pyfstat.py 81.2 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
18
19
20
import matplotlib.pyplot as plt
import emcee
import corner
import dill as pickle
21
import lal
22
23
import lalpulsar

24
25
26
27
28
29
try:
    from tqdm import tqdm
except ImportError:
    def tqdm(x):
        return x

30
plt.rcParams['text.usetex'] = True
31
plt.rcParams['axes.formatter.useoffset'] = False
32

33
34
35
36
37
38
39
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(' ', '')
40
            v = v.replace(' ', '').replace("'", "").replace('"', '').replace('\n', '')
41
42
43
44
45
46
            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')
47
48
49
    earth_ephem = None
    sun_ephem = None

50
51
52
53
54
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")
55
parser.add_argument("-u", "--use-old-data", action="store_true")
56
57
58
59
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
60
61
62
63

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

72
73

def initializer(func):
74
    """ Decorator function to automatically assign the parameters to self """
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
    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):
92
    """ Read in a .par file, returns a dictionary of the values """
93
94
95
96
    filename = '{}/{}.par'.format(outdir, label)
    d = {}
    with open(filename, 'r') as f:
        for line in f:
97
98
99
            if len(line.split('=')) > 1:
                key, val = line.rstrip('\n').split(' = ')
                key = key.strip()
100
                d[key] = np.float64(eval(val.rstrip('; ')))
101
102
103
104
    return d


class BaseSearchClass(object):
105
    """ The base search class, provides general functions """
106
107
108
109

    earth_ephem_default = earth_ephem
    sun_ephem_default = sun_ephem

110
    def add_log_file(self):
111
        """ Log output to a file, requires class to have outdir and label """
112
113
        logfilename = '{}/{}.log'.format(self.outdir, self.label)
        fh = logging.FileHandler(logfilename)
Gregory Ashton's avatar
Gregory Ashton committed
114
        fh.setLevel(logging.INFO)
115
116
117
118
119
        fh.setFormatter(logging.Formatter(
            '%(asctime)s %(levelname)-8s: %(message)s',
            datefmt='%y-%m-%d %H:%M'))
        logging.getLogger().addHandler(fh)

120
    def shift_matrix(self, n, dT):
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
        """ 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
        """

136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
        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
158
            lowest degree e.g [phi, F0, F1,...].
159
        dT: float
160
            difference between the two reference times as tref_new - tref_old.
161
162
163
164

        Returns
        -------
        theta_new: array-like shape (n,)
165
            vector of the coefficients as evaluate as the new reference time.
166
        """
167

168
169
170
171
        n = len(theta)
        m = self.shift_matrix(n, dT)
        return np.dot(m, theta)

172
    def calculate_thetas(self, theta, delta_thetas, tbounds, theta0_idx=0):
173
174
175
        """ Calculates the set of coefficients for the post-glitch signal """
        thetas = [theta]
        for i, dt in enumerate(delta_thetas):
176
177
178
179
180
181
182
183
184
185
186
187
188
            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]))
189
190
191
        return thetas


Gregory Ashton's avatar
Gregory Ashton committed
192
class ComputeFstat(object):
193
    """ Base class providing interface to `lalpulsar.ComputeFstat` """
Gregory Ashton's avatar
Gregory Ashton committed
194
195
196
197
198

    earth_ephem_default = earth_ephem
    sun_ephem_default = sun_ephem

    @initializer
199
200
    def __init__(self, tref, sftfilepath=None, minStartTime=None,
                 maxStartTime=None, binary=False, transient=True, BSGL=False,
Gregory Ashton's avatar
Gregory Ashton committed
201
202
203
                 BSGL_PREFACTOR=1, BSGL_FLOOR=None, detector=None,
                 minCoverFreq=None, maxCoverFreq=None, earth_ephem=None,
                 sun_ephem=None,
204
                 ):
205
206
207
208
209
        """
        Parameters
        ----------
        tref: int
            GPS seconds of the reference time.
210
211
        sftfilepath: str
            File patern to match SFTs
212
213
214
215
216
217
218
219
220
221
222
223
224
        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.
        BSGL_PREFACTOR: float
            If BSGL is True, one can specify a prefactor to multiply the
            computed BSGL value by, useful in MCMC searches to amplify the
            peaks.
Gregory Ashton's avatar
Gregory Ashton committed
225
226
        BSGL_FLOOR: float
            IF BSGL < BSGL_FLOOR -> BSGL_FLOOR
227
228
229
        detector: str
            Two character reference to the data to use, specify None for no
            contraint.
230
231
232
233
234
235
236
237
238
239
        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
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254

        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()

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

        logging.info('Initialising SFTCatalog')
        constraints = lalpulsar.SFTConstraints()
        if self.detector:
            constraints.detector = self.detector
255
256
257
258
259
        if self.minStartTime:
            constraints.minStartTime = lal.LIGOTimeGPS(self.minStartTime)
        if self.maxStartTime:
            constraints.maxStartTime = lal.LIGOTimeGPS(self.maxStartTime)

260
        logging.info('Loading data matching pattern {}'.format(
261
262
                     self.sftfilepath))
        SFTCatalog = lalpulsar.SFTdataFind(self.sftfilepath, constraints)
Gregory Ashton's avatar
Gregory Ashton committed
263
        names = list(set([d.header.name for d in SFTCatalog.data]))
264
        SFT_timestamps = [d.header.epoch for d in SFTCatalog.data]
265
        logging.info(
266
            'Loaded {} data files from detectors {} spanning {} to {}'.format(
267
268
269
                len(SFT_timestamps), names, int(SFT_timestamps[0]),
                int(SFT_timestamps[-1])))
        self.SFT_timestamps = SFT_timestamps
Gregory Ashton's avatar
Gregory Ashton committed
270
271
272
273
274
275

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

        logging.info('Initialising FstatInput')
        dFreq = 0
276
277
278
279
280
        if self.transient:
            self.whatToCompute = lalpulsar.FSTATQ_ATOMS_PER_DET
        else:
            self.whatToCompute = lalpulsar.FSTATQ_2F

Gregory Ashton's avatar
Gregory Ashton committed
281
282
283
284
285
286
287
288
        FstatOptionalArgs = lalpulsar.FstatOptionalArgsDefaults

        if self.minCoverFreq is None or self.maxCoverFreq is None:
            fA = SFTCatalog.data[0].header.f0
            numBins = SFTCatalog.data[0].numBins
            fB = fA + (numBins-1)*SFTCatalog.data[0].header.deltaF
            self.minCoverFreq = fA + 0.5
            self.maxCoverFreq = fB - 0.5
289
290
291
            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
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311

        self.FstatInput = lalpulsar.CreateFstatInput(SFTCatalog,
                                                     self.minCoverFreq,
                                                     self.maxCoverFreq,
                                                     dFreq,
                                                     ephems,
                                                     FstatOptionalArgs
                                                     )

        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()

312
        if self.BSGL:
Gregory Ashton's avatar
Gregory Ashton committed
313
314
            if len(names) < 2:
                raise ValueError("Can't use BSGL with single detector data")
315
316
317
318
319
320
321
322
323
324
            if self.BSGL_FLOOR is None:
                logging.info('Initialising BSGL with prefactor {:2.2f}'
                             .format(self.BSGL_PREFACTOR)
                             )
            else:
                logging.info('Initialising BSGL with prefactor {:0.2f} and '
                             'floor {}'.format(self.BSGL_PREFACTOR,
                                               self.BSGL_FLOOR)
                             )

325
326
            # Tuning parameters - to be reviewed
            numDetectors = 2
Gregory Ashton's avatar
Gregory Ashton committed
327
            Fstar0sc = 15.
328
            oLGX = np.zeros(10)
Gregory Ashton's avatar
Gregory Ashton committed
329
            oLGX[:numDetectors] = 1./numDetectors
330
331
332
            self.BSGLSetup = lalpulsar.CreateBSGLSetup(numDetectors,
                                                       Fstar0sc,
                                                       oLGX,
333
                                                       True,
334
335
                                                       1)
            self.twoFX = np.zeros(10)
Gregory Ashton's avatar
Gregory Ashton committed
336
            self.whatToCompute = (self.whatToCompute +
337
338
                                  lalpulsar.FSTATQ_2F_PER_DET)

339
        if self.transient:
340
            logging.info('Initialising transient parameters')
341
342
343
344
345
346
            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
347

Gregory Ashton's avatar
Gregory Ashton committed
348
    def run_computefstatistic_single_point(self, tstart, tend, F0, F1,
349
350
351
                                           F2, Alpha, Delta, asini=None,
                                           period=None, ecc=None, tp=None,
                                           argp=None):
352
        """ Returns the twoF fully-coherently at a single point """
Gregory Ashton's avatar
Gregory Ashton committed
353
354
355
356

        self.PulsarDopplerParams.fkdot = np.array([F0, F1, F2, 0, 0, 0, 0])
        self.PulsarDopplerParams.Alpha = Alpha
        self.PulsarDopplerParams.Delta = Delta
357
358
359
360
361
362
        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
363
364
365
366

        lalpulsar.ComputeFstat(self.FstatResults,
                               self.FstatInput,
                               self.PulsarDopplerParams,
367
                               1,
Gregory Ashton's avatar
Gregory Ashton committed
368
369
370
                               self.whatToCompute
                               )

371
        if self.transient is False:
372
373
374
375
376
377
378
379
            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)
            BSGL = lalpulsar.ComputeBSGL(twoF, self.twoFX,
                                         self.BSGLSetup)
380
381
            if self.BSGL_FLOOR is not None and BSGL < self.BSGL_FLOOR:
                return self.BSGL_FLOOR
Gregory Ashton's avatar
Gregory Ashton committed
382
383
            else:
                return self.BSGL_PREFACTOR * BSGL/np.log10(np.exp(1))
384

385
386
        self.windowRange.t0 = int(tstart)  # TYPE UINT4
        self.windowRange.tau = int(tend - tstart)  # TYPE UINT4
387

Gregory Ashton's avatar
Gregory Ashton committed
388
        FS = lalpulsar.ComputeTransientFstatMap(
389
            self.FstatResults.multiFatoms[0], self.windowRange, False)
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407

        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]
        BSGL = lalpulsar.ComputeBSGL(2*FS.F_mn.data[0][0], self.twoFX,
                                     self.BSGLSetup)

Gregory Ashton's avatar
Gregory Ashton committed
408
409
410
411
        if self.BSGL_FLOOR and BSGL < self.BSGL_FLOOR:
            return self.BSGL_FLOOR
        else:
            return self.BSGL_PREFACTOR * BSGL/np.log10(np.exp(1))
Gregory Ashton's avatar
Gregory Ashton committed
412

413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
    def calculate_twoF_cumulative(self, F0, F1, F2, Alpha, Delta, asini=None,
                                  period=None, ecc=None, tp=None, argp=None,
                                  tstart=None, tend=None, Npoints=1000,
                                  minfraction=0.01):
        """ Calculate the cumulative twoF along the obseration span """
        duration = tend - tstart
        taus = np.linspace(minfraction*duration, duration, Npoints)
        twoFs = []
        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,
430
                             title=None, **kwargs):
431
432
433
434
435
436
437
438
        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']))
        ax.set_ylabel(r'$\widetilde{2\mathcal{F}}_{\rm cumulative}$')
        ax.set_xlim(0, taus[-1]/86400)
439
        ax.set_title(title)
440
441
442
443
444
        if savefig:
            plt.savefig('{}/{}_twoFcumulative.png'.format(outdir, label))
        else:
            return ax

Gregory Ashton's avatar
Gregory Ashton committed
445
446

class SemiCoherentGlitchSearch(BaseSearchClass, ComputeFstat):
447
448
449
450
451
452
453
454
455
    """ A semi-coherent glitch search

    This implements a basic `semi-coherent glitch F-stat in which the data
    is divided into two segments either side of the proposed glitch and the
    fully-coherent F-stat in each segment is averaged to give the semi-coherent
    F-stat
    """

    @initializer
Gregory Ashton's avatar
Gregory Ashton committed
456
    def __init__(self, label, outdir, tref, tstart, tend, nglitch=0,
457
                 sftfilepath=None, theta0_idx=0, BSGL=False, BSGL_PREFACTOR=1,
Gregory Ashton's avatar
Gregory Ashton committed
458
459
460
                 BSGL_FLOOR=None, minStartTime=None, maxStartTime=None,
                 minCoverFreq=None, maxCoverFreq=None, detector=None,
                 earth_ephem=None, sun_ephem=None):
461
462
463
464
        """
        Parameters
        ----------
        label, outdir: str
465
466
467
468
469
470
            A label and directory to read/write data from/to.
        tref, tstart, tend: int
            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).
471
472
        sftfilepath: str
            File patern to match SFTs
473
474
475
476
        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)
477
478

        For all other parameters, see pyfstat.ComputeFStat.
479
480
481
482
483
484
485
        """

        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
486
487
        self.transient = True
        self.binary = False
488
489
490
        self.init_computefstatistic_single_point()

    def compute_nglitch_fstat(self, F0, F1, F2, Alpha, Delta, *args):
491
        """ Returns the semi-coherent glitch summed twoF """
492
493
494

        args = list(args)
        tboundaries = [self.tstart] + args[-self.nglitch:] + [self.tend]
495
496
497
498
499
500
501
502
        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)

503
504
        thetas = self.calculate_thetas(theta, delta_thetas, tboundaries,
                                       theta0_idx=self.theta0_idx)
505
506

        twoFSum = 0
507
        for i, theta_i_at_tref in enumerate(thetas):
508
509
510
            ts, te = tboundaries[i], tboundaries[i+1]

            twoFVal = self.run_computefstatistic_single_point(
511
512
                ts, te, theta_i_at_tref[1], theta_i_at_tref[2],
                theta_i_at_tref[3], Alpha, Delta)
513
514
            twoFSum += twoFVal

515
516
517
        if np.isfinite(twoFSum):
            return twoFSum
        else:
518
            return -np.inf
519
520
521

    def compute_glitch_fstat_single(self, F0, F1, F2, Alpha, Delta, delta_F0,
                                    delta_F1, tglitch):
522
523
524
525
        """ Returns the semi-coherent glitch summed twoF for nglitch=1

        Note: used for testing
        """
526
527
528
529
530
531
532
533
534
535
536

        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(
Gregory Ashton's avatar
Gregory Ashton committed
537
            self.tstart, tglitch, theta[0], theta[1], theta[2], Alpha,
538
539
540
541
542
543
            Delta)

        if tglitch == self.tend:
            return twoFsegA

        twoFsegB = self.run_computefstatistic_single_point(
Gregory Ashton's avatar
Gregory Ashton committed
544
            tglitch, self.tend, theta_post_glitch[0],
545
546
547
548
549
550
            theta_post_glitch[1], theta_post_glitch[2], Alpha,
            Delta)

        return twoFsegA + twoFsegB


Gregory Ashton's avatar
Gregory Ashton committed
551
552
class MCMCSearch(BaseSearchClass):
    """ MCMC search using ComputeFstat"""
553
    @initializer
554
    def __init__(self, label, outdir, sftfilepath, theta_prior, tref,
555
                 tstart, tend, nsteps=[100, 100, 100], nwalkers=100, ntemps=1,
556
                 log10temperature_min=-5, theta_initial=None, scatter_val=1e-10,
557
558
                 binary=False, BSGL=False, minCoverFreq=None,
                 maxCoverFreq=None, detector=None, earth_ephem=None,
559
                 sun_ephem=None, theta0_idx=0,
Gregory Ashton's avatar
Gregory Ashton committed
560
                 BSGL_PREFACTOR=1, BSGL_FLOOR=None):
561
562
563
564
        """
        Parameters
        label, outdir: str
            A label and directory to read/write data from/to
565
566
        sftfilepath: str
            File patern to match SFTs
567
        theta_prior: dict
568
569
570
571
            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.
572
573
574
575
        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.
576
577
578
579
580
581
582
        tref, tstart, tend: int
            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].
583
584
585
586
587
588
589
590
591
592
593
        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.
594
595
596
597
598
599
600
601
602
603
        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

        """

604
605
606
        self.minStartTime = tstart
        self.maxStartTime = tend

Gregory Ashton's avatar
Gregory Ashton committed
607
608
        if os.path.isdir(outdir) is False:
            os.mkdir(outdir)
609
        self.add_log_file()
Gregory Ashton's avatar
Gregory Ashton committed
610
611
        logging.info(
            'Set-up MCMC search for model {} on data {}'.format(
612
                self.label, self.sftfilepath))
613
        self.pickle_path = '{}/{}_saved_data.p'.format(self.outdir, self.label)
Gregory Ashton's avatar
Gregory Ashton committed
614
615
        self.theta_prior['tstart'] = self.tstart
        self.theta_prior['tend'] = self.tend
616
617
        self.unpack_input_theta()
        self.ndim = len(self.theta_keys)
618
619
620
621
        if self.log10temperature_min:
            self.betas = np.logspace(0, self.log10temperature_min, self.ntemps)
        else:
            self.betas = None
622

623
624
625
626
627
628
629
630
631
        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")

        self.old_data_is_okay_to_use = self.check_old_data_is_okay_to_use()
632
633
634
        self.log_input()

    def log_input(self):
635
        logging.info('theta_prior = {}'.format(self.theta_prior))
636
        logging.info('nwalkers={}'.format(self.nwalkers))
637
638
639
640
        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(
641
            self.log10temperature_min))
642
643
644

    def inititate_search_object(self):
        logging.info('Setting up search object')
Gregory Ashton's avatar
Gregory Ashton committed
645
        self.search = ComputeFstat(
646
647
648
649
            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,
650
            minStartTime=self.minStartTime, maxStartTime=self.maxStartTime,
Gregory Ashton's avatar
Gregory Ashton committed
651
            BSGL_PREFACTOR=self.BSGL_PREFACTOR, BSGL_FLOOR=self.BSGL_FLOOR)
652
653

    def logp(self, theta_vals, theta_prior, theta_keys, search):
Gregory Ashton's avatar
Gregory Ashton committed
654
        H = [self.generic_lnprior(**theta_prior[key])(p) for p, key in
655
656
657
658
659
660
             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]
Gregory Ashton's avatar
Gregory Ashton committed
661
        FS = search.run_computefstatistic_single_point(*self.fixed_theta)
662
663
664
        return FS

    def unpack_input_theta(self):
Gregory Ashton's avatar
Gregory Ashton committed
665
666
        full_theta_keys = ['tstart', 'tend', 'F0', 'F1', 'F2', 'Alpha',
                           'Delta']
667
668
669
        if self.binary:
            full_theta_keys += [
                'asini', 'period', 'ecc', 'tp', 'argp']
670
671
        full_theta_keys_copy = copy.copy(full_theta_keys)

Gregory Ashton's avatar
Gregory Ashton committed
672
673
        full_theta_symbols = ['_', '_', '$f$', '$\dot{f}$', '$\ddot{f}$',
                              r'$\alpha$', r'$\delta$']
674
675
676
677
        if self.binary:
            full_theta_symbols += [
                'asini', 'period', 'period', 'ecc', 'tp', 'argp']

678
679
        self.theta_keys = []
        fixed_theta_dict = {}
680
        for key, val in self.theta_prior.iteritems():
681
682
            if type(val) is dict:
                fixed_theta_dict[key] = 0
Gregory Ashton's avatar
Gregory Ashton committed
683
                self.theta_keys.append(key)
684
685
686
687
688
689
            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
690
            full_theta_keys_copy.pop(full_theta_keys_copy.index(key))
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706

        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):
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
        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
743

Gregory Ashton's avatar
Gregory Ashton committed
744
    def run_sampler_with_progress_bar(self, sampler, ns, p0):
745
746
        for result in tqdm(sampler.sample(p0, iterations=ns), total=ns):
            pass
Gregory Ashton's avatar
Gregory Ashton committed
747
748
749
        return sampler

    def run(self, proposal_scale_factor=2):
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765

        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),
766
            loglargs=(self.search,), betas=self.betas, a=proposal_scale_factor)
767

Gregory Ashton's avatar
Gregory Ashton committed
768
769
        p0 = self.generate_initial_p0()
        p0 = self.apply_corrections_to_p0(p0)
770
771
772
773
774
        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(
775
                j+1, ninit_steps, n))
Gregory Ashton's avatar
Gregory Ashton committed
776
            sampler = self.run_sampler_with_progress_bar(sampler, n, p0)
777
778
            logging.info("Mean acceptance fraction: {}"
                         .format(np.mean(sampler.acceptance_fraction, axis=1)))
779
780
781
            if self.ntemps > 1:
                logging.info("Tswap acceptance fraction: {}"
                             .format(sampler.tswap_acceptance_fraction))
Gregory Ashton's avatar
Gregory Ashton committed
782
            fig, axes = self.plot_walkers(sampler, symbols=self.theta_symbols)
783
784
785
            fig.savefig('{}/{}_init_{}_walkers.png'.format(
                self.outdir, self.label, j))

786
            p0 = self.get_new_p0(sampler)
Gregory Ashton's avatar
Gregory Ashton committed
787
            p0 = self.apply_corrections_to_p0(p0)
788
789
790
            self.check_initial_points(p0)
            sampler.reset()

Gregory Ashton's avatar
Gregory Ashton committed
791
792
793
794
        if len(self.nsteps) > 1:
            nburn = self.nsteps[-2]
        else:
            nburn = 0
795
796
797
        nprod = self.nsteps[-1]
        logging.info('Running final burn and prod with {} steps'.format(
            nburn+nprod))
Gregory Ashton's avatar
Gregory Ashton committed
798
        sampler = self.run_sampler_with_progress_bar(sampler, nburn+nprod, p0)
799
800
        logging.info("Mean acceptance fraction: {}"
                     .format(np.mean(sampler.acceptance_fraction, axis=1)))
801
802
803
        if self.ntemps > 1:
            logging.info("Tswap acceptance fraction: {}"
                         .format(sampler.tswap_acceptance_fraction))
804

Gregory Ashton's avatar
Gregory Ashton committed
805
806
        fig, axes = self.plot_walkers(sampler, symbols=self.theta_symbols,
                                      burnin_idx=nburn)
807
808
809
810
811
812
813
814
815
816
817
        fig.savefig('{}/{}_walkers.png'.format(self.outdir, self.label))

        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)

818
    def plot_corner(self, figsize=(7, 7),  tglitch_ratio=False,
819
820
821
                    add_prior=False, nstds=None, label_offset=0.4,
                    dpi=300, rc_context={}, **kwargs):

Gregory Ashton's avatar
Gregory Ashton committed
822
823
824
825
826
827
828
829
830
831
        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

832
833
834
835
836
837
        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)
838
839
            theta_symbols_plt = [s.replace('_{glitch}', r'_\textrm{glitch}')
                                 for s in theta_symbols_plt]
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888

            if tglitch_ratio:
                for j, k in enumerate(self.theta_keys):
                    if k == 'tglitch':
                        s = samples_plt[:, j]
                        samples_plt[:, j] = (s - self.tstart)/(
                                             self.tend - self.tstart)
                        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)
889
890
891
892
893
894

    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
895
            prior = self.generic_lnprior(**self.theta_prior[key])
896
897
898
899
900
901
            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)

902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
    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)
921
922
923
924
925
            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]
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
            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))

Gregory Ashton's avatar
Gregory Ashton committed
949
    def generic_lnprior(self, **kwargs):
950
951
952
953
954
955
956
957
958
959
960
961
962
963
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
        """ 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'])
992
993
        elif kwargs['type'] == 'neghalfnorm':
            return lambda x: halfnorm(-x, kwargs['loc'], kwargs['scale'])
994
995
996
997
998
999
1000
        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")