pyfstat.py 74.6 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
plt.rcParams['text.usetex'] = True
25
plt.rcParams['axes.formatter.useoffset'] = False
26

27
28
29
30
31
32
33
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(' ', '')
34
            v = v.replace(' ', '').replace("'", "").replace('"', '').replace('\n', '')
35
36
37
38
39
40
            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')
41
42
43
    earth_ephem = None
    sun_ephem = None

44
45
46
47
48
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")
49
parser.add_argument("-u", "--use-old-data", action="store_true")
50
51
52
53
54
55
56
57
58
59
60
61
62
parser.add_argument('unittest_args', nargs='*')
args, unknown = parser.parse_known_args()
sys.argv[1:] = args.unittest_args

if args.quite:
    log_level = logging.WARNING
else:
    log_level = logging.DEBUG

logging.basicConfig(level=log_level,
                    format='%(asctime)s %(levelname)-8s: %(message)s',
                    datefmt='%H:%M')

63
64

def initializer(func):
65
    """ Automatically assigns the parameters to self """
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
    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):
83
    """ Read in a .par file, returns a dictionary of the values """
84
85
86
87
    filename = '{}/{}.par'.format(outdir, label)
    d = {}
    with open(filename, 'r') as f:
        for line in f:
88
89
90
            if len(line.split('=')) > 1:
                key, val = line.rstrip('\n').split(' = ')
                key = key.strip()
91
                d[key] = np.float64(eval(val.rstrip('; ')))
92
93
94
95
    return d


class BaseSearchClass(object):
96
    """ The base search class, provides ephemeris and general utilities """
97
98
99
100

    earth_ephem_default = earth_ephem
    sun_ephem_default = sun_ephem

101
102
103
104
105
106
107
108
109
    def add_log_file(self):
        ' Log output to a log-file, requires class to have outdir and label '
        logfilename = '{}/{}.log'.format(self.outdir, self.label)
        fh = logging.FileHandler(logfilename)
        fh.setFormatter(logging.Formatter(
            '%(asctime)s %(levelname)-8s: %(message)s',
            datefmt='%y-%m-%d %H:%M'))
        logging.getLogger().addHandler(fh)

110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
    def shift_matrix(self, n, dT):
        """ Generate the shift matrix """
        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
135
            lowest degree e.g [phi, F0, F1,...].
136
        dT: float
137
            difference between the two reference times as tref_new - tref_old.
138
139
140
141

        Returns
        -------
        theta_new: array-like shape (n,)
142
            vector of the coefficients as evaluate as the new reference time.
143
144
145
146
147
        """
        n = len(theta)
        m = self.shift_matrix(n, dT)
        return np.dot(m, theta)

148
    def calculate_thetas(self, theta, delta_thetas, tbounds, theta0_idx=0):
149
150
151
        """ Calculates the set of coefficients for the post-glitch signal """
        thetas = [theta]
        for i, dt in enumerate(delta_thetas):
152
153
154
155
156
157
158
159
160
161
162
163
164
            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]))
165
166
167
        return thetas


Gregory Ashton's avatar
Gregory Ashton committed
168
169
170
171
172
173
174
class ComputeFstat(object):
    """ Base class providing interface to lalpulsar.ComputeFstat """

    earth_ephem_default = earth_ephem
    sun_ephem_default = sun_ephem

    @initializer
175
    def __init__(self, tref, sftfilepath=None,
176
                 minStartTime=None, maxStartTime=None,
Gregory Ashton's avatar
Gregory Ashton committed
177
                 minCoverFreq=None, maxCoverFreq=None,
178
                 detector=None, earth_ephem=None, sun_ephem=None,
179
                 binary=False, transient=True, BSGL=False):
180
181
182
183
184
        """
        Parameters
        ----------
        tref: int
            GPS seconds of the reference time.
185
186
        sftfilepath: str
            File patern to match SFTs
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
        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.
        detector: str
            Two character reference to the data to use, specify None for no
            contraint.
        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.
        binary: bool
            If true, search of binary parameters.
        transient: bool
            If true, allow for the Fstat to be computed over a transient range.
202
203
        BSGL: bool
            If true, compute the BSGL rather than the twoF value.
204
205

        """
Gregory Ashton's avatar
Gregory Ashton committed
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220

        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
221
222
223
224
225
        if self.minStartTime:
            constraints.minStartTime = lal.LIGOTimeGPS(self.minStartTime)
        if self.maxStartTime:
            constraints.maxStartTime = lal.LIGOTimeGPS(self.maxStartTime)

226
        logging.info('Loading data matching pattern {}'.format(
227
228
                     self.sftfilepath))
        SFTCatalog = lalpulsar.SFTdataFind(self.sftfilepath, constraints)
Gregory Ashton's avatar
Gregory Ashton committed
229
        names = list(set([d.header.name for d in SFTCatalog.data]))
230
        epochs = [d.header.epoch for d in SFTCatalog.data]
231
        logging.info(
232
233
            'Loaded {} data files from detectors {} spanning {} to {}'.format(
                len(epochs), names, int(epochs[0]), int(epochs[-1])))
Gregory Ashton's avatar
Gregory Ashton committed
234
235
236
237
238
239

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

        logging.info('Initialising FstatInput')
        dFreq = 0
240
241
242
243
244
        if self.transient:
            self.whatToCompute = lalpulsar.FSTATQ_ATOMS_PER_DET
        else:
            self.whatToCompute = lalpulsar.FSTATQ_2F

Gregory Ashton's avatar
Gregory Ashton committed
245
246
247
248
249
250
251
252
        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
253
254
255
            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
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275

        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()

276
277
278
279
        if self.BSGL:
            logging.info('Initialising BSGL: this will fail if numDet < 2')
            # Tuning parameters - to be reviewed
            numDetectors = 2
Gregory Ashton's avatar
Gregory Ashton committed
280
            Fstar0sc = 15.
281
            oLGX = np.zeros(10)
Gregory Ashton's avatar
Gregory Ashton committed
282
            oLGX[:numDetectors] = 1./numDetectors
283
284
285
286
287
288
            self.BSGLSetup = lalpulsar.CreateBSGLSetup(numDetectors,
                                                       Fstar0sc,
                                                       oLGX,
                                                       False,
                                                       1)
            self.twoFX = np.zeros(10)
Gregory Ashton's avatar
Gregory Ashton committed
289
            self.whatToCompute = (self.whatToCompute +
290
291
                                  lalpulsar.FSTATQ_2F_PER_DET)

292
        if self.transient:
293
            logging.info('Initialising transient parameters')
294
295
296
297
298
299
            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
300

Gregory Ashton's avatar
Gregory Ashton committed
301
    def run_computefstatistic_single_point(self, tstart, tend, F0, F1,
302
303
304
                                           F2, Alpha, Delta, asini=None,
                                           period=None, ecc=None, tp=None,
                                           argp=None):
305
        """ Returns the twoF fully-coherently at a single point """
Gregory Ashton's avatar
Gregory Ashton committed
306
307
308
309

        self.PulsarDopplerParams.fkdot = np.array([F0, F1, F2, 0, 0, 0, 0])
        self.PulsarDopplerParams.Alpha = Alpha
        self.PulsarDopplerParams.Delta = Delta
310
311
312
313
314
315
        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
316
317
318
319

        lalpulsar.ComputeFstat(self.FstatResults,
                               self.FstatInput,
                               self.PulsarDopplerParams,
320
                               1,
Gregory Ashton's avatar
Gregory Ashton committed
321
322
323
                               self.whatToCompute
                               )

324
        if self.transient is False:
325
326
327
328
329
330
331
332
333
            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)
            return BSGL
334

335
336
        self.windowRange.t0 = int(tstart)  # TYPE UINT4
        self.windowRange.tau = int(tend - tstart)  # TYPE UINT4
337

Gregory Ashton's avatar
Gregory Ashton committed
338
        FS = lalpulsar.ComputeTransientFstatMap(
339
            self.FstatResults.multiFatoms[0], self.windowRange, False)
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358

        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)

        return BSGL
Gregory Ashton's avatar
Gregory Ashton committed
359
360
361


class SemiCoherentGlitchSearch(BaseSearchClass, ComputeFstat):
362
363
364
365
366
367
368
369
370
    """ 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
371
    def __init__(self, label, outdir, tref, tstart, tend, nglitch=0,
372
                 sftfilepath=None, theta0_idx=0, BSGL=False,
373
374
375
                 minCoverFreq=None, maxCoverFreq=None, minStartTime=None,
                 maxStartTime=None, detector=None, earth_ephem=None,
                 sun_ephem=None):
376
377
378
379
        """
        Parameters
        ----------
        label, outdir: str
380
381
382
383
384
385
            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).
386
387
        sftfilepath: str
            File patern to match SFTs
388
389
390
391
        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)
392
        minCoverFreq, maxCoverFreq: float
393
394
395
            The min and max cover frequency passed to CreateFstatInput, if
            either is None the range of frequencies in the SFT less 1Hz is
            used.
396
397
        detector: str
            Two character reference to the data to use, specify None for no
398
            contraint.
399
400
        earth_ephem, sun_ephem: str
            Paths of the two files containing positions of Earth and Sun,
401
402
            respectively at evenly spaced times, as passed to CreateFstatInput.
            If None defaults defined in BaseSearchClass will be used.
403
404
405
406
407
408
409
        """

        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
410
411
        self.transient = True
        self.binary = False
412
413
414
        self.init_computefstatistic_single_point()

    def compute_nglitch_fstat(self, F0, F1, F2, Alpha, Delta, *args):
415
        """ Returns the semi-coherent glitch summed twoF """
416
417
418

        args = list(args)
        tboundaries = [self.tstart] + args[-self.nglitch:] + [self.tend]
419
420
421
422
423
424
425
426
        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)

427
428
        thetas = self.calculate_thetas(theta, delta_thetas, tboundaries,
                                       theta0_idx=self.theta0_idx)
429
430

        twoFSum = 0
431
        for i, theta_i_at_tref in enumerate(thetas):
432
433
434
            ts, te = tboundaries[i], tboundaries[i+1]

            twoFVal = self.run_computefstatistic_single_point(
435
436
                ts, te, theta_i_at_tref[1], theta_i_at_tref[2],
                theta_i_at_tref[3], Alpha, Delta)
437
438
            twoFSum += twoFVal

439
440
441
        if np.isfinite(twoFSum):
            return twoFSum
        else:
442
            return -np.inf
443
444
445

    def compute_glitch_fstat_single(self, F0, F1, F2, Alpha, Delta, delta_F0,
                                    delta_F1, tglitch):
446
447
448
449
        """ Returns the semi-coherent glitch summed twoF for nglitch=1

        Note: used for testing
        """
450
451
452
453
454
455
456
457
458
459
460

        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
461
            self.tstart, tglitch, theta[0], theta[1], theta[2], Alpha,
462
463
464
465
466
467
            Delta)

        if tglitch == self.tend:
            return twoFsegA

        twoFsegB = self.run_computefstatistic_single_point(
Gregory Ashton's avatar
Gregory Ashton committed
468
            tglitch, self.tend, theta_post_glitch[0],
469
470
471
472
473
474
            theta_post_glitch[1], theta_post_glitch[2], Alpha,
            Delta)

        return twoFsegA + twoFsegB


Gregory Ashton's avatar
Gregory Ashton committed
475
476
class MCMCSearch(BaseSearchClass):
    """ MCMC search using ComputeFstat"""
477
    @initializer
478
    def __init__(self, label, outdir, sftfilepath, theta_prior, tref,
479
                 tstart, tend, nsteps=[100, 100, 100], nwalkers=100, ntemps=1,
480
                 log10temperature_min=-5, theta_initial=None, scatter_val=1e-4,
481
482
483
                 binary=False, BSGL=False, minCoverFreq=None,
                 maxCoverFreq=None, detector=None, earth_ephem=None,
                 sun_ephem=None, theta0_idx=0):
484
485
486
487
        """
        Parameters
        label, outdir: str
            A label and directory to read/write data from/to
488
489
        sftfilepath: str
            File patern to match SFTs
490
        theta_prior: dict
491
492
493
494
            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.
495
496
497
498
        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.
499
500
501
502
503
504
505
        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].
506
507
508
509
510
511
512
513
514
515
516
        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.
517
518
519
520
521
522
523
524
525
526
        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

        """

527
528
529
        self.minStartTime = tstart
        self.maxStartTime = tend

Gregory Ashton's avatar
Gregory Ashton committed
530
531
        if os.path.isdir(outdir) is False:
            os.mkdir(outdir)
532
        self.add_log_file()
Gregory Ashton's avatar
Gregory Ashton committed
533
534
        logging.info(
            'Set-up MCMC search for model {} on data {}'.format(
535
                self.label, self.sftfilepath))
536
        self.pickle_path = '{}/{}_saved_data.p'.format(self.outdir, self.label)
Gregory Ashton's avatar
Gregory Ashton committed
537
538
        self.theta_prior['tstart'] = self.tstart
        self.theta_prior['tend'] = self.tend
539
540
        self.unpack_input_theta()
        self.ndim = len(self.theta_keys)
541
542
543
544
        if self.log10temperature_min:
            self.betas = np.logspace(0, self.log10temperature_min, self.ntemps)
        else:
            self.betas = None
545

546
547
548
549
550
551
552
553
554
        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()
555
556
557
        self.log_input()

    def log_input(self):
558
        logging.info('theta_prior = {}'.format(self.theta_prior))
559
        logging.info('nwalkers={}'.format(self.nwalkers))
560
561
562
563
        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(
564
            self.log10temperature_min))
565
566
567

    def inititate_search_object(self):
        logging.info('Setting up search object')
Gregory Ashton's avatar
Gregory Ashton committed
568
        self.search = ComputeFstat(
569
570
571
572
            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,
573
            minStartTime=self.minStartTime, maxStartTime=self.maxStartTime)
574
575

    def logp(self, theta_vals, theta_prior, theta_keys, search):
Gregory Ashton's avatar
Gregory Ashton committed
576
        H = [self.generic_lnprior(**theta_prior[key])(p) for p, key in
577
578
579
580
581
582
             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
583
        FS = search.run_computefstatistic_single_point(*self.fixed_theta)
584
585
586
        return FS

    def unpack_input_theta(self):
Gregory Ashton's avatar
Gregory Ashton committed
587
588
        full_theta_keys = ['tstart', 'tend', 'F0', 'F1', 'F2', 'Alpha',
                           'Delta']
589
590
591
        if self.binary:
            full_theta_keys += [
                'asini', 'period', 'ecc', 'tp', 'argp']
592
593
        full_theta_keys_copy = copy.copy(full_theta_keys)

Gregory Ashton's avatar
Gregory Ashton committed
594
595
        full_theta_symbols = ['_', '_', '$f$', '$\dot{f}$', '$\ddot{f}$',
                              r'$\alpha$', r'$\delta$']
596
597
598
599
        if self.binary:
            full_theta_symbols += [
                'asini', 'period', 'period', 'ecc', 'tp', 'argp']

600
601
        self.theta_keys = []
        fixed_theta_dict = {}
602
        for key, val in self.theta_prior.iteritems():
603
604
            if type(val) is dict:
                fixed_theta_dict[key] = 0
Gregory Ashton's avatar
Gregory Ashton committed
605
                self.theta_keys.append(key)
606
607
608
609
610
611
            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
612
            full_theta_keys_copy.pop(full_theta_keys_copy.index(key))
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628

        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):
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
        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
665

Gregory Ashton's avatar
Gregory Ashton committed
666
667
668
669
670
671
672
673
674
675
    def run_sampler_with_progress_bar(self, sampler, ns, p0):
        try:
            from tqdm import tqdm
            for result in tqdm(sampler.sample(p0, iterations=ns), total=ns):
                pass
        except ImportError:
            sampler.run_mcmc(p0, ns)
        return sampler

    def run(self, proposal_scale_factor=2):
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691

        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),
692
            loglargs=(self.search,), betas=self.betas, a=proposal_scale_factor)
693

Gregory Ashton's avatar
Gregory Ashton committed
694
695
        p0 = self.generate_initial_p0()
        p0 = self.apply_corrections_to_p0(p0)
696
697
698
699
700
        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(
701
                j+1, ninit_steps, n))
Gregory Ashton's avatar
Gregory Ashton committed
702
            sampler = self.run_sampler_with_progress_bar(sampler, n, p0)
703
704
            logging.info("Mean acceptance fraction: {}"
                         .format(np.mean(sampler.acceptance_fraction, axis=1)))
705
706
707
            if self.ntemps > 1:
                logging.info("Tswap acceptance fraction: {}"
                             .format(sampler.tswap_acceptance_fraction))
Gregory Ashton's avatar
Gregory Ashton committed
708
            fig, axes = self.plot_walkers(sampler, symbols=self.theta_symbols)
709
710
711
            fig.savefig('{}/{}_init_{}_walkers.png'.format(
                self.outdir, self.label, j))

712
            p0 = self.get_new_p0(sampler)
Gregory Ashton's avatar
Gregory Ashton committed
713
            p0 = self.apply_corrections_to_p0(p0)
714
715
716
            self.check_initial_points(p0)
            sampler.reset()

Gregory Ashton's avatar
Gregory Ashton committed
717
718
719
720
        if len(self.nsteps) > 1:
            nburn = self.nsteps[-2]
        else:
            nburn = 0
721
722
723
        nprod = self.nsteps[-1]
        logging.info('Running final burn and prod with {} steps'.format(
            nburn+nprod))
Gregory Ashton's avatar
Gregory Ashton committed
724
        sampler = self.run_sampler_with_progress_bar(sampler, nburn+nprod, p0)
725
726
        logging.info("Mean acceptance fraction: {}"
                     .format(np.mean(sampler.acceptance_fraction, axis=1)))
727
728
729
        if self.ntemps > 1:
            logging.info("Tswap acceptance fraction: {}"
                         .format(sampler.tswap_acceptance_fraction))
730

Gregory Ashton's avatar
Gregory Ashton committed
731
732
        fig, axes = self.plot_walkers(sampler, symbols=self.theta_symbols,
                                      burnin_idx=nburn)
733
734
735
736
737
738
739
740
741
742
743
        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)

744
    def plot_corner(self, figsize=(7, 7),  tglitch_ratio=False,
745
746
747
748
749
750
751
752
753
                    add_prior=False, nstds=None, label_offset=0.4,
                    dpi=300, rc_context={}, **kwargs):

        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)
754
755
            theta_symbols_plt = [s.replace('_{glitch}', r'_\textrm{glitch}')
                                 for s in theta_symbols_plt]
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804

            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)
805
806
807
808
809
810

    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
811
            prior = self.generic_lnprior(**self.theta_prior[key])
812
813
814
815
816
817
            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)

Gregory Ashton's avatar
Gregory Ashton committed
818
    def generic_lnprior(self, **kwargs):
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
        """ 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'])
861
862
        elif kwargs['type'] == 'neghalfnorm':
            return lambda x: halfnorm(-x, kwargs['loc'], kwargs['scale'])
863
864
865
866
867
868
869
        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
870
    def generate_rv(self, **kwargs):
871
872
873
874
875
876
877
878
        dist_type = kwargs.pop('type')
        if dist_type == "unif":
            return np.random.uniform(low=kwargs['lower'], high=kwargs['upper'])
        if dist_type == "norm":
            return np.random.normal(loc=kwargs['loc'], scale=kwargs['scale'])
        if dist_type == "halfnorm":
            return np.abs(np.random.normal(loc=kwargs['loc'],
                                           scale=kwargs['scale']))
879
880
881
        if dist_type == "neghalfnorm":
            return -1 * np.abs(np.random.normal(loc=kwargs['loc'],
                                                scale=kwargs['scale']))
882
883
884
885
886
887
        if dist_type == "lognorm":
            return np.random.lognormal(
                mean=kwargs['loc'], sigma=kwargs['scale'])
        else:
            raise ValueError("dist_type {} unknown".format(dist_type))

Gregory Ashton's avatar
Gregory Ashton committed
888
    def plot_walkers(self, sampler, symbols=None, alpha=0.4, color="k", temp=0,
Gregory Ashton's avatar
Gregory Ashton committed
889
                     burnin_idx=None):
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
        """ Plot all the chains from a sampler """

        shape = sampler.chain.shape
        if len(shape) == 3:
            nwalkers, nsteps, ndim = shape
            chain = sampler.chain[:, :, :]
        if len(shape) == 4:
            ntemps, nwalkers, nsteps, ndim = shape
            if temp < ntemps:
                logging.info("Plotting temperature {} chains".format(temp))
            else:
                raise ValueError(("Requested temperature {} outside of"
                                  "available range").format(temp))
            chain = sampler.chain[temp, :, :, :]

        with plt.style.context(('classic')):
Gregory Ashton's avatar
Gregory Ashton committed
906
907
908
909
            fig = plt.figure(figsize=(8, 4*ndim))
            ax = fig.add_subplot(ndim+1, 1, 1)
            axes = [ax] + [fig.add_subplot(ndim+1, 1, i, sharex=ax)
                           for i in range(2, ndim+1)]
910

Gregory Ashton's avatar
Gregory Ashton committed
911
            idxs = np.arange(chain.shape[1])
912
913
            if ndim > 1:
                for i in range(ndim):
914
                    axes[i].ticklabel_format(useOffset=False, axis='y')
Gregory Ashton's avatar
Gregory Ashton committed
915
916
917
918
919
920
                    cs = chain[:, :, i].T
                    if burnin_idx:
                        axes[i].plot(idxs[:burnin_idx], cs[:burnin_idx],
                                     color="r", alpha=alpha)
                    axes[i].plot(idxs[burnin_idx:], cs[burnin_idx:], color="k",
                                 alpha=alpha)
921
922
                    if symbols:
                        axes[i].set_ylabel(symbols[i])
923
            else:
Gregory Ashton's avatar
Gregory Ashton committed
924
                cs = chain[:, :, temp].T
925
926
                axes.plot(cs, color='k', alpha=alpha)
                axes.ticklabel_format(useOffset=False, axis='y')
927

Gregory Ashton's avatar
Gregory Ashton committed
928
929
930
        axes.append(fig.add_subplot(ndim+1, 1, ndim+1))
        lnl = sampler.lnlikelihood[temp, :, :]
        if burnin_idx:
Gregory Ashton's avatar
Gregory Ashton committed
931
932
            axes[-1].hist(lnl[:, :burnin_idx].flatten(), bins=50,
                          histtype='step', color='r')
Gregory Ashton's avatar
Gregory Ashton committed
933
934
        axes[-1].hist(lnl[:, burnin_idx:].flatten(), bins=50, histtype='step',
                      color='k')
Gregory Ashton's avatar
Gregory Ashton committed
935
936
937
938
        if self.BSGL:
            axes[-1].set_xlabel(r'$\mathcal{B}_\mathrm{S/GL}$')
        else:
            axes[-1].set_xlabel(r'$2\mathcal{F}$')
Gregory Ashton's avatar
Gregory Ashton committed
939

940
941
        return fig, axes

Gregory Ashton's avatar
Gregory Ashton committed
942
943
944
945
946
    def apply_corrections_to_p0(self, p0):
        """ Apply any correction to the initial p0 values """
        return p0

    def generate_scattered_p0(self, p):
947
        """ Generate a set of p0s scattered about p """
Gregory Ashton's avatar
Gregory Ashton committed
948
        p0 = [[p + self.scatter_val * p * np.random.randn(self.ndim)
949
950
951
952
               for i in xrange(self.nwalkers)]
              for j in xrange(self.ntemps)]
        return p0

Gregory Ashton's avatar
Gregory Ashton committed
953
    def generate_initial_p0(self):
954
955
956
        """ Generate a set of init vals for the walkers """

        if type(self.theta_initial) == dict:
957
            logging.info('Generate initial values from initial dictionary')
958
            if hasattr(self, 'nglitch') and self.nglitch > 1:
959
                raise ValueError('Initial dict not implemented for nglitch>1')
Gregory Ashton's avatar
Gregory Ashton committed
960
            p0 = [[[self.generate_rv(**self.theta_initial[key])
961
962
963
                    for key in self.theta_keys]
                   for i in range(self.nwalkers)]
                  for j in range(self.ntemps)]
964
965
966
967
968
969
        elif type(self.theta_initial) == list:
            logging.info('Generate initial values from list of theta_initial')
            p0 = [[[self.generate_rv(**val)
                    for val in self.theta_initial]
                   for i in range(self.nwalkers)]
                  for j in range(self.ntemps)]
970
        elif self.theta_initial is None:
971
            logging.info('Generate initial values from prior dictionary')
Gregory Ashton's avatar
Gregory Ashton committed
972
            p0 = [[[self.generate_rv(**self.theta_prior[key])
973
974
975
976
                    for key in self.theta_keys]
                   for i in range(self.nwalkers)]
                  for j in range(self.ntemps)]
        elif len(self.theta_initial) == self.ndim:
Gregory Ashton's avatar
Gregory Ashton committed
977
            p0 = self.generate_scattered_p0(self.theta_initial)
978
979
980
981
982
        else:
            raise ValueError('theta_initial not understood')

        return p0

983
    def get_new_p0(self, sampler):
984
985
986
987
988
989
        """ Returns new initial positions for walkers are burn0 stage

        This returns new positions for all walkers by scattering points about
        the maximum posterior with scale `scatter_val`.

        """
Gregory Ashton's avatar
Gregory Ashton committed
990
991
992
993
        temp_idx = 0
        pF = sampler.chain[temp_idx, :, :, :]
        lnl = sampler.lnlikelihood[temp_idx, :, :]
        lnp = sampler.lnprobability[temp_idx, :, :]
994
995

        # General warnings about the state of lnp
Gregory Ashton's avatar
Gregory Ashton committed
996
        if np.any(np.isnan(lnp)):
997
998
            logging.warning(
                "Of {} lnprobs {} are nan".format(
Gregory Ashton's avatar
Gregory Ashton committed
999
1000
                    np.shape(lnp), np.sum(np.isnan(lnp))))
        if np.any(np.isposinf(lnp)):
1001
1002
            logging.warning(
                "Of {} lnprobs {} are +np.inf".format(
Gregory Ashton's avatar
Gregory Ashton committed
1003
1004
                    np.shape(lnp), np.sum(np.isposinf(lnp))))
        if np.any(np.isneginf(lnp)):
1005
1006
            logging.warning(
                "Of {} lnprobs {} are -np.inf".format(
Gregory Ashton's avatar
Gregory Ashton committed
1007
                    np.shape(lnp), np.sum(np.isneginf(lnp))))
1008

1009
1010
        lnp_finite = copy.copy(lnp)
        lnp_finite[np.isinf(lnp)] = np.nan
Gregory Ashton's avatar
Gregory Ashton committed
1011
1012
        idx = np.unravel_index(np.nanargmax(lnp_finite), lnp_finite.shape)
        p = pF[idx]
1013
        p0 = self.generate_scattered_p0(p)
1014

1015
1016
1017
1018
1019
1020
1021
1022
        self.search.BSGL = False
        twoF = self.logl(p, self.search)
        self.search.BSGL = self.BSGL

        logging.info(('Gen. new p0 from pos {} which had det. stat.={:2.1f},'
                      ' twoF={:2.1f} and lnp={:2.1f}')
                     .format(idx[1], lnl[idx], twoF, lnp_finite[idx]))

1023
1024
1025
1026
1027
        return p0

    def get_save_data_dictionary(self):
        d = dict(nsteps=self.nsteps, nwalkers=self.nwalkers,
                 ntemps=self.ntemps, theta_keys=self.theta_keys,
Gregory Ashton's avatar
Gregory Ashton committed
1028
                 theta_prior=self.theta_prior, scatter_val=self.scatter_val,
1029
1030
                 log10temperature_min=self.log10temperature_min,
                 theta0_idx=self.theta0_idx)
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
        return d

    def save_data(self, sampler, samples, lnprobs, lnlikes):
        d = self.get_save_data_dictionary()
        d['sampler'] = sampler
        d['samples'] = samples
        d['lnprobs'] = lnprobs
        d['lnlikes'] = lnlikes

        if os.path.isfile(self.pickle_path):
            logging.info('Saving backup of {} as {}.old'.format(
                self.pickle_path, self.pickle_path))
            os.rename(self.pickle_path, self.pickle_path+".old")
        with open(self.pickle_path, "wb") as File:
            pickle.dump(d, File)

    def get_list_of_matching_sfts(self):
1048
        matches = glob.glob(self.sftfilepath)
1049
1050
1051
1052
        if len(matches) > 0:
            return matches
        else:
            raise IOError('No sfts found matching {}'.format(
1053
                self.sftfilepath))
1054
1055
1056
1057
1058
1059
1060

    def get_saved_data(self):
        with open(self.pickle_path, "r") as File:
            d = pickle.load(File)
        return d

    def check_old_data_is_okay_to_use(self):
1061
1062
1063
1064
        if args.use_old_data:
            logging.info("Forcing use of old data")
            return True

1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
        if os.path.isfile(self.pickle_path) is False:
            logging.info('No pickled data found')
            return False

        oldest_sft = min([os.path.getmtime(f) for f in
                          self.get_list_of_matching_sfts()])
        if os.path.getmtime(self.pickle_path) < oldest_sft:
            logging.info('Pickled data outdates sft files')
            return False

        old_d = self.get_saved_data().copy()
        new_d = self.get_save_data_dictionary().copy()

        old_d.pop('samples')
        old_d.pop('sampler')
        old_d.pop('lnprobs')
        old_d.pop('lnlikes')

        mod_keys = []
        for key in new_d.keys():
            if key in old_d:
                if new_d[key] != old_d[key]:
                    mod_keys.append((key, old_d[key], new_d[key]))
            else:
1089
                raise ValueError('Keys {} not in old dictionary'.format(key))
1090
1091
1092
1093
1094
1095
1096
1097
1098

        if len(mod_keys) == 0:
            return True
        else:
            logging.warning("Saved data differs from requested")
            logging.info("Differences found in following keys:")
            for key in mod_keys:
                if len(key) == 3:
                    if np.isscalar(key[1]) or key[0] == 'nsteps':
1099
                        logging.info("    {} : {} -> {}".format(*key))
1100
                    else:
1101
                        logging.info("    " + key[0])
1102
1103
1104
1105
1106
                else:
                    logging.info(key)
            return False

    def get_max_twoF(self, threshold=0.05):
1107
        """ Returns the max likelihood sample and the corresponding 2F value
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121

        Note: the sample is returned as a dictionary along with an estimate of
        the standard deviation calculated from the std of all samples with a
        twoF within `threshold` (relative) to the max twoF

        """
        if any(np.isposinf(self.lnlikes)):
            logging.info('twoF values contain positive infinite values')
        if any(np.isneginf(self.lnlikes)):
            logging.info('twoF values contain negative infinite values')
        if any(np.isnan(self.lnlikes)):
            logging.info('twoF values contain nan')
        idxs = np.isfinite(self.lnlikes)
        jmax = np.nanargmax(self.lnlikes[idxs])
1122
        maxlogl = self.lnlikes[jmax]
1123
        d = OrderedDict()
1124

1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
        if self.BSGL:
            if hasattr(self, 'search') is False:
                self.inititate_search_object()
            p = self.samples[jmax]
            self.search.BSGL = False
            maxtwoF = self.logl(p, self.search)
            self.search.BSGL = self.BSGL
        else:
            maxtwoF = maxlogl

Gregory Ashton's avatar
Gregory Ashton committed
1135
        repeats = []
1136
        for i, k in enumerate(self.theta_keys):
Gregory Ashton's avatar
Gregory Ashton committed
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
            if k in d and k not in repeats:
                d[k+'_0'] = d[k]  # relabel the old key
                d.pop(k)
                repeats.append(k)
            if k in repeats:
                k = k + '_0'
                count = 1
                while k in d:
                    k = k.replace('_{}'.format(count-1), '_{}'.format(count))
                    count += 1
1147
1148
1149
1150
1151
            d[k] = self.samples[jmax][i]
        return d, maxtwoF

    def get_median_stds(self):
        """ Returns a dict of the median and std of all production samples """
1152
        d = OrderedDict()
Gregory Ashton's avatar
Gregory Ashton committed
1153
        repeats = []
1154
        for s, k in zip(self.samples.T, self.theta_keys):
Gregory Ashton's avatar
Gregory Ashton committed
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
            if k in d and k not in repeats:
                d[k+'_0'] = d[k]  # relabel the old key
                d[k+'_0_std'] = d[k+'_std']
                d.pop(k)
                d.pop(k+'_std')
                repeats.append(k)
            if k in repeats:
                k = k + '_0'
                count = 1
                while k in d:
                    k = k.replace('_{}'.format(count-1), '_{}'.format(count))
                    count += 1

1168
1169
1170
1171
1172
1173
1174
1175
            d[k] = np.median(s)
            d[k+'_std'] = np.std(s)
        return d

    def write_par(self, method='med'):
        """ Writes a .par of the best-fit params with an estimated std """
        logging.info('Writing {}/{}.par using the {} method'.format(
            self.outdir, self.label, method))
1176
1177
1178
1179

        median_std_d = self.get_median_stds()
        max_twoF_d, max_twoF = self.get_max_twoF()

Gregory Ashton's avatar
Gregory Ashton committed
1180
        logging.info('Writing par file with max twoF = {}'.format(max_twoF))
1181
1182
1183
        filename = '{}/{}.par'.format(self.outdir, self.label)
        with open(filename, 'w+') as f:
            f.write('MaxtwoF = {}\n'.format(max_twoF))
1184
            f.write('theta0_index = {}\n'.format(self.theta0_idx))
1185
            if method == 'med':
1186
1187
                for key, val in median_std_d.iteritems():
                    f.write('{} = {:1.16e}\n'.format(key, val))
1188
            if method == 'twoFmax':
1189
1190
1191
1192
                for key, val in max_twoF_d.iteritems():
                    f.write('{} = {:1.16e}\n'.format(key, val))

    def print_summary(self):
Gregory Ashton's avatar
Gregory Ashton committed
1193
        max_twoFd, max_twoF = self.get_max_twoF()
1194
        median_std_d = self.get_median_stds()
Gregory Ashton's avatar
Gregory Ashton committed
1195
        print('\nSummary:')
1196
        print('theta0 index: {}'.format(self.theta0_idx))
Gregory Ashton's avatar
Gregory Ashton committed
1197
1198
1199
1200
        print('Max twoF: {} with parameters:'.format(max_twoF))
        for k in np.sort(max_twoFd.keys()):
            print('  {:10s} = {:1.9e}'.format(k, max_twoFd[k]))
        print('\nMedian +/- std for production values')
1201
        for k in np.sort(median_std_d.keys()):
1202
            if 'std' not in k:
Gregory Ashton's avatar
Gregory Ashton committed
1203
                print('  {:10s} = {:1.9e} +/- {:1.9e}'.format(
1204
                    k, median_std_d[k], median_std_d[k+'_std']))
1205
1206


Gregory Ashton's avatar
Gregory Ashton committed
1207
1208
1209
class MCMCGlitchSearch(MCMCSearch):
    """ MCMC search using the SemiCoherentGlitchSearch """
    @initializer
1210
    def __init__(self, label, outdir, sftfilepath, theta_prior, tref,
1211
1212
                 tstart, tend, nglitch=1, nsteps=[100, 100, 100], nwalkers=100,
                 ntemps=1, log10temperature_min=-5, theta_initial=None,
1213
                 scatter_val=1e-4, dtglitchmin=1*86400, theta0_idx=0,
1214
                 detector=None, BSGL=False,
1215
                 minCoverFreq=None, maxCoverFreq=None, earth_ephem=None,
Gregory Ashton's avatar
Gregory Ashton committed
1216
1217
1218
1219
1220
                 sun_ephem=None):
        """
        Parameters
        label, outdir: str
            A label and directory to read/write data from/to
1221
1222
_        sftfilepath: str
            File patern to match SFTs
Gregory Ashton's avatar
Gregory Ashton committed
1223
1224
1225
1226
1227
1228
1229
1230
1231
        theta_prior: dict
            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.
        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.
1232
1233
1234
1235
        scatter_val, float or ndim array
            Size of scatter to use about the initialisation step, if given as
            an array it must be of length ndim and the order is given by
            theta_keys
Gregory Ashton's avatar
Gregory Ashton committed
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
        nglitch: int
            The number of glitches to allow
        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].
        dtglitchmin: int
            The minimum duration (in seconds) of a segment between two glitches
            or a glitch and the start/end of the data
1248
1249
1250
1251
1252
1253
        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).
1254
1255
1256
1257
        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)
1258
1259
1260
        detector: str
            Two character reference to the data to use, specify None for no
            contraint.
Gregory Ashton's avatar
Gregory Ashton committed
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
        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
1271
1272
        if os.path.isdir(outdir) is False:
            os.mkdir(outdir)
1273
        self.add_log_file()
Gregory Ashton's avatar
Gregory Ashton committed
1274
1275
        logging.info(('Set-up MCMC glitch search with {} glitches for model {}'
                      ' on data {}').format(self.nglitch, self.label,
1276
                                            self.sftfilepath))
1277
1278
        self.minStartTime = tstart
        self.maxStartTime = tend
Gregory Ashton's avatar
Gregory Ashton committed
1279
1280
1281
        self.pickle_path = '{}/{}_saved_data.p'.format(self.outdir, self.label)
        self.unpack_input_theta()
        self.ndim = len(self.theta_keys)
1282
1283
1284
1285
        if self.log10temperature_min:
            self.betas = np.logspace(0, self.log10temperature_min, self.ntemps)
        else:
            self.betas = None
Gregory Ashton's avatar
Gregory Ashton committed
1286
1287
1288
1289
1290
1291
1292
1293
1294
        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_t