/
lightcurvefile.py
548 lines (470 loc) · 21.1 KB
/
lightcurvefile.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
"""Defines LightCurveFile classes, i.e. files that contain LightCurves."""
from __future__ import division, print_function
import logging
import warnings
import numpy as np
import matplotlib as mpl
from matplotlib import pyplot as plt
from astropy.io import fits as pyfits
from astropy.io.fits import Undefined
from .utils import (bkjd_to_astropy_time, KeplerQualityFlags, TessQualityFlags,
LightkurveWarning, detect_filetype)
from . import MPLSTYLE
__all__ = ['LightCurveFile', 'KeplerLightCurveFile', 'TessLightCurveFile']
log = logging.getLogger(__name__)
class LightCurveFile(object):
"""Generic class to represent FITS files which contain one or more light curves.
Parameters
----------
path : str or `astropy.io.fits.HDUList` object
Local path or remote url of a lightcurve FITS file.
Also accepts a FITS file object already opened using AstroPy.
kwargs : dict
Keyword arguments to be passed to astropy.io.fits.open.
"""
def __init__(self, path, **kwargs):
if isinstance(path, pyfits.HDUList):
self.path = None
self.hdu = path
else:
self.path = path
self.hdu = pyfits.open(self.path, **kwargs)
def header(self, ext=0):
"""DEPRECATED. Please use ``get_header()`` instead."""
warnings.warn("`LightCurveFile.header` is deprecated, please use "
"`LightCurveFile.get_header()` instead.",
LightkurveWarning)
return self.hdu[ext].header
def get_header(self, ext=0):
"""Returns the metadata embedded in the file.
Light Curve Files contain embedded metadata headers spread across three
different FITS extensions:
1. The "PRIMARY" extension (``ext=0``) provides a metadata header
providing details on the target and its CCD position.
2. The "LIGHTCURVE" extension (``ext=1``) provides details on the
data columns and the systematics removal.
3. The "APERTURE" extension (``ext=2``) provides details on the
aperture pixel mask and the expected coordinate system (WCS).
Parameters
----------
ext : int or str
FITS extension name or number.
Returns
-------
header : `~astropy.io.fits.header.Header`
Header object containing metadata keywords.
"""
return self.hdu[ext].header
def get_keyword(self, keyword, hdu=0, default=None):
"""Returns a header keyword value.
If the keyword is Undefined or does not exist,
then return ``default`` instead.
"""
try:
kw = self.hdu[hdu].header[keyword]
except KeyError:
return default
if isinstance(kw, Undefined):
return default
return kw
@property
def time(self):
"""The file's `TIME` column."""
return self.hdu[1].data['TIME'][self.quality_mask]
@property
def cadenceno(self):
"""The file's `CADENCENO` column."""
return self.hdu[1].data['CADENCENO'][self.quality_mask]
@property
def ra(self):
"""Right Ascension as recorded in the header's `RA_OBJ` keyword."""
return self.get_keyword('RA_OBJ')
@property
def dec(self):
"""Declination as recorded in the header's `DEC_OBJ` keyword."""
return self.get_keyword('DEC_OBJ')
@property
def FLUX(self):
"""Returns a `~lightkurve.lightcurve.LightCurve` object based on the
contents of the `FLUX` column in the file, if that column exists."""
return self.get_lightcurve('FLUX')
@property
def SAP_FLUX(self):
"""Returns a `~lightkurve.lightcurve.LightCurve` object based on the
contents of the `SAP_FLUX` column in the file, if that column exists."""
return self.get_lightcurve('SAP_FLUX')
@property
def PDCSAP_FLUX(self):
"""Returns a `~lightkurve.lightcurve.LightCurve` object based on the
contents of the `PDCSAP_FLUX` column in the file, if that column exists.
"""
return self.get_lightcurve('PDCSAP_FLUX')
def _flux_types(self):
"""Returns a list of available flux types for this light curve file"""
types = [n for n in self.hdu[1].data.columns.names if 'FLUX' in n]
types = [n for n in types if not ('ERR' in n)]
return types
def _get_quality(self):
"""Returns the quality flag vector, which may go by different names
"""
if 'QUALITY' in self.hdu[1].data.columns.names:
quality_vector = self.hdu[1].data['QUALITY']
elif 'SAP_QUALITY' in self.hdu[1].data.columns.names:
quality_vector = self.hdu[1].data['SAP_QUALITY']
else:
quality_vector = np.zeros(len(self.hdu[1].data['TIME']))
return quality_vector
def _create_plot(self, method='plot', flux_types=None, style='lightkurve',
**kwargs):
"""Implements `plot()`, `scatter()`, and `errorbar()` to avoid code duplication.
Returns
-------
ax : `~matplotlib.axes.Axes`
The matplotlib Axes object.
"""
if style is None or style == 'lightkurve':
style = MPLSTYLE
with plt.style.context(style):
if not ('ax' in kwargs):
fig, ax = plt.subplots(1)
kwargs['ax'] = ax
if flux_types is None:
flux_types = self._flux_types()
if isinstance(flux_types, str):
flux_types = [flux_types]
for idx, ft in enumerate(flux_types):
lc = self.get_lightcurve(ft)
kwargs['color'] = np.asarray(mpl.rcParams['axes.prop_cycle'])[idx]['color']
if method == 'plot':
lc.plot(label=ft, **kwargs)
elif method == 'scatter':
lc.scatter(label=ft, **kwargs)
elif method == 'errorbar':
lc.errorbar(label=ft, **kwargs)
def plot(self, flux_types=None, style='lightkurve', **kwargs):
"""Plot the light curve file using matplotlib's `plot` method.
Parameters
----------
ax : `~matplotlib.axes.Axes`
A matplotlib axes object to plot into. If no axes is provided,
a new one will be generated.
flux_types : list or None
Which fluxes in the LCF to plot. Default is lcf._flux_types().
For Kepler this is PDCSAP and SAP flux. Pass a list to change flux
types.
normalize : bool
Normalize the lightcurve before plotting?
xlabel : str
Plot x axis label
ylabel : str
Plot y axis label
title : str
Plot set_title
style : str
Path or URL to a matplotlib style file, or name of one of
matplotlib's built-in stylesheets (e.g. 'ggplot').
Lightkurve's custom stylesheet is used by default.
kwargs : dict
Dictionary of arguments to be passed to `matplotlib.pyplot.plot`.
Returns
-------
ax : `~matplotlib.axes.Axes`
The matplotlib axes object.
"""
return self._create_plot(method='plot', flux_types=flux_types,
style=style, **kwargs)
def scatter(self, flux_types=None, style='lightkurve', **kwargs):
"""Plot the light curve file using matplotlib's `scatter` method.
Parameters
----------
ax : `~matplotlib.axes.Axes`
A matplotlib axes object to plot into. If no axes is provided,
a new one will be generated.
flux_types : list or None
Which fluxes in the LCF to plot. Default is lcf._flux_types().
For Kepler this is PDCSAP and SAP flux. Pass a list to change flux
types.
normalize : bool
Normalize the lightcurve before plotting?
xlabel : str
Plot x axis label
ylabel : str
Plot y axis label
title : str
Plot set_title
style : str
Path or URL to a matplotlib style file, or name of one of
matplotlib's built-in stylesheets (e.g. 'ggplot').
Lightkurve's custom stylesheet is used by default.
kwargs : dict
Dictionary of arguments to be passed to `matplotlib.pyplot.plot`.
Returns
-------
ax : `~matplotlib.axes.Axes`
The matplotlib axes object.
"""
return self._create_plot(method='scatter', flux_types=flux_types,
style=style, **kwargs)
def errorbar(self, flux_types=None, style='lightkurve', **kwargs):
"""Plot the light curve file using matplotlib's `errorbar` method.
Parameters
----------
ax : `~matplotlib.axes.Axes`
A matplotlib axes object to plot into. If no axes is provided,
a new one will be generated.
flux_types : list or None
Which fluxes in the LCF to plot. Default is lcf._flux_types().
For Kepler this is PDCSAP and SAP flux. Pass a list to change flux
types.
normalize : bool
Normalize the lightcurve before plotting?
xlabel : str
Plot x axis label
ylabel : str
Plot y axis label
title : str
Plot set_title
style : str
Path or URL to a matplotlib style file, or name of one of
matplotlib's built-in stylesheets (e.g. 'ggplot').
Lightkurve's custom stylesheet is used by default.
kwargs : dict
Dictionary of arguments to be passed to `matplotlib.pyplot.plot`.
Returns
-------
ax : `~matplotlib.axes.Axes`
The matplotlib axes object.
"""
return self._create_plot(method='errorbar', flux_types=flux_types,
style=style, **kwargs)
class KeplerLightCurveFile(LightCurveFile):
"""Subclass of :class:`LightCurveFile <lightkurve.lightcurvefile.LightCurveFile>`
to represent files generated by NASA's Kepler pipeline.
Parameters
----------
path : str
Local path or remote url of a FITS file in Kepler's lightcurve format.
quality_bitmask : str or int
Bitmask (integer) which identifies the quality flag bitmask that should
be used to mask out bad cadences. If a string is passed, it has the
following meaning:
* "none": no cadences will be ignored (`quality_bitmask=0`).
* "default": cadences with severe quality issues will be ignored
(`quality_bitmask=1130799`).
* "hard": more conservative choice of flags to ignore
(`quality_bitmask=1664431`). This is known to remove good data.
* "hardest": removes all data that has been flagged
(`quality_bitmask=2096639`). This mask is not recommended.
See the :class:`KeplerQualityFlags` class for details on the bitmasks.
kwargs : dict
Keyword arguments to be passed to astropy.io.fits.open.
"""
def __init__(self, path, quality_bitmask='default', **kwargs):
super(KeplerLightCurveFile, self).__init__(path, **kwargs)
# check to make sure the correct filetype has been provided
filetype = detect_filetype(self.get_header())
if filetype == 'TessLightCurveFile':
warnings.warn("A TESS data product is being opened using the "
"`KeplerLightCurveFile` class. "
"Please use `TessLightCurveFile` instead.",
LightkurveWarning)
elif filetype is None:
warnings.warn("Given fits file not recognized as Kepler or TESS "
"observation.", LightkurveWarning)
elif "TargetPixelFile" in filetype:
warnings.warn("A `TargetPixelFile` object is being opened as a "
"`KeplerLightCurveFile`. "
"Please use `KeplerTargetPixelFile` instead.",
LightkurveWarning)
self.quality_bitmask = quality_bitmask
self.quality_mask = KeplerQualityFlags.create_quality_mask(
quality_array=self.hdu[1].data['SAP_QUALITY'],
bitmask=quality_bitmask)
self.targetid = self.get_keyword('KEPLERID')
def __repr__(self):
return('KeplerLightCurveFile(ID: {})'.format(self.targetid))
@property
def astropy_time(self):
"""Returns an AstroPy Time object for all good-quality cadences."""
return bkjd_to_astropy_time(bkjd=self.time)
def get_lightcurve(self, flux_type, centroid_type='MOM_CENTR'):
if centroid_type+"1" in self.hdu[1].data.columns.names:
centroid_col = self.hdu[1].data[centroid_type + "1"][self.quality_mask]
centroid_row = self.hdu[1].data[centroid_type + "2"][self.quality_mask]
else:
centroid_col = np.repeat(np.NaN, self.quality_mask.sum())
centroid_row = np.repeat(np.NaN, self.quality_mask.sum())
if flux_type in self._flux_types():
# We did not import lightcurve at the top to prevent circular imports
from .lightcurve import KeplerLightCurve
f = self.hdu[1].data[flux_type][self.quality_mask]
fe = self.hdu[1].data[flux_type + "_ERR"][self.quality_mask]
if flux_type == 'SAP_FLUX':
f /= self.hdu[1].header.get('FLFRCSAP', 1)
fe /= self.hdu[1].header.get('FLFRCSAP', 1)
f /= self.hdu[1].header.get('CROWDSAP', 1)
fe /= self.hdu[1].header.get('CROWDSAP', 1)
return KeplerLightCurve(
time=self.hdu[1].data['TIME'][self.quality_mask],
time_format='bkjd',
time_scale='tdb',
flux=f,
flux_err=fe,
centroid_col=centroid_col,
centroid_row=centroid_row,
quality=self._get_quality()[self.quality_mask],
quality_bitmask=self.quality_bitmask,
channel=self.channel,
campaign=self.campaign,
quarter=self.quarter,
mission=self.mission,
cadenceno=self.cadenceno,
targetid=self.targetid,
label=self.get_keyword('OBJECT'),
ra=self.ra,
dec=self.dec)
else:
raise KeyError("{} is not a valid flux type. Available types are: {}".
format(flux_type, self._flux_types()))
@property
def channel(self):
"""Kepler CCD channel number. ('CHANNEL' header keyword)"""
return self.get_keyword('CHANNEL')
@property
def obsmode(self):
"""'short cadence' or 'long cadence'. ('OBSMODE' header keyword)"""
return self.get_keyword('OBSMODE')
@property
def pos_corr1(self):
"""Returns the column position correction."""
return self.hdu[1].data['POS_CORR1'][self.quality_mask]
@property
def pos_corr2(self):
"""Returns the row position correction."""
return self.hdu[1].data['POS_CORR2'][self.quality_mask]
@property
def quarter(self):
"""Kepler quarter number. ('QUARTER' header keyword)"""
return self.get_keyword('QUARTER')
@property
def campaign(self):
"""K2 Campaign number. ('CAMPAIGN' header keyword)"""
return self.get_keyword('CAMPAIGN')
@property
def mission(self):
"""'Kepler' or 'K2'. ('MISSION' header keyword)"""
return self.get_keyword('MISSION')
def compute_cotrended_lightcurve(self, cbvs=(1, 2), **kwargs):
"""Returns a LightCurve object after cotrending the SAP_FLUX
against the cotrending basis vectors.
Parameters
----------
cbvs : tuple or list of ints
The list of cotrending basis vectors to fit to the data. For example,
(1, 2) will fit the first two basis vectors.
kwargs : dict
Dictionary of keyword arguments to be passed to
KeplerCBVCorrector.correct.
Returns
-------
lc : LightCurve object
CBV flux-corrected lightcurve.
"""
from .correctors import KeplerCBVCorrector
return KeplerCBVCorrector(self).correct(cbvs=cbvs, **kwargs)
class TessLightCurveFile(LightCurveFile):
"""Subclass of :class:`LightCurveFile <lightkurve.lightcurvefile.LightCurveFile>`
to represent files generated by NASA's TESS pipeline.
Parameters
----------
path : str
Local path or remote url of a FITS file in TESS's lightcurve format.
quality_bitmask : str or int
Bitmask (integer) which identifies the quality flag bitmask that should
be used to mask out bad cadences. If a string is passed, it has the
following meaning:
* "none": no cadences will be ignored (`quality_bitmask=0`).
* "default": cadences with severe quality issues will be ignored
(`quality_bitmask=175`).
* "hard": more conservative choice of flags to ignore
(`quality_bitmask=7407`). This is known to remove good data.
* "hardest": removes all data that has been flagged
(`quality_bitmask=8191`). This mask is not recommended.
See the :class:`TessQualityFlags` class for details on the bitmasks.
kwargs : dict
Keyword arguments to be passed to astropy.io.fits.open.
"""
def __init__(self, path, quality_bitmask='default', **kwargs):
super(TessLightCurveFile, self).__init__(path, **kwargs)
# check to make sure the correct filetype has been provided
filetype = detect_filetype(self.get_header())
if filetype == 'KeplerLightCurveFile':
warnings.warn("A Kepler data product is being opened using the "
"`TessLightCurveFile` class. "
"Please use `KeplerLightCurveFile` instead.",
LightkurveWarning)
elif filetype is None:
warnings.warn("Given fits file not recognized as Kepler or TESS "
"observation.", LightkurveWarning)
elif "TargetPixelFile" in filetype:
warnings.warn("A `TargetPixelFile` object is being opened as a "
"`TessLightCurveFile`. "
"Please use `TessTargetPixelFile` instead.",
LightkurveWarning)
self.quality_bitmask = quality_bitmask
self.quality_mask = TessQualityFlags.create_quality_mask(
quality_array=self._get_quality(),
bitmask=quality_bitmask)
# Early TESS releases had cadences with time=NaN (i.e. missing data)
# which were not flagged by a QUALITY flag yet; the line below prevents
# these cadences from being used. They would break most methods!
self.quality_mask &= np.isfinite(self.hdu[1].data['TIME'])
self.targetid = self.get_keyword('TICID')
def __repr__(self):
return('TessLightCurveFile(TICID: {})'.format(self.targetid))
@property
def sector(self):
"""TESS Sector number ('SECTOR' header keyword)."""
return self.get_keyword('SECTOR')
@property
def camera(self):
"""TESS Camera number ('CAMERA' header keyword)."""
return self.get_keyword('CAMERA')
@property
def ccd(self):
"""TESS CCD number ('CCD' header keyword)."""
return self.get_keyword('CCD')
@property
def mission(self):
return 'TESS'
def get_lightcurve(self, flux_type, centroid_type='MOM_CENTR'):
if centroid_type+"1" in self.hdu[1].data.columns.names:
centroid_col = self.hdu[1].data[centroid_type + "1"][self.quality_mask]
centroid_row = self.hdu[1].data[centroid_type + "2"][self.quality_mask]
else:
centroid_col = np.repeat(np.NaN, self.quality_mask.sum())
centroid_row = np.repeat(np.NaN, self.quality_mask.sum())
if flux_type in self._flux_types():
# We did not import TessLightCurve at the top to prevent circular imports
from .lightcurve import TessLightCurve
return TessLightCurve(
time=self.hdu[1].data['TIME'][self.quality_mask],
time_format='btjd',
time_scale='tdb',
flux=self.hdu[1].data[flux_type][self.quality_mask],
flux_err=self.hdu[1].data[flux_type + "_ERR"][self.quality_mask],
centroid_col=centroid_col,
centroid_row=centroid_row,
quality=self._get_quality()[self.quality_mask],
quality_bitmask=self.quality_bitmask,
cadenceno=self.cadenceno,
targetid=self.targetid,
label=self.get_keyword('OBJECT'),
sector=self.sector,
camera=self.camera,
ccd=self.ccd,
ra=self.ra,
dec=self.dec)
else:
raise KeyError("{} is not a valid flux type. Available types are: {}".
format(flux_type, self._flux_types()))