pyfstat.py 116 KB
Newer Older
1
2
3
4
5
6
7
8
9
10
""" Classes for various types of searches using ComputeFstatistic """
import os
import sys
import itertools
import logging
import argparse
import copy
import glob
import inspect
from functools import wraps
11
import subprocess
12
from collections import OrderedDict
13
14
15

import numpy as np
import matplotlib
16
matplotlib.use('Agg')
17
import matplotlib.pyplot as plt
18
import scipy.special
19
20
21
import emcee
import corner
import dill as pickle
22
import lal
23
24
import lalpulsar

25
26
27
28
29
30
try:
    from tqdm import tqdm
except ImportError:
    def tqdm(x):
        return x

31
plt.rcParams['text.usetex'] = True
32
plt.rcParams['axes.formatter.useoffset'] = False
33

34
35
36
37
38
39
40
config_file = os.path.expanduser('~')+'/.pyfstat.conf'
if os.path.isfile(config_file):
    d = {}
    with open(config_file, 'r') as f:
        for line in f:
            k, v = line.split('=')
            k = k.replace(' ', '')
41
            v = v.replace(' ', '').replace("'", "").replace('"', '').replace('\n', '')
42
43
44
45
46
47
            d[k] = v
    earth_ephem = d['earth_ephem']
    sun_ephem = d['sun_ephem']
else:
    logging.warning('No ~/.pyfstat.conf file found please provide the paths '
                    'when initialising searches')
48
49
50
    earth_ephem = None
    sun_ephem = None

51
52
53
54
55
parser = argparse.ArgumentParser()
parser.add_argument("-q", "--quite", help="Decrease output verbosity",
                    action="store_true")
parser.add_argument("-c", "--clean", help="Don't use cached data",
                    action="store_true")
56
parser.add_argument("-u", "--use-old-data", action="store_true")
57
parser.add_argument('-s', "--setup-only", action="store_true")
58
parser.add_argument('-n', "--no-template-counting", action="store_true")
59
60
61
62
parser.add_argument('unittest_args', nargs='*')
args, unknown = parser.parse_known_args()
sys.argv[1:] = args.unittest_args

Gregory Ashton's avatar
Gregory Ashton committed
63
64
65
logger = logging.getLogger()
logger.setLevel(logging.DEBUG)
stream_handler = logging.StreamHandler()
66
if args.quite:
Gregory Ashton's avatar
Gregory Ashton committed
67
    stream_handler.setLevel(logging.WARNING)
68
else:
Gregory Ashton's avatar
Gregory Ashton committed
69
70
71
72
    stream_handler.setLevel(logging.DEBUG)
stream_handler.setFormatter(logging.Formatter(
    '%(asctime)s %(levelname)-8s: %(message)s', datefmt='%H:%M'))
logger.addHandler(stream_handler)
73

74

75
76
77
78
79
80
81
82
83
def round_to_n(x, n):
    if not x:
        return 0
    power = -int(np.floor(np.log10(abs(x)))) + (n - 1)
    factor = (10 ** power)
    return round(x * factor) / factor


def texify_float(x, d=1):
84
85
    if type(x) == str:
        return x
86
87
88
89
90
91
92
93
94
95
96
    x = round_to_n(x, d)
    if 0.01 < abs(x) < 100:
        return str(x)
    else:
        power = int(np.floor(np.log10(abs(x))))
        stem = np.round(x / 10**power, d)
        if d == 1:
            stem = int(stem)
        return r'${}{{\times}}10^{{{}}}$'.format(stem, power)


97
def initializer(func):
98
    """ Decorator function to automatically assign the parameters to self """
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
    names, varargs, keywords, defaults = inspect.getargspec(func)

    @wraps(func)
    def wrapper(self, *args, **kargs):
        for name, arg in list(zip(names[1:], args)) + list(kargs.items()):
            setattr(self, name, arg)

        for name, default in zip(reversed(names), reversed(defaults)):
            if not hasattr(self, name):
                setattr(self, name, default)

        func(self, *args, **kargs)

    return wrapper


def read_par(label, outdir):
116
    """ Read in a .par file, returns a dictionary of the values """
117
118
119
120
    filename = '{}/{}.par'.format(outdir, label)
    d = {}
    with open(filename, 'r') as f:
        for line in f:
121
122
123
            if len(line.split('=')) > 1:
                key, val = line.rstrip('\n').split(' = ')
                key = key.strip()
124
                d[key] = np.float64(eval(val.rstrip('; ')))
125
126
127
    return d


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
def get_V_estimate(
        nsegs, tref, minStartTime, maxStartTime, DeltaOmega, DeltaFs,
        fiducial_freq, detector_names, earth_ephem, sun_ephem):
    """ Returns V, Vsky, Vpe estimated from the super-sky metric

    Parameters
    ----------
    nsegs: int
        Number of semi-coherent segments
    tref: int
        Reference time in GPS seconds
    minStartTime, maxStartTime: int
        Minimum and maximum SFT timestamps
    DeltaOmega: float
        Solid angle of the sky-patch
    DeltaFs: array
        Array of [DeltaF0, DeltaF1, ...], length determines the number of
        spin-down terms.
    fiducial_freq: float
        Fidicual frequency
    detector_names: array
        Array of detectors to average over
    earth_ephem, sun_ephem: st
        Paths to the ephemeris files

    """
    spindowns = len(DeltaFs) - 1
    tboundaries = np.linspace(minStartTime, maxStartTime, nsegs+1)

    ref_time = lal.LIGOTimeGPS(tref)
    segments = lal.SegListCreate()
    for j in range(len(tboundaries)-1):
        seg = lal.SegCreate(lal.LIGOTimeGPS(tboundaries[j]),
                            lal.LIGOTimeGPS(tboundaries[j+1]),
                            j)
        lal.SegListAppend(segments, seg)
    detNames = lal.CreateStringVector(*detector_names)
    detectors = lalpulsar.MultiLALDetector()
    lalpulsar.ParseMultiLALDetector(detectors, detNames)
    detector_weights = None
    detector_motion = (lalpulsar.DETMOTION_SPIN
                       + lalpulsar.DETMOTION_ORBIT)
    ephemeris = lalpulsar.InitBarycenter(earth_ephem, sun_ephem)
    try:
        SSkyMetric = lalpulsar.ComputeSuperskyMetrics(
            spindowns, ref_time, segments, fiducial_freq, detectors,
            detector_weights, detector_motion, ephemeris)
    except RuntimeError as e:
        logging.debug('Encountered run-time error {}'.format(e))
        return None, None, None

    sqrtdetG_SKY = np.sqrt(np.linalg.det(
        SSkyMetric.semi_rssky_metric.data[:2, :2]))
    sqrtdetG_PE = np.sqrt(np.linalg.det(
        SSkyMetric.semi_rssky_metric.data[2:, 2:]))

    Vsky = .5*sqrtdetG_SKY*DeltaOmega
    Vpe = sqrtdetG_PE * np.prod(DeltaFs)
    if Vsky == 0:
        Vsky = 1
    if Vpe == 0:
        Vpe = 1
    return (Vsky * Vpe, Vsky, Vpe)


193
class BaseSearchClass(object):
194
    """ The base search class, provides general functions """
195
196
197
198

    earth_ephem_default = earth_ephem
    sun_ephem_default = sun_ephem

199
    def add_log_file(self):
200
        """ Log output to a file, requires class to have outdir and label """
201
202
        logfilename = '{}/{}.log'.format(self.outdir, self.label)
        fh = logging.FileHandler(logfilename)
Gregory Ashton's avatar
Gregory Ashton committed
203
        fh.setLevel(logging.INFO)
204
205
206
207
208
        fh.setFormatter(logging.Formatter(
            '%(asctime)s %(levelname)-8s: %(message)s',
            datefmt='%y-%m-%d %H:%M'))
        logging.getLogger().addHandler(fh)

209
    def shift_matrix(self, n, dT):
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
        """ Generate the shift matrix

        Parameters
        ----------
        n: int
            The dimension of the shift-matrix to generate
        dT: float
            The time delta of the shift matrix

        Returns
        -------
        m: array (n, n)
            The shift matrix
        """

225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
        m = np.zeros((n, n))
        factorial = np.math.factorial
        for i in range(n):
            for j in range(n):
                if i == j:
                    m[i, j] = 1.0
                elif i > j:
                    m[i, j] = 0.0
                else:
                    if i == 0:
                        m[i, j] = 2*np.pi*float(dT)**(j-i) / factorial(j-i)
                    else:
                        m[i, j] = float(dT)**(j-i) / factorial(j-i)
        return m

    def shift_coefficients(self, theta, dT):
        """ Shift a set of coefficients by dT

        Parameters
        ----------
        theta: array-like, shape (n,)
            vector of the expansion coefficients to transform starting from the
247
            lowest degree e.g [phi, F0, F1,...].
248
        dT: float
249
            difference between the two reference times as tref_new - tref_old.
250
251
252
253

        Returns
        -------
        theta_new: array-like shape (n,)
254
            vector of the coefficients as evaluate as the new reference time.
255
        """
256

257
258
259
260
        n = len(theta)
        m = self.shift_matrix(n, dT)
        return np.dot(m, theta)

261
    def calculate_thetas(self, theta, delta_thetas, tbounds, theta0_idx=0):
262
263
264
        """ Calculates the set of coefficients for the post-glitch signal """
        thetas = [theta]
        for i, dt in enumerate(delta_thetas):
265
266
267
268
269
270
271
272
273
274
275
276
277
            if i < theta0_idx:
                pre_theta_at_ith_glitch = self.shift_coefficients(
                    thetas[0], tbounds[i+1] - self.tref)
                post_theta_at_ith_glitch = pre_theta_at_ith_glitch - dt
                thetas.insert(0, self.shift_coefficients(
                    post_theta_at_ith_glitch, self.tref - tbounds[i+1]))

            elif i >= theta0_idx:
                pre_theta_at_ith_glitch = self.shift_coefficients(
                    thetas[i], tbounds[i+1] - self.tref)
                post_theta_at_ith_glitch = pre_theta_at_ith_glitch + dt
                thetas.append(self.shift_coefficients(
                    post_theta_at_ith_glitch, self.tref - tbounds[i+1]))
278
279
        return thetas

Gregory Ashton's avatar
Gregory Ashton committed
280
281
282
283
284
285
286
287
288
289
290
291
292
293
    def generate_loudest(self):
        params = read_par(self.label, self.outdir)
        for key in ['Alpha', 'Delta', 'F0', 'F1']:
            if key not in params:
                params[key] = self.theta_prior[key]
        cmd = ('lalapps_ComputeFstatistic_v2 -a {} -d {} -f {} -s {} -D "{}"'
               ' --refTime={} --outputLoudest="{}/{}.loudest" '
               '--minStartTime={} --maxStartTime={}').format(
                    params['Alpha'], params['Delta'], params['F0'],
                    params['F1'], self.sftfilepath, params['tref'],
                    self.outdir, self.label, self.minStartTime,
                    self.maxStartTime)
        subprocess.call([cmd], shell=True)

294

Gregory Ashton's avatar
Gregory Ashton committed
295
class ComputeFstat(object):
296
    """ Base class providing interface to `lalpulsar.ComputeFstat` """
Gregory Ashton's avatar
Gregory Ashton committed
297
298
299
300
301

    earth_ephem_default = earth_ephem
    sun_ephem_default = sun_ephem

    @initializer
302
303
    def __init__(self, tref, sftfilepath=None, minStartTime=None,
                 maxStartTime=None, binary=False, transient=True, BSGL=False,
304
                 detector=None, minCoverFreq=None, maxCoverFreq=None,
305
                 earth_ephem=None, sun_ephem=None, injectSources=None
306
                 ):
307
308
309
310
311
        """
        Parameters
        ----------
        tref: int
            GPS seconds of the reference time.
312
313
        sftfilepath: str
            File patern to match SFTs
314
315
316
317
318
319
320
321
322
323
324
325
        minStartTime, maxStartTime: float GPStime
            Only use SFTs with timestemps starting from (including, excluding)
            this epoch
        binary: bool
            If true, search of binary parameters.
        transient: bool
            If true, allow for the Fstat to be computed over a transient range.
        BSGL: bool
            If true, compute the BSGL rather than the twoF value.
        detector: str
            Two character reference to the data to use, specify None for no
            contraint.
326
327
328
329
330
331
332
333
334
335
        minCoverFreq, maxCoverFreq: float
            The min and max cover frequency passed to CreateFstatInput, if
            either is None the range of frequencies in the SFT less 1Hz is
            used.
        earth_ephem, sun_ephem: str
            Paths of the two files containing positions of Earth and Sun,
            respectively at evenly spaced times, as passed to CreateFstatInput.
            If None defaults defined in BaseSearchClass will be used.

        """
Gregory Ashton's avatar
Gregory Ashton committed
336
337
338
339
340
341
342
343

        if earth_ephem is None:
            self.earth_ephem = self.earth_ephem_default
        if sun_ephem is None:
            self.sun_ephem = self.sun_ephem_default

        self.init_computefstatistic_single_point()

Gregory Ashton's avatar
Gregory Ashton committed
344
345
346
    def get_SFTCatalog(self):
        if hasattr(self, 'SFTCatalog'):
            return
Gregory Ashton's avatar
Gregory Ashton committed
347
348
349
350
        logging.info('Initialising SFTCatalog')
        constraints = lalpulsar.SFTConstraints()
        if self.detector:
            constraints.detector = self.detector
351
352
353
354
355
        if self.minStartTime:
            constraints.minStartTime = lal.LIGOTimeGPS(self.minStartTime)
        if self.maxStartTime:
            constraints.maxStartTime = lal.LIGOTimeGPS(self.maxStartTime)

356
        logging.info('Loading data matching pattern {}'.format(
357
358
                     self.sftfilepath))
        SFTCatalog = lalpulsar.SFTdataFind(self.sftfilepath, constraints)
359
360
        detector_names = list(set([d.header.name for d in SFTCatalog.data]))
        self.detector_names = detector_names
361
        SFT_timestamps = [d.header.epoch for d in SFTCatalog.data]
Gregory Ashton's avatar
Gregory Ashton committed
362
363
364
365
366
367
        try:
            from bashplotlib.histogram import plot_hist
            print('Data timestamps histogram:')
            plot_hist(SFT_timestamps, height=5, bincount=50)
        except IOError:
            pass
368
        if len(detector_names) == 0:
Gregory Ashton's avatar
Gregory Ashton committed
369
370
            raise ValueError('No data loaded.')
        logging.info('Loaded {} data files from detectors {}'.format(
371
            len(SFT_timestamps), detector_names))
Gregory Ashton's avatar
Gregory Ashton committed
372
373
374
375
376
377
        logging.info('Data spans from {} ({}) to {} ({})'.format(
            int(SFT_timestamps[0]),
            subprocess.check_output('lalapps_tconvert {}'.format(
                int(SFT_timestamps[0])), shell=True).rstrip('\n'),
            int(SFT_timestamps[-1]),
            subprocess.check_output('lalapps_tconvert {}'.format(
378
                int(SFT_timestamps[-1])), shell=True).rstrip('\n')))
Gregory Ashton's avatar
Gregory Ashton committed
379
380
381
382
383
384
        self.SFTCatalog = SFTCatalog

    def init_computefstatistic_single_point(self):
        """ Initilisation step of run_computefstatistic for a single point """

        self.get_SFTCatalog()
Gregory Ashton's avatar
Gregory Ashton committed
385
386
387
388
389
390

        logging.info('Initialising ephems')
        ephems = lalpulsar.InitBarycenter(self.earth_ephem, self.sun_ephem)

        logging.info('Initialising FstatInput')
        dFreq = 0
391
392
393
394
395
        if self.transient:
            self.whatToCompute = lalpulsar.FSTATQ_ATOMS_PER_DET
        else:
            self.whatToCompute = lalpulsar.FSTATQ_2F

396
397
398
399
400
401
402
403
404
405
406
        FstatOAs = lalpulsar.FstatOptionalArgs()
        FstatOAs.randSeed = lalpulsar.FstatOptionalArgsDefaults.randSeed
        FstatOAs.SSBprec = lalpulsar.FstatOptionalArgsDefaults.SSBprec
        FstatOAs.Dterms = lalpulsar.FstatOptionalArgsDefaults.Dterms
        FstatOAs.runningMedianWindow = lalpulsar.FstatOptionalArgsDefaults.runningMedianWindow
        FstatOAs.FstatMethod = lalpulsar.FstatOptionalArgsDefaults.FstatMethod
        FstatOAs.InjectSqrtSX = lalpulsar.FstatOptionalArgsDefaults.injectSqrtSX
        FstatOAs.assumeSqrtSX = lalpulsar.FstatOptionalArgsDefaults.assumeSqrtSX
        FstatOAs.prevInput = lalpulsar.FstatOptionalArgsDefaults.prevInput
        FstatOAs.collectTiming = lalpulsar.FstatOptionalArgsDefaults.collectTiming

407
        if hasattr(self, 'injectSource') and type(self.injectSources) == dict:
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
            logging.info('Injecting source with params: {}'.format(
                self.injectSources))
            PPV = lalpulsar.CreatePulsarParamsVector(1)
            PP = PPV.data[0]
            PP.Amp.h0 = self.injectSources['h0']
            PP.Amp.cosi = self.injectSources['cosi']
            PP.Amp.phi0 = self.injectSources['phi0']
            PP.Amp.psi = self.injectSources['psi']
            PP.Doppler.Alpha = self.injectSources['Alpha']
            PP.Doppler.Delta = self.injectSources['Delta']
            PP.Doppler.fkdot = np.array(self.injectSources['fkdot'])
            PP.Doppler.refTime = self.tref
            if 't0' not in self.injectSources:
                PP.Transient.type = lalpulsar.TRANSIENT_NONE
            FstatOAs.injectSources = PPV
        else:
            FstatOAs.injectSources = lalpulsar.FstatOptionalArgsDefaults.injectSources
Gregory Ashton's avatar
Gregory Ashton committed
425
426

        if self.minCoverFreq is None or self.maxCoverFreq is None:
Gregory Ashton's avatar
Gregory Ashton committed
427
            fAs = [d.header.f0 for d in self.SFTCatalog.data]
Gregory Ashton's avatar
Gregory Ashton committed
428
            fBs = [d.header.f0 + (d.numBins-1)*d.header.deltaF
Gregory Ashton's avatar
Gregory Ashton committed
429
                   for d in self.SFTCatalog.data]
Gregory Ashton's avatar
Gregory Ashton committed
430
431
            self.minCoverFreq = np.min(fAs) + 0.5
            self.maxCoverFreq = np.max(fBs) - 0.5
432
433
434
            logging.info('Min/max cover freqs not provided, using '
                         '{} and {}, est. from SFTs'.format(
                             self.minCoverFreq, self.maxCoverFreq))
Gregory Ashton's avatar
Gregory Ashton committed
435

Gregory Ashton's avatar
Gregory Ashton committed
436
        self.FstatInput = lalpulsar.CreateFstatInput(self.SFTCatalog,
Gregory Ashton's avatar
Gregory Ashton committed
437
438
439
440
                                                     self.minCoverFreq,
                                                     self.maxCoverFreq,
                                                     dFreq,
                                                     ephems,
441
                                                     FstatOAs
Gregory Ashton's avatar
Gregory Ashton committed
442
443
444
445
446
447
448
449
450
451
452
453
454
                                                     )

        logging.info('Initialising PulsarDoplerParams')
        PulsarDopplerParams = lalpulsar.PulsarDopplerParams()
        PulsarDopplerParams.refTime = self.tref
        PulsarDopplerParams.Alpha = 1
        PulsarDopplerParams.Delta = 1
        PulsarDopplerParams.fkdot = np.array([0, 0, 0, 0, 0, 0, 0])
        self.PulsarDopplerParams = PulsarDopplerParams

        logging.info('Initialising FstatResults')
        self.FstatResults = lalpulsar.FstatResults()

455
        if self.BSGL:
Gregory Ashton's avatar
Gregory Ashton committed
456
            if len(self.names) < 2:
Gregory Ashton's avatar
Gregory Ashton committed
457
                raise ValueError("Can't use BSGL with single detector data")
458
            else:
459
                logging.info('Initialising BSGL')
460

461
462
            # Tuning parameters - to be reviewed
            numDetectors = 2
463
464
465
466
467
468
469
470
471
472
            if hasattr(self, 'nsegs'):
                p_val_threshold = 1e-6
                Fstar0s = np.linspace(0, 1000, 10000)
                p_vals = scipy.special.gammaincc(2*self.nsegs, Fstar0s)
                Fstar0 = Fstar0s[np.argmin(np.abs(p_vals - p_val_threshold))]
                if Fstar0 == Fstar0s[-1]:
                    raise ValueError('Max Fstar0 exceeded')
            else:
                Fstar0 = 15.
            logging.info('Using Fstar0 of {:1.2f}'.format(Fstar0))
473
            oLGX = np.zeros(10)
Gregory Ashton's avatar
Gregory Ashton committed
474
            oLGX[:numDetectors] = 1./numDetectors
475
            self.BSGLSetup = lalpulsar.CreateBSGLSetup(numDetectors,
476
                                                       Fstar0,
477
                                                       oLGX,
478
                                                       True,
479
480
                                                       1)
            self.twoFX = np.zeros(10)
Gregory Ashton's avatar
Gregory Ashton committed
481
            self.whatToCompute = (self.whatToCompute +
482
483
                                  lalpulsar.FSTATQ_2F_PER_DET)

484
        if self.transient:
485
            logging.info('Initialising transient parameters')
486
487
488
489
490
491
            self.windowRange = lalpulsar.transientWindowRange_t()
            self.windowRange.type = lalpulsar.TRANSIENT_RECTANGULAR
            self.windowRange.t0Band = 0
            self.windowRange.dt0 = 1
            self.windowRange.tauBand = 0
            self.windowRange.dtau = 1
492

493
494
495
496
497
498
499
500
501
    def compute_fullycoherent_det_stat_single_point(
            self, F0, F1, F2, Alpha, Delta, asini=None, period=None, ecc=None,
            tp=None, argp=None):
        """ Compute the fully-coherent det. statistic at a single point """

        return self.run_computefstatistic_single_point(
            self.minStartTime, self.maxStartTime, F0, F1, F2, Alpha, Delta,
            asini, period, ecc, tp, argp)

Gregory Ashton's avatar
Gregory Ashton committed
502
    def run_computefstatistic_single_point(self, tstart, tend, F0, F1,
503
504
505
                                           F2, Alpha, Delta, asini=None,
                                           period=None, ecc=None, tp=None,
                                           argp=None):
506
        """ Returns twoF or ln(BSGL) fully-coherently at a single point """
Gregory Ashton's avatar
Gregory Ashton committed
507
508
509
510

        self.PulsarDopplerParams.fkdot = np.array([F0, F1, F2, 0, 0, 0, 0])
        self.PulsarDopplerParams.Alpha = Alpha
        self.PulsarDopplerParams.Delta = Delta
511
512
513
514
515
516
        if self.binary:
            self.PulsarDopplerParams.asini = asini
            self.PulsarDopplerParams.period = period
            self.PulsarDopplerParams.ecc = ecc
            self.PulsarDopplerParams.tp = tp
            self.PulsarDopplerParams.argp = argp
Gregory Ashton's avatar
Gregory Ashton committed
517
518
519
520

        lalpulsar.ComputeFstat(self.FstatResults,
                               self.FstatInput,
                               self.PulsarDopplerParams,
521
                               1,
Gregory Ashton's avatar
Gregory Ashton committed
522
523
524
                               self.whatToCompute
                               )

525
        if self.transient is False:
526
527
528
529
530
531
            if self.BSGL is False:
                return self.FstatResults.twoF[0]

            twoF = np.float(self.FstatResults.twoF[0])
            self.twoFX[0] = self.FstatResults.twoFPerDet(0)
            self.twoFX[1] = self.FstatResults.twoFPerDet(1)
532
533
534
            log10_BSGL = lalpulsar.ComputeBSGL(twoF, self.twoFX,
                                               self.BSGLSetup)
            return log10_BSGL/np.log10(np.exp(1))
535

536
537
        self.windowRange.t0 = int(tstart)  # TYPE UINT4
        self.windowRange.tau = int(tend - tstart)  # TYPE UINT4
538

Gregory Ashton's avatar
Gregory Ashton committed
539
        FS = lalpulsar.ComputeTransientFstatMap(
540
            self.FstatResults.multiFatoms[0], self.windowRange, False)
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555

        if self.BSGL is False:
            return 2*FS.F_mn.data[0][0]

        FstatResults_single = copy.copy(self.FstatResults)
        FstatResults_single.lenth = 1
        FstatResults_single.data = self.FstatResults.multiFatoms[0].data[0]
        FS0 = lalpulsar.ComputeTransientFstatMap(
            FstatResults_single.multiFatoms[0], self.windowRange, False)
        FstatResults_single.data = self.FstatResults.multiFatoms[0].data[1]
        FS1 = lalpulsar.ComputeTransientFstatMap(
            FstatResults_single.multiFatoms[0], self.windowRange, False)

        self.twoFX[0] = 2*FS0.F_mn.data[0][0]
        self.twoFX[1] = 2*FS1.F_mn.data[0][0]
556
557
        log10_BSGL = lalpulsar.ComputeBSGL(
                2*FS.F_mn.data[0][0], self.twoFX, self.BSGLSetup)
558

559
        return log10_BSGL/np.log10(np.exp(1))
Gregory Ashton's avatar
Gregory Ashton committed
560

561
562
    def calculate_twoF_cumulative(self, F0, F1, F2, Alpha, Delta, asini=None,
                                  period=None, ecc=None, tp=None, argp=None,
563
564
                                  tstart=None, tend=None, npoints=1000,
                                  minfraction=0.01, maxfraction=1):
565
566
        """ Calculate the cumulative twoF along the obseration span """
        duration = tend - tstart
567
568
        tstart = tstart + minfraction*duration
        taus = np.linspace(minfraction*duration, maxfraction*duration, npoints)
569
        twoFs = []
Gregory Ashton's avatar
Gregory Ashton committed
570
571
572
        if self.transient is False:
            self.transient = True
            self.init_computefstatistic_single_point()
573
574
575
576
577
578
579
580
581
        for tau in taus:
            twoFs.append(self.run_computefstatistic_single_point(
                tstart=tstart, tend=tstart+tau, F0=F0, F1=F1, F2=F2,
                Alpha=Alpha, Delta=Delta, asini=asini, period=period, ecc=ecc,
                tp=tp, argp=argp))

        return taus, np.array(twoFs)

    def plot_twoF_cumulative(self, label, outdir, ax=None, c='k', savefig=True,
582
                             title=None, **kwargs):
583

584
585
586
587
588
589
        taus, twoFs = self.calculate_twoF_cumulative(**kwargs)
        if ax is None:
            fig, ax = plt.subplots()
        ax.plot(taus/86400., twoFs, label=label, color=c)
        ax.set_xlabel(r'Days from $t_{{\rm start}}={:.0f}$'.format(
            kwargs['tstart']))
Gregory Ashton's avatar
Gregory Ashton committed
590
591
592
593
        if self.BSGL:
            ax.set_ylabel(r'$\log_{10}(\mathrm{BSGL})_{\rm cumulative}$')
        else:
            ax.set_ylabel(r'$\widetilde{2\mathcal{F}}_{\rm cumulative}$')
594
        ax.set_xlim(0, taus[-1]/86400)
595
        ax.set_title(title)
596
597
        if savefig:
            plt.savefig('{}/{}_twoFcumulative.png'.format(outdir, label))
Gregory Ashton's avatar
Gregory Ashton committed
598
            return taus, twoFs
599
600
601
        else:
            return ax

Gregory Ashton's avatar
Gregory Ashton committed
602

603
604
605
606
607
608
609
class SemiCoherentSearch(BaseSearchClass, ComputeFstat):
    """ A semi-coherent search """

    @initializer
    def __init__(self, label, outdir, tref, nsegs=None, sftfilepath=None,
                 binary=False, BSGL=False, minStartTime=None,
                 maxStartTime=None, minCoverFreq=None, maxCoverFreq=None,
610
611
                 detector=None, earth_ephem=None, sun_ephem=None,
                 injectSources=None):
612
613
614
615
616
        """
        Parameters
        ----------
        label, outdir: str
            A label and directory to read/write data from/to.
617
        tref, minStartTime, maxStartTime: int
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
            GPS seconds of the reference time, and start and end of the data.
        nsegs: int
            The (fixed) number of segments
        sftfilepath: str
            File patern to match SFTs

        For all other parameters, see pyfstat.ComputeFStat.
        """

        self.fs_file_name = "{}/{}_FS.dat".format(self.outdir, self.label)
        if self.earth_ephem is None:
            self.earth_ephem = self.earth_ephem_default
        if self.sun_ephem is None:
            self.sun_ephem = self.sun_ephem_default
        self.transient = True
        self.init_computefstatistic_single_point()
        self.init_semicoherent_parameters()

    def init_semicoherent_parameters(self):
637
638
639
        logging.info(('Initialising semicoherent parameters from {} to {} in'
                      ' {} segments').format(
            self.minStartTime, self.maxStartTime, self.nsegs))
640
641
        self.transient = True
        self.whatToCompute = lalpulsar.FSTATQ_2F+lalpulsar.FSTATQ_ATOMS_PER_DET
642
643
644
        self.tboundaries = np.linspace(self.minStartTime, self.maxStartTime,
                                       self.nsegs+1)

Gregory Ashton's avatar
Gregory Ashton committed
645
646
647
648
    def run_semi_coherent_computefstatistic_single_point(
            self, F0, F1, F2, Alpha, Delta, asini=None,
            period=None, ecc=None, tp=None, argp=None):
        """ Returns twoF or ln(BSGL) semi-coherently at a single point """
649

Gregory Ashton's avatar
Gregory Ashton committed
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
        self.PulsarDopplerParams.fkdot = np.array([F0, F1, F2, 0, 0, 0, 0])
        self.PulsarDopplerParams.Alpha = Alpha
        self.PulsarDopplerParams.Delta = Delta
        if self.binary:
            self.PulsarDopplerParams.asini = asini
            self.PulsarDopplerParams.period = period
            self.PulsarDopplerParams.ecc = ecc
            self.PulsarDopplerParams.tp = tp
            self.PulsarDopplerParams.argp = argp

        lalpulsar.ComputeFstat(self.FstatResults,
                               self.FstatInput,
                               self.PulsarDopplerParams,
                               1,
                               self.whatToCompute
                               )

        if self.transient is False:
            if self.BSGL is False:
                return self.FstatResults.twoF[0]

            twoF = np.float(self.FstatResults.twoF[0])
            self.twoFX[0] = self.FstatResults.twoFPerDet(0)
            self.twoFX[1] = self.FstatResults.twoFPerDet(1)
            log10_BSGL = lalpulsar.ComputeBSGL(twoF, self.twoFX,
                                               self.BSGLSetup)
            return log10_BSGL/np.log10(np.exp(1))

        detStat = 0
        for tstart, tend in zip(self.tboundaries[:-1], self.tboundaries[1:]):
            self.windowRange.t0 = int(tstart)  # TYPE UINT4
            self.windowRange.tau = int(tend - tstart)  # TYPE UINT4

            FS = lalpulsar.ComputeTransientFstatMap(
                self.FstatResults.multiFatoms[0], self.windowRange, False)

            if self.BSGL is False:
                detStat += 2*FS.F_mn.data[0][0]
                continue
689

Gregory Ashton's avatar
Gregory Ashton committed
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
            FstatResults_single = copy.copy(self.FstatResults)
            FstatResults_single.lenth = 1
            FstatResults_single.data = self.FstatResults.multiFatoms[0].data[0]
            FS0 = lalpulsar.ComputeTransientFstatMap(
                FstatResults_single.multiFatoms[0], self.windowRange, False)
            FstatResults_single.data = self.FstatResults.multiFatoms[0].data[1]
            FS1 = lalpulsar.ComputeTransientFstatMap(
                FstatResults_single.multiFatoms[0], self.windowRange, False)

            self.twoFX[0] = 2*FS0.F_mn.data[0][0]
            self.twoFX[1] = 2*FS1.F_mn.data[0][0]
            log10_BSGL = lalpulsar.ComputeBSGL(
                    2*FS.F_mn.data[0][0], self.twoFX, self.BSGLSetup)

            detStat += log10_BSGL/np.log10(np.exp(1))

        return detStat
707
708


Gregory Ashton's avatar
Gregory Ashton committed
709
class SemiCoherentGlitchSearch(BaseSearchClass, ComputeFstat):
710
711
712
    """ A semi-coherent glitch search

    This implements a basic `semi-coherent glitch F-stat in which the data
713
714
    is divided into segments either side of the proposed glitches and the
    fully-coherent F-stat in each segment is summed to give the semi-coherent
715
716
717
718
    F-stat
    """

    @initializer
719
720
721
    def __init__(self, label, outdir, tref, minStartTime, maxStartTime,
                 nglitch=0, sftfilepath=None, theta0_idx=0, BSGL=False,
                 minCoverFreq=None, maxCoverFreq=None,
722
                 detector=None, earth_ephem=None, sun_ephem=None):
723
724
725
726
        """
        Parameters
        ----------
        label, outdir: str
727
            A label and directory to read/write data from/to.
728
        tref, minStartTime, maxStartTime: int
729
730
731
732
            GPS seconds of the reference time, and start and end of the data.
        nglitch: int
            The (fixed) number of glitches; this can zero, but occasionally
            this causes issue (in which case just use ComputeFstat).
733
734
        sftfilepath: str
            File patern to match SFTs
735
736
737
738
        theta0_idx, int
            Index (zero-based) of which segment the theta refers to - uyseful
            if providing a tight prior on theta to allow the signal to jump
            too theta (and not just from)
739
740

        For all other parameters, see pyfstat.ComputeFStat.
741
742
743
744
745
746
747
        """

        self.fs_file_name = "{}/{}_FS.dat".format(self.outdir, self.label)
        if self.earth_ephem is None:
            self.earth_ephem = self.earth_ephem_default
        if self.sun_ephem is None:
            self.sun_ephem = self.sun_ephem_default
748
749
        self.transient = True
        self.binary = False
750
751
752
        self.init_computefstatistic_single_point()

    def compute_nglitch_fstat(self, F0, F1, F2, Alpha, Delta, *args):
753
        """ Returns the semi-coherent glitch summed twoF """
754
755

        args = list(args)
756
757
        tboundaries = ([self.minStartTime] + args[-self.nglitch:]
                       + [self.maxStartTime])
758
759
760
761
762
763
764
765
        delta_F0s = args[-3*self.nglitch:-2*self.nglitch]
        delta_F1s = args[-2*self.nglitch:-self.nglitch]
        delta_F2 = np.zeros(len(delta_F0s))
        delta_phi = np.zeros(len(delta_F0s))
        theta = [0, F0, F1, F2]
        delta_thetas = np.atleast_2d(
                np.array([delta_phi, delta_F0s, delta_F1s, delta_F2]).T)

766
767
        thetas = self.calculate_thetas(theta, delta_thetas, tboundaries,
                                       theta0_idx=self.theta0_idx)
768
769

        twoFSum = 0
770
        for i, theta_i_at_tref in enumerate(thetas):
771
772
773
            ts, te = tboundaries[i], tboundaries[i+1]

            twoFVal = self.run_computefstatistic_single_point(
774
775
                ts, te, theta_i_at_tref[1], theta_i_at_tref[2],
                theta_i_at_tref[3], Alpha, Delta)
776
777
            twoFSum += twoFVal

778
779
780
        if np.isfinite(twoFSum):
            return twoFSum
        else:
781
            return -np.inf
782
783
784

    def compute_glitch_fstat_single(self, F0, F1, F2, Alpha, Delta, delta_F0,
                                    delta_F1, tglitch):
785
786
        """ Returns the semi-coherent glitch summed twoF for nglitch=1

787
        Note: OBSOLETE, used only for testing
788
        """
789
790
791
792
793
794
795
796
797
798
799

        theta = [F0, F1, F2]
        delta_theta = [delta_F0, delta_F1, 0]
        tref = self.tref

        theta_at_glitch = self.shift_coefficients(theta, tglitch - tref)
        theta_post_glitch_at_glitch = theta_at_glitch + delta_theta
        theta_post_glitch = self.shift_coefficients(
            theta_post_glitch_at_glitch, tref - tglitch)

        twoFsegA = self.run_computefstatistic_single_point(
800
            self.minStartTime, tglitch, theta[0], theta[1], theta[2], Alpha,
801
802
            Delta)

803
        if tglitch == self.maxStartTime:
804
805
806
            return twoFsegA

        twoFsegB = self.run_computefstatistic_single_point(
807
            tglitch, self.maxStartTime, theta_post_glitch[0],
808
809
810
811
812
813
            theta_post_glitch[1], theta_post_glitch[2], Alpha,
            Delta)

        return twoFsegA + twoFsegB


Gregory Ashton's avatar
Gregory Ashton committed
814
815
class MCMCSearch(BaseSearchClass):
    """ MCMC search using ComputeFstat"""
816
    @initializer
817
    def __init__(self, label, outdir, sftfilepath, theta_prior, tref,
Gregory Ashton's avatar
Gregory Ashton committed
818
                 minStartTime, maxStartTime, nsteps=[100, 100],
819
820
                 nwalkers=100, ntemps=1, log10temperature_min=-5,
                 theta_initial=None, scatter_val=1e-10,
821
822
                 binary=False, BSGL=False, minCoverFreq=None,
                 maxCoverFreq=None, detector=None, earth_ephem=None,
823
                 sun_ephem=None, injectSources=None):
824
825
826
827
        """
        Parameters
        label, outdir: str
            A label and directory to read/write data from/to
828
829
        sftfilepath: str
            File patern to match SFTs
830
        theta_prior: dict
831
832
833
834
            Dictionary of priors and fixed values for the search parameters.
            For each parameters (key of the dict), if it is to be held fixed
            the value should be the constant float, if it is be searched, the
            value should be a dictionary of the prior.
835
836
837
838
        theta_initial: dict, array, (None)
            Either a dictionary of distribution about which to distribute the
            initial walkers about, an array (from which the walkers will be
            scattered by scatter_val, or  None in which case the prior is used.
839
        tref, minStartTime, maxStartTime: int
840
841
842
843
844
845
            GPS seconds of the reference time, start time and end time
        nsteps: list (m,)
            List specifying the number of steps to take, the last two entries
            give the nburn and nprod of the 'production' run, all entries
            before are for iterative initialisation steps (usually just one)
            e.g. [1000, 1000, 500].
846
847
848
849
850
851
852
853
854
855
856
        nwalkers, ntemps: int,
            The number of walkers and temperates to use in the parallel
            tempered PTSampler.
        log10temperature_min float < 0
            The  log_10(tmin) value, the set of betas passed to PTSampler are
            generated from np.logspace(0, log10temperature_min, ntemps).
        binary: Bool
            If true, search over binary parameters
        detector: str
            Two character reference to the data to use, specify None for no
            contraint.
857
858
859
860
861
862
863
864
865
866
        minCoverFreq, maxCoverFreq: float
            Minimum and maximum instantaneous frequency which will be covered
            over the SFT time span as passed to CreateFstatInput
        earth_ephem, sun_ephem: str
            Paths of the two files containing positions of Earth and Sun,
            respectively at evenly spaced times, as passed to CreateFstatInput
            If None defaults defined in BaseSearchClass will be used

        """

Gregory Ashton's avatar
Gregory Ashton committed
867
868
        if os.path.isdir(outdir) is False:
            os.mkdir(outdir)
869
        self.add_log_file()
Gregory Ashton's avatar
Gregory Ashton committed
870
871
        logging.info(
            'Set-up MCMC search for model {} on data {}'.format(
872
                self.label, self.sftfilepath))
873
874
875
        self.pickle_path = '{}/{}_saved_data.p'.format(self.outdir, self.label)
        self.unpack_input_theta()
        self.ndim = len(self.theta_keys)
876
877
878
879
        if self.log10temperature_min:
            self.betas = np.logspace(0, self.log10temperature_min, self.ntemps)
        else:
            self.betas = None
880

881
882
883
884
885
886
887
888
        if earth_ephem is None:
            self.earth_ephem = self.earth_ephem_default
        if sun_ephem is None:
            self.sun_ephem = self.sun_ephem_default

        if args.clean and os.path.isfile(self.pickle_path):
            os.rename(self.pickle_path, self.pickle_path+".old")

889
890
891
        self.log_input()

    def log_input(self):
892
        logging.info('theta_prior = {}'.format(self.theta_prior))
893
        logging.info('nwalkers={}'.format(self.nwalkers))
894
895
896
897
        logging.info('scatter_val = {}'.format(self.scatter_val))
        logging.info('nsteps = {}'.format(self.nsteps))
        logging.info('ntemps = {}'.format(self.ntemps))
        logging.info('log10temperature_min = {}'.format(
898
            self.log10temperature_min))
899
900
901

    def inititate_search_object(self):
        logging.info('Setting up search object')
Gregory Ashton's avatar
Gregory Ashton committed
902
        self.search = ComputeFstat(
903
904
905
906
            tref=self.tref, sftfilepath=self.sftfilepath,
            minCoverFreq=self.minCoverFreq, maxCoverFreq=self.maxCoverFreq,
            earth_ephem=self.earth_ephem, sun_ephem=self.sun_ephem,
            detector=self.detector, BSGL=self.BSGL, transient=False,
907
            minStartTime=self.minStartTime, maxStartTime=self.maxStartTime,
908
            binary=self.binary, injectSources=self.injectSources)
909
910

    def logp(self, theta_vals, theta_prior, theta_keys, search):
Gregory Ashton's avatar
Gregory Ashton committed
911
        H = [self.generic_lnprior(**theta_prior[key])(p) for p, key in
912
913
914
915
916
917
             zip(theta_vals, theta_keys)]
        return np.sum(H)

    def logl(self, theta, search):
        for j, theta_i in enumerate(self.theta_idxs):
            self.fixed_theta[theta_i] = theta[j]
918
919
        FS = search.compute_fullycoherent_det_stat_single_point(
            *self.fixed_theta)
920
921
922
        return FS

    def unpack_input_theta(self):
923
        full_theta_keys = ['F0', 'F1', 'F2', 'Alpha', 'Delta']
924
925
926
        if self.binary:
            full_theta_keys += [
                'asini', 'period', 'ecc', 'tp', 'argp']
927
928
        full_theta_keys_copy = copy.copy(full_theta_keys)

929
930
        full_theta_symbols = ['$f$', '$\dot{f}$', '$\ddot{f}$', r'$\alpha$',
                              r'$\delta$']
931
932
933
934
        if self.binary:
            full_theta_symbols += [
                'asini', 'period', 'period', 'ecc', 'tp', 'argp']

935
936
        self.theta_keys = []
        fixed_theta_dict = {}
937
        for key, val in self.theta_prior.iteritems():
938
939
            if type(val) is dict:
                fixed_theta_dict[key] = 0
Gregory Ashton's avatar
Gregory Ashton committed
940
                self.theta_keys.append(key)
941
942
943
944
945
946
            elif type(val) in [float, int, np.float64]:
                fixed_theta_dict[key] = val
            else:
                raise ValueError(
                    'Type {} of {} in theta not recognised'.format(
                        type(val), key))
Gregory Ashton's avatar
Gregory Ashton committed
947
            full_theta_keys_copy.pop(full_theta_keys_copy.index(key))
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963

        if len(full_theta_keys_copy) > 0:
            raise ValueError(('Input dictionary `theta` is missing the'
                              'following keys: {}').format(
                                  full_theta_keys_copy))

        self.fixed_theta = [fixed_theta_dict[key] for key in full_theta_keys]
        self.theta_idxs = [full_theta_keys.index(k) for k in self.theta_keys]
        self.theta_symbols = [full_theta_symbols[i] for i in self.theta_idxs]

        idxs = np.argsort(self.theta_idxs)
        self.theta_idxs = [self.theta_idxs[i] for i in idxs]
        self.theta_symbols = [self.theta_symbols[i] for i in idxs]
        self.theta_keys = [self.theta_keys[i] for i in idxs]

    def check_initial_points(self, p0):
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
        for nt in range(self.ntemps):
            logging.info('Checking temperature {} chains'.format(nt))
            initial_priors = np.array([
                self.logp(p, self.theta_prior, self.theta_keys, self.search)
                for p in p0[nt]])
            number_of_initial_out_of_bounds = sum(initial_priors == -np.inf)

            if number_of_initial_out_of_bounds > 0:
                logging.warning(
                    'Of {} initial values, {} are -np.inf due to the prior'
                    .format(len(initial_priors),
                            number_of_initial_out_of_bounds))

                p0 = self.generate_new_p0_to_fix_initial_points(
                    p0, nt, initial_priors)

    def generate_new_p0_to_fix_initial_points(self, p0, nt, initial_priors):
        logging.info('Attempting to correct intial values')
        idxs = np.arange(self.nwalkers)[initial_priors == -np.inf]
        count = 0
        while sum(initial_priors == -np.inf) > 0 and count < 100:
            for j in idxs:
                p0[nt][j] = (p0[nt][np.random.randint(0, self.nwalkers)]*(
                             1+np.random.normal(0, 1e-10, self.ndim)))
            initial_priors = np.array([
                self.logp(p, self.theta_prior, self.theta_keys,
                          self.search)
                for p in p0[nt]])
            count += 1

        if sum(initial_priors == -np.inf) > 0:
            logging.info('Failed to fix initial priors')
        else:
            logging.info('Suceeded to fix initial priors')

        return p0
1000

Gregory Ashton's avatar
Gregory Ashton committed
1001
    def run_sampler_with_progress_bar(self, sampler, ns, p0):
1002
1003
        for result in tqdm(sampler.sample(p0, iterations=ns), total=ns):
            pass
Gregory Ashton's avatar
Gregory Ashton committed
1004
1005
        return sampler

1006
    def run(self, proposal_scale_factor=2, **kwargs):
1007

Gregory Ashton's avatar
Gregory Ashton committed
1008
        self.old_data_is_okay_to_use = self.check_old_data_is_okay_to_use()
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
        if self.old_data_is_okay_to_use is True:
            logging.warning('Using saved data from {}'.format(
                self.pickle_path))
            d = self.get_saved_data()
            self.sampler = d['sampler']
            self.samples = d['samples']
            self.lnprobs = d['lnprobs']
            self.lnlikes = d['lnlikes']
            return

        self.inititate_search_object()

        sampler = emcee.PTSampler(
            self.ntemps, self.nwalkers, self.ndim, self.logl, self.logp,
            logpargs=(self.theta_prior, self.theta_keys, self.search),
1024
            loglargs=(self.search,), betas=self.betas, a=proposal_scale_factor)
1025

Gregory Ashton's avatar
Gregory Ashton committed
1026
1027
        p0 = self.generate_initial_p0()
        p0 = self.apply_corrections_to_p0(p0)
1028
1029
1030
1031
1032
        self.check_initial_points(p0)

        ninit_steps = len(self.nsteps) - 2
        for j, n in enumerate(self.nsteps[:-2]):
            logging.info('Running {}/{} initialisation with {} steps'.format(
Gregory Ashton's avatar
Gregory Ashton committed
1033
                j, ninit_steps, n))
Gregory Ashton's avatar
Gregory Ashton committed
1034
            sampler = self.run_sampler_with_progress_bar(sampler, n, p0)
1035
1036
            logging.info("Mean acceptance fraction: {}"
                         .format(np.mean(sampler.acceptance_fraction, axis=1)))
1037
1038
1039
            if self.ntemps > 1:
                logging.info("Tswap acceptance fraction: {}"
                             .format(sampler.tswap_acceptance_fraction))
1040
1041
            fig, axes = self.plot_walkers(sampler, symbols=self.theta_symbols,
                                          **kwargs)
1042
            fig.savefig('{}/{}_init_{}_walkers.png'.format(
1043
                self.outdir, self.label, j), dpi=200)
1044

1045
            p0 = self.get_new_p0(sampler)
Gregory Ashton's avatar
Gregory Ashton committed
1046
            p0 = self.apply_corrections_to_p0(p0)
1047
1048
1049
            self.check_initial_points(p0)
            sampler.reset()

Gregory Ashton's avatar
Gregory Ashton committed
1050
1051
1052
1053
        if len(self.nsteps) > 1:
            nburn = self.nsteps[-2]
        else:
            nburn = 0
1054
1055
1056
        nprod = self.nsteps[-1]
        logging.info('Running final burn and prod with {} steps'.format(
            nburn+nprod))
Gregory Ashton's avatar
Gregory Ashton committed
1057
        sampler = self.run_sampler_with_progress_bar(sampler, nburn+nprod, p0)
1058
1059
        logging.info("Mean acceptance fraction: {}"
                     .format(np.mean(sampler.acceptance_fraction, axis=1)))
1060
1061
1062
        if self.ntemps > 1:
            logging.info("Tswap acceptance fraction: {}"
                         .format(sampler.tswap_acceptance_fraction))
1063

Gregory Ashton's avatar
Gregory Ashton committed
1064
        fig, axes = self.plot_walkers(sampler, symbols=self.theta_symbols,
1065
1066
1067
                                      burnin_idx=nburn, **kwargs)
        fig.savefig('{}/{}_walkers.png'.format(self.outdir, self.label),
                    dpi=200)
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077

        samples = sampler.chain[0, :, nburn:, :].reshape((-1, self.ndim))
        lnprobs = sampler.lnprobability[0, :, nburn:].reshape((-1))
        lnlikes = sampler.lnlikelihood[0, :, nburn:].reshape((-1))
        self.sampler = sampler
        self.samples = samples
        self.lnprobs = lnprobs
        self.lnlikes = lnlikes
        self.save_data(sampler, samples, lnprobs, lnlikes)

1078
    def plot_corner(self, figsize=(7, 7),  tglitch_ratio=False,
1079
1080
1081
                    add_prior=False, nstds=None, label_offset=0.4,
                    dpi=300, rc_context={}, **kwargs):

Gregory Ashton's avatar
Gregory Ashton committed
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
        if self.ndim < 2:
            with plt.rc_context(rc_context):
                fig, ax = plt.subplots(figsize=figsize)
                ax.hist(self.samples, bins=50, histtype='stepfilled')
                ax.set_xlabel(self.theta_symbols[0])

            fig.savefig('{}/{}_corner.png'.format(
                self.outdir, self.label), dpi=dpi)
            return

1092
1093
1094
1095
1096
1097
        with plt.rc_context(rc_context):
            fig, axes = plt.subplots(self.ndim, self.ndim,
                                     figsize=figsize)

            samples_plt = copy.copy(self.samples)
            theta_symbols_plt = copy.copy(self.theta_symbols)
1098
1099
            theta_symbols_plt = [s.replace('_{glitch}', r'_\textrm{glitch}')
                                 for s in theta_symbols_plt]
1100
1101
1102
1103
1104

            if tglitch_ratio:
                for j, k in enumerate(self.theta_keys):
                    if k == 'tglitch':
                        s = samples_plt[:, j]
1105
1106
1107
                        samples_plt[:, j] = (
                            s - self.minStartTime)/(
                                self.maxStartTime - self.minStartTime)
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
                        theta_symbols_plt[j] = r'$R_{\textrm{glitch}}$'

            if type(nstds) is int and 'range' not in kwargs:
                _range = []
                for j, s in enumerate(samples_plt.T):
                    median = np.median(s)
                    std = np.std(s)
                    _range.append((median - nstds*std, median + nstds*std))
            else:
                _range = None

            fig_triangle = corner.corner(samples_plt,
                                         labels=theta_symbols_plt,
                                         fig=fig,
                                         bins=50,
                                         max_n_ticks=4,
                                         plot_contours=True,
                                         plot_datapoints=True,
                                         label_kwargs={'fontsize': 8},
                                         data_kwargs={'alpha': 0.1,
                                                      'ms': 0.5},
                                         range=_range,
                                         **kwargs)

            axes_list = fig_triangle.get_axes()
            axes = np.array(axes_list).reshape(self.ndim, self.ndim)
            plt.draw()
            for ax in axes[:, 0]:
                ax.yaxis.set_label_coords(-label_offset, 0.5)
            for ax in axes[-1, :]:
                ax.xaxis.set_label_coords(0.5, -label_offset)
            for ax in axes_list:
                ax.set_rasterized(True)
                ax.set_rasterization_zorder(-10)
            plt.tight_layout(h_pad=0.0, w_pad=0.0)
            fig.subplots_adjust(hspace=0.05, wspace=0.05)

            if add_prior:
                self.add_prior_to_corner(axes, samples_plt)

            fig_triangle.savefig('{}/{}_corner.png'.format(
                self.outdir, self.label), dpi=dpi)
1150
1151
1152
1153
1154
1155

    def add_prior_to_corner(self, axes, samples):
        for i, key in enumerate(self.theta_keys):
            ax = axes[i][i]
            xlim = ax.get_xlim()
            s = samples[:, i]
Gregory Ashton's avatar
Gregory Ashton committed
1156
            prior = self.generic_lnprior(**self.theta_prior[key])
1157
1158
1159
1160
1161
1162
            x = np.linspace(s.min(), s.max(), 100)
            ax2 = ax.twinx()
            ax2.get_yaxis().set_visible(False)
            ax2.plot(x, [prior(xi) for xi in x], '-r')
            ax.set_xlim(xlim)

1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
    def plot_prior_posterior(self, normal_stds=2):
        """ Plot the posterior in the context of the prior """
        fig, axes = plt.subplots(nrows=self.ndim, figsize=(8, 4*self.ndim))
        N = 1000
        from scipy.stats import gaussian_kde

        for i, (ax, key) in enumerate(zip(axes, self.theta_keys)):
            prior_dict = self.theta_prior[key]
            prior_func = self.generic_lnprior(**prior_dict)
            if prior_dict['type'] == 'unif':
                x = np.linspace(prior_dict['lower'], prior_dict['upper'], N)
                prior = prior_func(x)
                prior[0] = 0
                prior[-1] = 0
            elif prior_dict['type'] == 'norm':
                lower = prior_dict['loc'] - normal_stds * prior_dict['scale']
                upper = prior_dict['loc'] + normal_stds * prior_dict['scale']
                x = np.linspace(lower, upper, N)
                prior = prior_func(x)
1182
1183
1184
1185
1186
            elif prior_dict['type'] == 'halfnorm':
                lower = prior_dict['loc']
                upper = prior_dict['loc'] + normal_stds * prior_dict['scale']
                x = np.linspace(lower, upper, N)
                prior = [prior_func(xi) for xi in x]
Gregory Ashton's avatar
Gregory Ashton committed
1187
1188
1189
1190
1191
            elif prior_dict['type'] == 'neghalfnorm':
                upper = prior_dict['loc']
                lower = prior_dict['loc'] - normal_stds * prior_dict['scale']
                x = np.linspace(lower, upper, N)
                prior = [prior_func(xi) for xi in x]
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
            else:
                raise ValueError('Not implemented for prior type {}'.format(
                    prior_dict['type']))
            priorln = ax.plot(x, prior, 'r', label='prior')
            ax.set_xlabel(self.theta_symbols[i])

            s = self.samples[:, i]
            while len(s) > 10**4:
                # random downsample to avoid slow calculation of kde
                s = np.random.choice(s, size=int(len(s)/2.))
            kde = gaussian_kde(s)
            ax2 = ax.twinx()
            postln = ax2.plot(x, kde.pdf(x), 'k', label='posterior')
            ax2.set_yticklabels([])
            ax.set_yticklabels([])

        lns = priorln + postln
        labs = [l.get_label() for l in lns]
        axes[0].legend(lns, labs, loc=1, framealpha=0.8)

        fig.savefig('{}/{}_prior_posterior.png'.format(
            self.outdir, self.label))

1215
    def plot_cumulative_max(self, **kwargs):
Gregory Ashton's avatar
Gregory Ashton committed
1216
1217
1218
1219
        d, maxtwoF = self.get_max_twoF()
        for key, val in self.theta_prior.iteritems():
            if key not in d:
                d[key] = val
1220
1221
1222
1223
1224
1225

        if hasattr(self, 'search') is False:
            self.inititate_search_object()
        if self.binary is False:
            self.search.plot_twoF_cumulative(
                self.label, self.outdir, F0=d['F0'], F1=d['F1'], F2=d['F2'],
1226
1227
1228
                Alpha=d['Alpha'], Delta=d['Delta'],
                minStartTime=self.minStartTime, maxStartTime=self.maxStartTime,
                **kwargs)
1229
1230
1231
1232
1233
        else:
            self.search.plot_twoF_cumulative(
                self.label, self.outdir, F0=d['F0'], F1=d['F1'], F2=d['F2'],
                Alpha=d['Alpha'], Delta=d['Delta'], asini=d['asini'],
                period=d['period'], ecc=d['ecc'], argp=d['argp'], tp=d['argp'],
1234
1235
                minStartTime=self.minStartTime, maxStartTime=self.maxStartTime,
                **kwargs)
Gregory Ashton's avatar
Gregory Ashton committed
1236

Gregory Ashton's avatar
Gregory Ashton committed
1237
    def generic_lnprior(self, **kwargs):
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
        """ Return a lambda function of the pdf

        Parameters
        ----------
        kwargs: dict
            A dictionary containing 'type' of pdf and shape parameters

        """

        def logunif(x, a, b):
            above = x < b
            below = x > a
            if type(above) is not np.ndarray:
                if above and below:
                    return -np.log(b-a)
                else:
                    return -np.inf
            else:
                idxs = np.array([all(tup) for tup in zip(above, below)])
                p = np.zeros(len(x)) - np.inf
                p[idxs] = -np.log(b-a)
                return p

        def halfnorm(x, loc, scale):
            if x < 0:
                return -np.inf
            else:
                return -0.5*((x-loc)**2/scale**2+np.log(0.5*np.pi*scale**2))

        def cauchy(x, x0, gamma):
            return 1.0/(np.pi*gamma*(1+((x-x0)/gamma)**2))

        def exp(x, x0, gamma):
            if x > x0:
                return np.log(gamma) - gamma*(x - x0)
            else:
                return -np.inf

        if kwargs['type'] == 'unif':
            return lambda x: logunif(x, kwargs['lower'], kwargs['upper'])
        elif kwargs['type'] == 'halfnorm':
            return lambda x: halfnorm(x, kwargs['loc'], kwargs['scale'])
1280
1281
        elif kwargs['type'] == 'neghalfnorm':
            return lambda x: halfnorm(-x, kwargs['loc'], kwargs['scale'])
1282
1283
1284
1285
1286
1287
1288
        elif kwargs['type'] == 'norm':
            return lambda x: -0.5*((x - kwargs['loc'])**2/kwargs['scale']**2
                                   + np.log(2*np.pi*kwargs['scale']**2))
        else:
            logging.info("kwargs:", kwargs)
            raise ValueError("Print unrecognise distribution")

Gregory Ashton's avatar
Gregory Ashton committed
1289
    def generate_rv(self, **kwargs):
1290
1291
1292
1293
1294
1295
1296
1297
        dist_type = kwargs.pop('type')
        if dist_type == "unif":
            return np.random.uniform(low=kwargs['lower'], high=kwargs['upper'])
        if