatalogsTask, 

228 doc="Task to load DiaObjects and DiaSources from the Apdb.", 

229 ) 

230 associator = pexConfig.ConfigurableField( 

231 target=AssociationTask, 

232 doc="Task used to associate DiaSources with DiaObjects.", 

233 ) 

234 doSolarSystemAssociation = pexConfig.Field( 

235 dtype=bool, 

236 default=False, 

237 doc="Process SolarSystem objects through the pipeline.", 

238 ) 

239 solarSystemAssociator = pexConfig.ConfigurableField( 

240 target=SolarSystemAssociationTask, 

241 doc="Task used to associate DiaSources with SolarSystemObjects.", 

242 ) 

243 diaCalculation = pexConfig.ConfigurableField( 

244 target=DiaObjectCalculationTask, 

245 doc="Task to compute summary statistics for DiaObjects.", 

246 ) 

247 diaForcedSource = pexConfig.ConfigurableField( 

248 target=DiaForcedSourceTask, 

249 doc="Task used for force photometer DiaObject locations in direct and " 

250 "difference images.", 

251 ) 

252 alertPackager = pexConfig.ConfigurableField( 

253 target=PackageAlertsTask, 

254 doc="Subtask for packaging Ap data into alerts.", 

255 ) 

256 doPackageAlerts = pexConfig.Field( 

257 dtype=bool, 

258 default=False, 

259 doc="Package Dia-data into serialized alerts for distribution and " 

260 "write them to disk.", 

261 ) 

262 doWriteAssociatedSources = pexConfig.Field( 

263 dtype=bool, 

264 default=False, 

265 doc="Write out associated DiaSources, DiaForcedSources, and DiaObjects, " 

266 "formatted following the Science Data Model.", 

267 ) 

268 imagePixelMargin = pexConfig.RangeField( 

269 dtype=int, 

270 default=10, 

271 min=0, 

272 doc="Pad the image by this many pixels before removing off-image " 

273 "diaObjects for association.", 

274 ) 

275 idGenerator = DetectorVisitIdGeneratorConfig.make_field() 

276 

277 def setDefaults(self): 

278 self.apdb.dia_object_index = "baseline" 

279 self.apdb.dia_object_columns = [] 

280 self.diaCalculation.plugins = ["ap_meanPosition", 

281 "ap_nDiaSources", 

282 "ap_diaObjectFlag", 

283 "ap_meanFlux", 

284 "ap_percentileFlux", 

285 "ap_sigmaFlux", 

286 "ap_chi2Flux", 

287 "ap_madFlux", 

288 "ap_skewFlux", 

289 "ap_minMaxFlux", 

290 "ap_maxSlopeFlux", 

291 "ap_meanErrFlux", 

292 "ap_linearFit", 

293 "ap_stetsonJ", 

294 "ap_meanTotFlux", 

295 "ap_sigmaTotFlux"] 

296 

297 

298class DiaPipelineTask(pipeBase.PipelineTask): 

299 """Task for loading, associating and storing Difference Image Analysis 

300 (DIA) Objects and Sources. 

301 """ 

302 ConfigClass = DiaPipelineConfig 

303 _DefaultName = "diaPipe" 

304 

305 def __init__(self, initInputs=None, **kwargs): 

306 super().__init__(**kwargs) 

307 self.apdb = self.config.apdb.apply() 

308 self.makeSubtask("diaCatalogLoader") 

309 self.makeSubtask("associator") 

310 self.makeSubtask("diaCalculation") 

311 self.makeSubtask("diaForcedSource") 

312 if self.config.doPackageAlerts: 

313 self.makeSubtask("alertPackager") 

314 if self.config.doSolarSystemAssociation: 

315 self.makeSubtask("solarSystemAssociator") 

316 

317 def runQuantum(self, butlerQC, inputRefs, outputRefs): 

318 inputs = butlerQC.get(inputRefs) 

319 inputs["idGenerator"] = self.config.idGenerator.apply(butlerQC.quantum.dataId) 

320 # Need to set ccdExposureIdBits (now deprecated) to None and pass it, 

321 # since there are non-optional positional arguments after it. 

322 inputs["ccdExposureIdBits"] = None 

323 inputs["band"] = butlerQC.quantum.dataId["band"] 

324 if not self.config.doSolarSystemAssociation: 

325 inputs["solarSystemObjectTable"] = None 

326 

327 outputs = self.run(**inputs) 

328 

329 butlerQC.put(outputs, outputRefs) 

330 

331 @timeMethod 

332 def run(self, 

333 diaSourceTable, 

334 solarSystemObjectTable, 

335 diffIm, 

336 exposure, 

337 template, 

338 ccdExposureIdBits, # TODO: remove on DM-38687. 

339 band, 

340 idGenerator=None): 

341 """Process DiaSources and DiaObjects. 

342 

343 Load previous DiaObjects and their DiaSource history. Calibrate the 

344 values in the diaSourceCat. Associate new DiaSources with previous 

345 DiaObjects. Run forced photometry at the updated DiaObject locations. 

346 Store the results in the Alert Production Database (Apdb). 

347 

348 Parameters 

349 ---------- 

350 diaSourceTable : `pandas.DataFrame` 

351 Newly detected DiaSources. 

352 diffIm : `lsst.afw.image.ExposureF` 

353 Difference image exposure in which the sources in ``diaSourceCat`` 

354 were detected. 

355 exposure : `lsst.afw.image.ExposureF` 

356 Calibrated exposure differenced with a template to create 

357 ``diffIm``. 

358 template : `lsst.afw.image.ExposureF` 

359 Template exposure used to create diffIm. 

360 ccdExposureIdBits : `int` 

361 Number of bits used for a unique ``ccdVisitId``. Deprecated in 

362 favor of ``idGenerator``, and ignored if that is present (will be 

363 removed after v26). Pass `None` explicitly to avoid a deprecation 

364 warning (a default is impossible given that later positional 

365 arguments are not defaulted). 

366 band : `str` 

367 The band in which the new DiaSources were detected. 

368 idGenerator : `lsst.meas.base.IdGenerator`, optional 

369 Object that generates source IDs and random number generator seeds. 

370 Will be required after ``ccdExposureIdBits`` is removed. 

371 

372 Returns 

373 ------- 

374 results : `lsst.pipe.base.Struct` 

375 Results struct with components. 

376 

377 - ``apdbMaker`` : Marker dataset to store in the Butler indicating 

378 that this ccdVisit has completed successfully. 

379 (`lsst.dax.apdb.ApdbConfig`) 

380 - ``associatedDiaSources`` : Catalog of newly associated 

381 DiaSources. (`pandas.DataFrame`) 

382 """ 

383 # Load the DiaObjects and DiaSource history. 

384 loaderResult = self.diaCatalogLoader.run(diffIm, self.apdb) 

385 if len(loaderResult.diaObjects) > 0: 

386 diaObjects = self.purgeDiaObjects(diffIm.getBBox(), diffIm.getWcs(), loaderResult.diaObjects, 

387 buffer=self.config.imagePixelMargin) 

388 else: 

389 diaObjects = loaderResult.diaObjects 

390 

391 # Associate new DiaSources with existing DiaObjects. 

392 assocResults = self.associator.run(diaSourceTable, diaObjects, 

393 exposure_time=diffIm.visitInfo.exposureTime) 

394 

395 if self.config.doSolarSystemAssociation: 

396 ssoAssocResult = self.solarSystemAssociator.run( 

397 assocResults.unAssocDiaSources, 

398 solarSystemObjectTable, 

399 diffIm) 

400 createResults = self.createNewDiaObjects( 

401 ssoAssocResult.unAssocDiaSources) 

402 associatedDiaSources = pd.concat( 

403 [assocResults.matchedDiaSources, 

404 ssoAssocResult.ssoAssocDiaSources, 

405 createResults.diaSources]) 

406 nTotalSsObjects = ssoAssocResult.nTotalSsObjects 

407 nAssociatedSsObjects = ssoAssocResult.nAssociatedSsObjects 

408 else: 

409 createResults = self.createNewDiaObjects( 

410 assocResults.unAssocDiaSources) 

411 associatedDiaSources = pd.concat( 

412 [assocResults.matchedDiaSources, 

413 createResults.diaSources]) 

414 nTotalSsObjects = 0 

415 nAssociatedSsObjects = 0 

416 

417 # Create new DiaObjects from unassociated diaSources. 

418 self._add_association_meta_data(assocResults.nUpdatedDiaObjects, 

419 assocResults.nUnassociatedDiaObjects, 

420 createResults.nNewDiaObjects, 

421 nTotalSsObjects, 

422 nAssociatedSsObjects) 

423 # Index the DiaSource catalog for this visit after all associations 

424 # have been made. 

425 updatedDiaObjectIds = associatedDiaSources["diaObjectId"][ 

426 associatedDiaSources["diaObjectId"] != 0].to_numpy() 

427 associatedDiaSources.set_index(["diaObjectId", 

428 "band", 

429 "diaSourceId"], 

430 drop=False, 

431 inplace=True) 

432 

433 # Append new DiaObjects and DiaSources to their previous history. 

434 diaObjects = pd.concat( 

435 [diaObjects, 

436 createResults.newDiaObjects.set_index("diaObjectId", drop=False)], 

437 sort=True) 

438 if self.testDataFrameIndex(diaObjects): 

439 raise RuntimeError( 

440 "Duplicate DiaObjects created after association. This is " 

441 "likely due to re-running data with an already populated " 

442 "Apdb. If this was not the case then there was an unexpected " 

443 "failure in Association while matching and creating new " 

444 "DiaObjects and should be reported. Exiting.") 

445 mergedDiaSourceHistory = pd.concat( 

446 [loaderResult.diaSources, associatedDiaSources], 

447 sort=True) 

448 # Test for DiaSource duplication first. If duplicates are found, 

449 # this likely means this is duplicate data being processed and sent 

450 # to the Apdb. 

451 if self.testDataFrameIndex(mergedDiaSourceHistory): 

452 raise RuntimeError( 

453 "Duplicate DiaSources found after association and merging " 

454 "with history. This is likely due to re-running data with an " 

455 "already populated Apdb. If this was not the case then there " 

456 "was an unexpected failure in Association while matching " 

457 "sources to objects, and should be reported. Exiting.") 

458 

459 # Compute DiaObject Summary statistics from their full DiaSource 

460 # history. 

461 diaCalResult = self.diaCalculation.run( 

462 diaObjects, 

463 mergedDiaSourceHistory, 

464 updatedDiaObjectIds, 

465 [band]) 

466 # Test for duplication in the updated DiaObjects. 

467 if self.testDataFrameIndex(diaCalResult.diaObjectCat): 

468 raise RuntimeError( 

469 "Duplicate DiaObjects (loaded + updated) created after " 

470 "DiaCalculation. This is unexpected behavior and should be " 

471 "reported. Exiting.") 

472 if self.testDataFrameIndex(diaCalResult.updatedDiaObjects): 

473 raise RuntimeError( 

474 "Duplicate DiaObjects (updated) created after " 

475 "DiaCalculation. This is unexpected behavior and should be " 

476 "reported. Exiting.") 

477 

478 # Force photometer on the Difference and Calibrated exposures using 

479 # the new and updated DiaObject locations. 

480 diaForcedSources = self.diaForcedSource.run( 

481 diaCalResult.diaObjectCat, 

482 diaCalResult.updatedDiaObjects.loc[:, "diaObjectId"].to_numpy(), 

483 # Passing a ccdExposureIdBits here that isn't None will make 

484 # diaForcedSource emit a deprecation warning, so we don't have to 

485 # emit our own. 

486 ccdExposureIdBits, 

487 exposure, 

488 diffIm, 

489 idGenerator=idGenerator) 

490 

491 # Store DiaSources, updated DiaObjects, and DiaForcedSources in the 

492 # Apdb. 

493 self.apdb.store( 

494 DateTime.now(), 

495 diaCalResult.updatedDiaObjects, 

496 associatedDiaSources, 

497 diaForcedSources) 

498 

499 if self.config.doPackageAlerts: 

500 if len(loaderResult.diaForcedSources) > 1: 

501 diaForcedSources = pd.concat( 

502 [diaForcedSources, loaderResult.diaForcedSources], 

503 sort=True) 

504 if self.testDataFrameIndex(diaForcedSources): 

505 self.log.warning( 

506 "Duplicate DiaForcedSources created after merge with " 

507 "history and new sources. This may cause downstream " 

508 "problems. Dropping duplicates.") 

509 # Drop duplicates via index and keep the first appearance. 

510 # Reset due to the index shape being slight different than 

511 # expected. 

512 diaForcedSources = diaForcedSources.groupby( 

513 diaForcedSources.index).first() 

514 diaForcedSources.reset_index(drop=True, inplace=True) 

515 diaForcedSources.set_index( 

516 ["diaObjectId", "diaForcedSourceId"], 

517 drop=False, 

518 inplace=True) 

519 self.alertPackager.run(associatedDiaSources, 

520 diaCalResult.diaObjectCat, 

521 loaderResult.diaSources, 

522 diaForcedSources, 

523 diffIm, 

524 template) 

525 

526 return pipeBase.Struct(apdbMarker=self.config.apdb.value, 

527 associatedDiaSources=associatedDiaSources, 

528 diaForcedSources=diaForcedSources, 

529 diaObjects=diaObjects, 

530 longTrailedSources=assocResults.longTrailedSources 

531 ) 

532 

533 def createNewDiaObjects(self, unAssocDiaSources): 

534 """Loop through the set of DiaSources and create new DiaObjects 

535 for unassociated DiaSources. 

536 

537 Parameters 

538 ---------- 

539 unAssocDiaSources : `pandas.DataFrame` 

540 Set of DiaSources to create new DiaObjects from. 

541 

542 Returns 

543 ------- 

544 results : `lsst.pipe.base.Struct` 

545 Results struct containing: 

546 

547 - ``diaSources`` : DiaSource catalog with updated DiaObject ids. 

548 (`pandas.DataFrame`) 

549 - ``newDiaObjects`` : Newly created DiaObjects from the 

550 unassociated DiaSources. (`pandas.DataFrame`) 

551 - ``nNewDiaObjects`` : Number of newly created diaObjects.(`int`) 

552 """ 

553 if len(unAssocDiaSources) == 0: 

554 tmpObj = self._initialize_dia_object(0) 

555 newDiaObjects = pd.DataFrame(data=[], 

556 columns=tmpObj.keys()) 

557 else: 

558 newDiaObjects = unAssocDiaSources["diaSourceId"].apply( 

559 self._initialize_dia_object) 

560 unAssocDiaSources["diaObjectId"] = unAssocDiaSources["diaSourceId"] 

561 return pipeBase.Struct(diaSources=unAssocDiaSources, 

562 newDiaObjects=newDiaObjects, 

563 nNewDiaObjects=len(newDiaObjects)) 

564 

565 def _initialize_dia_object(self, objId): 

566 """Create a new DiaObject with values required to be initialized by the 

567 Ppdb. 

568 

569 Parameters 

570 ---------- 

571 objid : `int` 

572 ``diaObjectId`` value for the of the new DiaObject. 

573 

574 Returns 

575 ------- 

576 diaObject : `dict` 

577 Newly created DiaObject with keys: 

578 

579 ``diaObjectId`` 

580 Unique DiaObjectId (`int`). 

581 ``pmParallaxNdata`` 

582 Number of data points used for parallax calculation (`int`). 

583 ``nearbyObj1`` 

584 Id of the a nearbyObject in the Object table (`int`). 

585 ``nearbyObj2`` 

586 Id of the a nearbyObject in the Object table (`int`). 

587 ``nearbyObj3`` 

588 Id of the a nearbyObject in the Object table (`int`). 

589 ``?_psfFluxNdata`` 

590 Number of data points used to calculate point source flux 

591 summary statistics in each bandpass (`int`). 

592 """ 

593 new_dia_object = {"diaObjectId": objId, 

594 "pmParallaxNdata": 0, 

595 "nearbyObj1": 0, 

596 "nearbyObj2": 0, 

597 "nearbyObj3": 0, 

598 "flags": 0} 

599 for f in ["u", "g", "r", "i", "z", "y"]: 

600 new_dia_object["%s_psfFluxNdata" % f] = 0 

601 return pd.Series(data=new_dia_object) 

602 

603 def testDataFrameIndex(self, df): 

604 """Test the sorted DataFrame index for duplicates. 

605 

606 Wrapped as a separate function to allow for mocking of the this task 

607 in unittesting. Default of a mock return for this test is True. 

608 

609 Parameters 

610 ---------- 

611 df : `pandas.DataFrame` 

612 DataFrame to text. 

613 

614 Returns 

615 ------- 

616 `bool` 

617 True if DataFrame contains duplicate rows. 

618 """ 

619 return df.index.has_duplicates 

620 

621 def _add_association_meta_data(self, 

622 nUpdatedDiaObjects, 

623 nUnassociatedDiaObjects, 

624 nNewDiaObjects, 

625 nTotalSsObjects, 

626 nAssociatedSsObjects): 

627 """Store summaries of the association step in the task metadata. 

628 

629 Parameters 

630 ---------- 

631 nUpdatedDiaObjects : `int` 

632 Number of previous DiaObjects associated and updated in this 

633 ccdVisit. 

634 nUnassociatedDiaObjects : `int` 

635 Number of previous DiaObjects that were not associated or updated 

636 in this ccdVisit. 

637 nNewDiaObjects : `int` 

638 Number of newly created DiaObjects for this ccdVisit. 

639 nTotalSsObjects : `int` 

640 Number of SolarSystemObjects within the observable detector 

641 area. 

642 nAssociatedSsObjects : `int` 

643 Number of successfully associated SolarSystemObjects. 

644 """ 

645 self.metadata.add('numUpdatedDiaObjects', nUpdatedDiaObjects) 

646 self.metadata.add('numUnassociatedDiaObjects', nUnassociatedDiaObjects) 

647 self.metadata.add('numNewDiaObjects', nNewDiaObjects) 

648 self.metadata.add('numTotalSolarSystemObjects', nTotalSsObjects) 

649 self.metadata.add('numAssociatedSsObjects', nAssociatedSsObjects) 

650 

651 def purgeDiaObjects(self, bbox, wcs, diaObjCat, buffer=0): 

652 """Drop diaObjects that are outside the exposure bounding box. 

653 

654 Parameters 

655 ---------- 

656 bbox : `lsst.geom.Box2I` 

657 Bounding box of the exposure. 

658 wcs : `lsst.afw.geom.SkyWcs` 

659 Coordinate system definition (wcs) for the exposure. 

660 diaObjCat : `pandas.DataFrame` 

661 DiaObjects loaded from the Apdb. 

662 buffer : `int`, optional 

663 Width, in pixels, to pad the exposure bounding box. 

664 

665 Returns 

666 ------- 

667 diaObjCat : `pandas.DataFrame` 

668 DiaObjects loaded from the Apdb, restricted to the exposure 

669 bounding box. 

670 """ 

671 try: 

672 bbox.grow(buffer) 

673 raVals = diaObjCat.ra.to_numpy() 

674 decVals = diaObjCat.dec.to_numpy() 

675 xVals, yVals = wcs.skyToPixelArray(raVals, decVals, degrees=True) 

676 selector = bbox.contains(xVals, yVals) 

677 nPurged = np.sum(~selector) 

678 if nPurged > 0: 

679 diaObjCat = diaObjCat[selector].copy() 

680 self.log.info(f"Dropped {nPurged} diaObjects that were outside the bbox " 

681 f"leaving {len(diaObjCat)} in the catalog") 

682 except Exception as e: 

683 self.log.warning("Error attempting to check diaObject history: %s", e) 

684 return diaObjCat