pyfstat.py 75.1 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
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
54
55
56
57

logger = logging.getLogger()
logger.setLevel(logging.DEBUG)
stream_handler = logging.StreamHandler()
58
if args.quite:
Gregory Ashton's avatar
Gregory Ashton committed
59
    stream_handler.setLevel(logging.WARNING)
60
else:
Gregory Ashton's avatar
Gregory Ashton committed
61
62
63
64
    stream_handler.setLevel(logging.DEBUG)
stream_handler.setFormatter(logging.Formatter(
    '%(asctime)s %(levelname)-8s: %(message)s', datefmt='%H:%M'))
logger.addHandler(stream_handler)
65

66
67

def initializer(func):
68
    """ Automatically assigns the parameters to self """
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
    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):
86
    """ Read in a .par file, returns a dictionary of the values """
87
88
89
90
    filename = '{}/{}.par'.format(outdir, label)
    d = {}
    with open(filename, 'r') as f:
        for line in f:
91
92
93
            if len(line.split('=')) > 1:
                key, val = line.rstrip('\n').split(' = ')
                key = key.strip()
94
                d[key] = np.float64(eval(val.rstrip('; ')))
95
96
97
98
    return d


class BaseSearchClass(object):
99
    """ The base search class, provides ephemeris and general utilities """
100
101
102
103

    earth_ephem_default = earth_ephem
    sun_ephem_default = sun_ephem

104
105
106
107
    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)
Gregory Ashton's avatar
Gregory Ashton committed
108
        fh.setLevel(logging.INFO)
109
110
111
112
113
        fh.setFormatter(logging.Formatter(
            '%(asctime)s %(levelname)-8s: %(message)s',
            datefmt='%y-%m-%d %H:%M'))
        logging.getLogger().addHandler(fh)

114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
    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
139
            lowest degree e.g [phi, F0, F1,...].
140
        dT: float
141
            difference between the two reference times as tref_new - tref_old.
142
143
144
145

        Returns
        -------
        theta_new: array-like shape (n,)
146
            vector of the coefficients as evaluate as the new reference time.
147
148
149
150
151
        """
        n = len(theta)
        m = self.shift_matrix(n, dT)
        return np.dot(m, theta)

152
    def calculate_thetas(self, theta, delta_thetas, tbounds, theta0_idx=0):
153
154
155
        """ Calculates the set of coefficients for the post-glitch signal """
        thetas = [theta]
        for i, dt in enumerate(delta_thetas):
156
157
158
159
160
161
162
163
164
165
166
167
168
            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]))
169
170
171
        return thetas


Gregory Ashton's avatar
Gregory Ashton committed
172
173
174
175
176
177
178
class ComputeFstat(object):
    """ Base class providing interface to lalpulsar.ComputeFstat """

    earth_ephem_default = earth_ephem
    sun_ephem_default = sun_ephem

    @initializer
179
    def __init__(self, tref, sftfilepath=None,
180
                 minStartTime=None, maxStartTime=None,
Gregory Ashton's avatar
Gregory Ashton committed
181
                 minCoverFreq=None, maxCoverFreq=None,
182
                 detector=None, earth_ephem=None, sun_ephem=None,
183
                 binary=False, transient=True, BSGL=False):
184
185
186
187
188
        """
        Parameters
        ----------
        tref: int
            GPS seconds of the reference time.
189
190
        sftfilepath: str
            File patern to match SFTs
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
        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.
206
207
        BSGL: bool
            If true, compute the BSGL rather than the twoF value.
208
209

        """
Gregory Ashton's avatar
Gregory Ashton committed
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224

        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
225
226
227
228
229
        if self.minStartTime:
            constraints.minStartTime = lal.LIGOTimeGPS(self.minStartTime)
        if self.maxStartTime:
            constraints.maxStartTime = lal.LIGOTimeGPS(self.maxStartTime)

230
        logging.info('Loading data matching pattern {}'.format(
231
232
                     self.sftfilepath))
        SFTCatalog = lalpulsar.SFTdataFind(self.sftfilepath, constraints)
Gregory Ashton's avatar
Gregory Ashton committed
233
        names = list(set([d.header.name for d in SFTCatalog.data]))
234
        epochs = [d.header.epoch for d in SFTCatalog.data]
235
        logging.info(
236
237
            'Loaded {} data files from detectors {} spanning {} to {}'.format(
                len(epochs), names, int(epochs[0]), int(epochs[-1])))
Gregory Ashton's avatar
Gregory Ashton committed
238
239
240
241
242
243

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

        logging.info('Initialising FstatInput')
        dFreq = 0
244
245
246
247
248
        if self.transient:
            self.whatToCompute = lalpulsar.FSTATQ_ATOMS_PER_DET
        else:
            self.whatToCompute = lalpulsar.FSTATQ_2F

Gregory Ashton's avatar
Gregory Ashton committed
249
250
251
252
253
254
255
256
        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
257
258
259
            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
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279

        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()

280
281
282
283
        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
284
            Fstar0sc = 15.
285
            oLGX = np.zeros(10)
Gregory Ashton's avatar
Gregory Ashton committed
286
            oLGX[:numDetectors] = 1./numDetectors
287
288
289
            self.BSGLSetup = lalpulsar.CreateBSGLSetup(numDetectors,
                                                       Fstar0sc,
                                                       oLGX,
290
                                                       True,
291
292
                                                       1)
            self.twoFX = np.zeros(10)
Gregory Ashton's avatar
Gregory Ashton committed
293
            self.whatToCompute = (self.whatToCompute +
294
295
                                  lalpulsar.FSTATQ_2F_PER_DET)

296
        if self.transient:
297
            logging.info('Initialising transient parameters')
298
299
300
301
302
303
            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
304

Gregory Ashton's avatar
Gregory Ashton committed
305
    def run_computefstatistic_single_point(self, tstart, tend, F0, F1,
306
307
308
                                           F2, Alpha, Delta, asini=None,
                                           period=None, ecc=None, tp=None,
                                           argp=None):
309
        """ Returns the twoF fully-coherently at a single point """
Gregory Ashton's avatar
Gregory Ashton committed
310

311
312
        BSGL_PREFACTOR = 10 * 1 / np.log10(np.exp(1))

Gregory Ashton's avatar
Gregory Ashton committed
313
314
315
        self.PulsarDopplerParams.fkdot = np.array([F0, F1, F2, 0, 0, 0, 0])
        self.PulsarDopplerParams.Alpha = Alpha
        self.PulsarDopplerParams.Delta = Delta
316
317
318
319
320
321
        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
322
323
324
325

        lalpulsar.ComputeFstat(self.FstatResults,
                               self.FstatInput,
                               self.PulsarDopplerParams,
326
                               1,
Gregory Ashton's avatar
Gregory Ashton committed
327
328
329
                               self.whatToCompute
                               )

330
        if self.transient is False:
331
332
333
334
335
336
337
338
            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)
339
            return BSGL_PREFACTOR * BSGL
340

341
342
        self.windowRange.t0 = int(tstart)  # TYPE UINT4
        self.windowRange.tau = int(tend - tstart)  # TYPE UINT4
343

Gregory Ashton's avatar
Gregory Ashton committed
344
        FS = lalpulsar.ComputeTransientFstatMap(
345
            self.FstatResults.multiFatoms[0], self.windowRange, False)
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363

        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)

364
        return BSGL_PREFACTOR * BSGL
Gregory Ashton's avatar
Gregory Ashton committed
365
366
367


class SemiCoherentGlitchSearch(BaseSearchClass, ComputeFstat):
368
369
370
371
372
373
374
375
376
    """ 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
377
    def __init__(self, label, outdir, tref, tstart, tend, nglitch=0,
378
                 sftfilepath=None, theta0_idx=0, BSGL=False,
379
380
381
                 minCoverFreq=None, maxCoverFreq=None, minStartTime=None,
                 maxStartTime=None, detector=None, earth_ephem=None,
                 sun_ephem=None):
382
383
384
385
        """
        Parameters
        ----------
        label, outdir: str
386
387
388
389
390
391
            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).
392
393
        sftfilepath: str
            File patern to match SFTs
394
395
396
397
        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)
398
        minCoverFreq, maxCoverFreq: float
399
400
401
            The min and max cover frequency passed to CreateFstatInput, if
            either is None the range of frequencies in the SFT less 1Hz is
            used.
402
403
        detector: str
            Two character reference to the data to use, specify None for no
404
            contraint.
405
406
        earth_ephem, sun_ephem: str
            Paths of the two files containing positions of Earth and Sun,
407
408
            respectively at evenly spaced times, as passed to CreateFstatInput.
            If None defaults defined in BaseSearchClass will be used.
409
410
411
412
413
414
415
        """

        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
416
417
        self.transient = True
        self.binary = False
418
419
420
        self.init_computefstatistic_single_point()

    def compute_nglitch_fstat(self, F0, F1, F2, Alpha, Delta, *args):
421
        """ Returns the semi-coherent glitch summed twoF """
422
423
424

        args = list(args)
        tboundaries = [self.tstart] + args[-self.nglitch:] + [self.tend]
425
426
427
428
429
430
431
432
        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)

433
434
        thetas = self.calculate_thetas(theta, delta_thetas, tboundaries,
                                       theta0_idx=self.theta0_idx)
435
436

        twoFSum = 0
437
        for i, theta_i_at_tref in enumerate(thetas):
438
439
440
            ts, te = tboundaries[i], tboundaries[i+1]

            twoFVal = self.run_computefstatistic_single_point(
441
442
                ts, te, theta_i_at_tref[1], theta_i_at_tref[2],
                theta_i_at_tref[3], Alpha, Delta)
443
444
            twoFSum += twoFVal

445
446
447
        if np.isfinite(twoFSum):
            return twoFSum
        else:
448
            return -np.inf
449
450
451

    def compute_glitch_fstat_single(self, F0, F1, F2, Alpha, Delta, delta_F0,
                                    delta_F1, tglitch):
452
453
454
455
        """ Returns the semi-coherent glitch summed twoF for nglitch=1

        Note: used for testing
        """
456
457
458
459
460
461
462
463
464
465
466

        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
467
            self.tstart, tglitch, theta[0], theta[1], theta[2], Alpha,
468
469
470
471
472
473
            Delta)

        if tglitch == self.tend:
            return twoFsegA

        twoFsegB = self.run_computefstatistic_single_point(
Gregory Ashton's avatar
Gregory Ashton committed
474
            tglitch, self.tend, theta_post_glitch[0],
475
476
477
478
479
480
            theta_post_glitch[1], theta_post_glitch[2], Alpha,
            Delta)

        return twoFsegA + twoFsegB


Gregory Ashton's avatar
Gregory Ashton committed
481
482
class MCMCSearch(BaseSearchClass):
    """ MCMC search using ComputeFstat"""
483
    @initializer
484
    def __init__(self, label, outdir, sftfilepath, theta_prior, tref,
485
                 tstart, tend, nsteps=[100, 100, 100], nwalkers=100, ntemps=1,
486
                 log10temperature_min=-5, theta_initial=None, scatter_val=1e-4,
487
488
489
                 binary=False, BSGL=False, minCoverFreq=None,
                 maxCoverFreq=None, detector=None, earth_ephem=None,
                 sun_ephem=None, theta0_idx=0):
490
491
492
493
        """
        Parameters
        label, outdir: str
            A label and directory to read/write data from/to
494
495
        sftfilepath: str
            File patern to match SFTs
496
        theta_prior: dict
497
498
499
500
            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.
501
502
503
504
        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.
505
506
507
508
509
510
511
        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].
512
513
514
515
516
517
518
519
520
521
522
        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.
523
524
525
526
527
528
529
530
531
532
        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

        """

533
534
535
        self.minStartTime = tstart
        self.maxStartTime = tend

Gregory Ashton's avatar
Gregory Ashton committed
536
537
        if os.path.isdir(outdir) is False:
            os.mkdir(outdir)
538
        self.add_log_file()
Gregory Ashton's avatar
Gregory Ashton committed
539
540
        logging.info(
            'Set-up MCMC search for model {} on data {}'.format(
541
                self.label, self.sftfilepath))
542
        self.pickle_path = '{}/{}_saved_data.p'.format(self.outdir, self.label)
Gregory Ashton's avatar
Gregory Ashton committed
543
544
        self.theta_prior['tstart'] = self.tstart
        self.theta_prior['tend'] = self.tend
545
546
        self.unpack_input_theta()
        self.ndim = len(self.theta_keys)
547
548
549
550
        if self.log10temperature_min:
            self.betas = np.logspace(0, self.log10temperature_min, self.ntemps)
        else:
            self.betas = None
551

552
553
554
555
556
557
558
559
560
        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()
561
562
563
        self.log_input()

    def log_input(self):
564
        logging.info('theta_prior = {}'.format(self.theta_prior))
565
        logging.info('nwalkers={}'.format(self.nwalkers))
566
567
568
569
        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(
570
            self.log10temperature_min))
571
572
573

    def inititate_search_object(self):
        logging.info('Setting up search object')
Gregory Ashton's avatar
Gregory Ashton committed
574
        self.search = ComputeFstat(
575
576
577
578
            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,
579
            minStartTime=self.minStartTime, maxStartTime=self.maxStartTime)
580
581

    def logp(self, theta_vals, theta_prior, theta_keys, search):
Gregory Ashton's avatar
Gregory Ashton committed
582
        H = [self.generic_lnprior(**theta_prior[key])(p) for p, key in
583
584
585
586
587
588
             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
589
        FS = search.run_computefstatistic_single_point(*self.fixed_theta)
590
591
592
        return FS

    def unpack_input_theta(self):
Gregory Ashton's avatar
Gregory Ashton committed
593
594
        full_theta_keys = ['tstart', 'tend', 'F0', 'F1', 'F2', 'Alpha',
                           'Delta']
595
596
597
        if self.binary:
            full_theta_keys += [
                'asini', 'period', 'ecc', 'tp', 'argp']
598
599
        full_theta_keys_copy = copy.copy(full_theta_keys)

Gregory Ashton's avatar
Gregory Ashton committed
600
601
        full_theta_symbols = ['_', '_', '$f$', '$\dot{f}$', '$\ddot{f}$',
                              r'$\alpha$', r'$\delta$']
602
603
604
605
        if self.binary:
            full_theta_symbols += [
                'asini', 'period', 'period', 'ecc', 'tp', 'argp']

606
607
        self.theta_keys = []
        fixed_theta_dict = {}
608
        for key, val in self.theta_prior.iteritems():
609
610
            if type(val) is dict:
                fixed_theta_dict[key] = 0
Gregory Ashton's avatar
Gregory Ashton committed
611
                self.theta_keys.append(key)
612
613
614
615
616
617
            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
618
            full_theta_keys_copy.pop(full_theta_keys_copy.index(key))
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634

        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):
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
665
666
667
668
669
670
        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
671

Gregory Ashton's avatar
Gregory Ashton committed
672
673
674
675
676
677
678
679
680
681
    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):
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697

        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),
698
            loglargs=(self.search,), betas=self.betas, a=proposal_scale_factor)
699

Gregory Ashton's avatar
Gregory Ashton committed
700
701
        p0 = self.generate_initial_p0()
        p0 = self.apply_corrections_to_p0(p0)
702
703
704
705
706
        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(
707
                j+1, ninit_steps, n))
Gregory Ashton's avatar
Gregory Ashton committed
708
            sampler = self.run_sampler_with_progress_bar(sampler, n, p0)
709
710
            logging.info("Mean acceptance fraction: {}"
                         .format(np.mean(sampler.acceptance_fraction, axis=1)))
711
712
713
            if self.ntemps > 1:
                logging.info("Tswap acceptance fraction: {}"
                             .format(sampler.tswap_acceptance_fraction))
Gregory Ashton's avatar
Gregory Ashton committed
714
            fig, axes = self.plot_walkers(sampler, symbols=self.theta_symbols)
715
716
717
            fig.savefig('{}/{}_init_{}_walkers.png'.format(
                self.outdir, self.label, j))

718
            p0 = self.get_new_p0(sampler)
Gregory Ashton's avatar
Gregory Ashton committed
719
            p0 = self.apply_corrections_to_p0(p0)
720
721
722
            self.check_initial_points(p0)
            sampler.reset()

Gregory Ashton's avatar
Gregory Ashton committed
723
724
725
726
        if len(self.nsteps) > 1:
            nburn = self.nsteps[-2]
        else:
            nburn = 0
727
728
729
        nprod = self.nsteps[-1]
        logging.info('Running final burn and prod with {} steps'.format(
            nburn+nprod))
Gregory Ashton's avatar
Gregory Ashton committed
730
        sampler = self.run_sampler_with_progress_bar(sampler, nburn+nprod, p0)
731
732
        logging.info("Mean acceptance fraction: {}"
                     .format(np.mean(sampler.acceptance_fraction, axis=1)))
733
734
735
        if self.ntemps > 1:
            logging.info("Tswap acceptance fraction: {}"
                         .format(sampler.tswap_acceptance_fraction))
736

Gregory Ashton's avatar
Gregory Ashton committed
737
738
        fig, axes = self.plot_walkers(sampler, symbols=self.theta_symbols,
                                      burnin_idx=nburn)
739
740
741
742
743
744
745
746
747
748
749
        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)

750
    def plot_corner(self, figsize=(7, 7),  tglitch_ratio=False,
751
752
753
754
755
756
757
758
759
                    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)
760
761
            theta_symbols_plt = [s.replace('_{glitch}', r'_\textrm{glitch}')
                                 for s in theta_symbols_plt]
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
805
806
807
808
809
810

            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)
811
812
813
814
815
816

    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
817
            prior = self.generic_lnprior(**self.theta_prior[key])
818
819
820
821
822
823
            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
824
    def generic_lnprior(self, **kwargs):
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
861
862
863
864
865
866
        """ 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'])
867
868
        elif kwargs['type'] == 'neghalfnorm':
            return lambda x: halfnorm(-x, kwargs['loc'], kwargs['scale'])
869
870
871
872
873
874
875
        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
876
    def generate_rv(self, **kwargs):
877
878
879
880
881
882
883
884
        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']))
885
886
887
        if dist_type == "neghalfnorm":
            return -1 * np.abs(np.random.normal(loc=kwargs['loc'],
                                                scale=kwargs['scale']))
888
889
890
891
892
893
        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
894
    def plot_walkers(self, sampler, symbols=None, alpha=0.4, color="k", temp=0,
Gregory Ashton's avatar
Gregory Ashton committed
895
                     burnin_idx=None):
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
        """ 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
912
913
914
915
            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)]
916

Gregory Ashton's avatar
Gregory Ashton committed
917
            idxs = np.arange(chain.shape[1])
918
919
            if ndim > 1:
                for i in range(ndim):
920
                    axes[i].ticklabel_format(useOffset=False, axis='y')
Gregory Ashton's avatar
Gregory Ashton committed
921
922
923
924
925
926
                    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)
927
928
                    if symbols:
                        axes[i].set_ylabel(symbols[i])
929
            else:
Gregory Ashton's avatar
Gregory Ashton committed
930
                cs = chain[:, :, temp].T
931
932
                axes.plot(cs, color='k', alpha=alpha)
                axes.ticklabel_format(useOffset=False, axis='y')
933

Gregory Ashton's avatar
Gregory Ashton committed
934
935
936
        axes.append(fig.add_subplot(ndim+1, 1, ndim+1))
        lnl = sampler.lnlikelihood[temp, :, :]
        if burnin_idx:
Gregory Ashton's avatar
Gregory Ashton committed
937
938
            axes[-1].hist(lnl[:, :burnin_idx].flatten(), bins=50,
                          histtype='step', color='r')
Gregory Ashton's avatar
Gregory Ashton committed
939
940
        axes[-1].hist(lnl[:, burnin_idx:].flatten(), bins=50, histtype='step',
                      color='k')
Gregory Ashton's avatar
Gregory Ashton committed
941
942
943
944
        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
945

946
947
        return fig, axes

Gregory Ashton's avatar
Gregory Ashton committed
948
949
950
951
952
    def apply_corrections_to_p0(self, p0):
        """ Apply any correction to the initial p0 values """
        return p0

    def generate_scattered_p0(self, p):
953
        """ Generate a set of p0s scattered about p """
Gregory Ashton's avatar
Gregory Ashton committed
954
        p0 = [[p + self.scatter_val * p * np.random.randn(self.ndim)
955
956
957
958
               for i in xrange(self.nwalkers)]
              for j in xrange(self.ntemps)]
        return p0

Gregory Ashton's avatar
Gregory Ashton committed
959
    def generate_initial_p0(self):
960
961
962
        """ Generate a set of init vals for the walkers """

        if type(self.theta_initial) == dict:
963
            logging.info('Generate initial values from initial dictionary')
964
            if hasattr(self, 'nglitch') and self.nglitch > 1:
965
                raise ValueError('Initial dict not implemented for nglitch>1')
Gregory Ashton's avatar
Gregory Ashton committed
966
            p0 = [[[self.generate_rv(**self.theta_initial[key])
967
968
969
                    for key in self.theta_keys]
                   for i in range(self.nwalkers)]
                  for j in range(self.ntemps)]
970
971
972
973
974
975
        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)]
976
        elif self.theta_initial is None:
977
            logging.info('Generate initial values from prior dictionary')
Gregory Ashton's avatar
Gregory Ashton committed
978
            p0 = [[[self.generate_rv(**self.theta_prior[key])
979
980
981
982
                    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
983
            p0 = self.generate_scattered_p0(self.theta_initial)
984
985
986
987
988
        else:
            raise ValueError('theta_initial not understood')

        return p0

989
    def get_new_p0(self, sampler):
990
991
992
993
994
995
        """ 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
996
997
998
999
        temp_idx = 0
        pF = sampler.chain[temp_idx, :, :, :]
        lnl = sampler.lnlikelihood[temp_idx, :, :]
        lnp = sampler.lnprobability[temp_idx, :, :]
1000
1001

        # General warnings about the state of lnp
Gregory Ashton's avatar
Gregory Ashton committed
1002
        if np.any(np.isnan(lnp)):
1003
1004
            logging.warning(
                "Of {} lnprobs {} are nan".format(
Gregory Ashton's avatar
Gregory Ashton committed
1005
1006
                    np.shape(lnp), np.sum(np.isnan(lnp))))
        if np.any(np.isposinf(lnp)):
1007
1008
            logging.warning(
                "Of {} lnprobs {} are +np.inf".format(
Gregory Ashton's avatar
Gregory Ashton committed
1009
1010
                    np.shape(lnp), np.sum(np.isposinf(lnp))))
        if np.any(np.isneginf(lnp)):
1011
1012
            logging.warning(
                "Of {} lnprobs {} are -np.inf".format(
Gregory Ashton's avatar
Gregory Ashton committed
1013
                    np.shape(lnp), np.sum(np.isneginf(lnp))))
1014

1015
1016
        lnp_finite = copy.copy(lnp)
        lnp_finite[np.isinf(lnp)] = np.nan
Gregory Ashton's avatar
Gregory Ashton committed
1017
1018
        idx = np.unravel_index(np.nanargmax(lnp_finite), lnp_finite.shape)
        p = pF[idx]
1019
        p0 = self.generate_scattered_p0(p)
1020

1021
1022
1023
1024
1025
1026
1027
1028
        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]))

1029
1030
1031
1032
1033
        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
1034
                 theta_prior=self.theta_prior, scatter_val=self.scatter_val,
1035
1036
                 log10temperature_min=self.log10temperature_min,
                 theta0_idx=self.theta0_idx)
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
        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):
1054
        matches = glob.glob(self.sftfilepath)
1055
1056
1057
1058
        if len(matches) > 0:
            return matches
        else:
            raise IOError('No sfts found matching {}'.format(
1059
                self.sftfilepath))
1060
1061
1062
1063
1064
1065
1066

    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):
1067
1068
1069
1070
        if args.use_old_data:
            logging.info("Forcing use of old data")
            return True

1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
        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:
1095
                raise ValueError('Keys {} not in old dictionary'.format(key))
1096
1097
1098
1099
1100
1101
1102
1103
1104

        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':
1105
                        logging.info("    {} : {} -> {}".format(*key))
1106
                    else:
1107
                        logging.info("    " + key[0])
1108
1109
1110
1111
1112
                else:
                    logging.info(key)
            return False

    def get_max_twoF(self, threshold=0.05):
1113
        """ Returns the max likelihood sample and the corresponding 2F value
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127

        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])
1128
        maxlogl = self.lnlikes[jmax]
1129
        d = OrderedDict()
1130

1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
        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
1141
        repeats = []
1142
        for i, k in enumerate(self.theta_keys):
Gregory Ashton's avatar
Gregory Ashton committed
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
            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
1153
1154
1155
1156
1157
            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 """
1158
        d = OrderedDict()
Gregory Ashton's avatar
Gregory Ashton committed
1159
        repeats = []
1160
        for s, k in zip(self.samples.T, self.theta_keys):
Gregory Ashton's avatar
Gregory Ashton committed
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
            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

1174
1175
1176
1177
1178
1179
1180
1181
            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))
1182
1183
1184
1185

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

Gregory Ashton's avatar
Gregory Ashton committed
1186
        logging.info('Writing par file with max twoF = {}'.format(max_twoF))
1187
1188
1189
        filename = '{}/{}.par'.format(self.outdir, self.label)
        with open(filename, 'w+') as f:
            f.write('MaxtwoF = {}\n'.format(max_twoF))
1190
            f.write('theta0_index = {}\n'.format(self.theta0_idx))
1191
            if method == 'med':
1192
1193
                for key, val in median_std_d.iteritems():
                    f.write('{} = {:1.16e}\n'.format(key, val))
1194
            if method == 'twoFmax':
1195
1196
1197
1198
                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
1199
        max_twoFd, max_twoF = self.get_max_twoF()
1200
        median_std_d = self.get_median_stds()
Gregory Ashton's avatar
Gregory Ashton committed
1201
        print('\nSummary:')
1202
        print('theta0 index: {}'.format(self.theta0_idx))
Gregory Ashton's avatar
Gregory Ashton committed
1203
1204
1205
1206
        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')
1207
        for k in np.sort(median_std_d.keys()):
1208
            if 'std' not in k:
Gregory Ashton's avatar
Gregory Ashton committed
1209
                print('  {:10s} = {:1.9e} +/- {:1.9e}'.format(
1210
                    k, median_std_d[k], median_std_d[k+'_std']))
1211
1212


Gregory Ashton's avatar
Gregory Ashton committed
1213
1214
1215
class MCMCGlitchSearch(MCMCSearch):
    """ MCMC search using the SemiCoherentGlitchSearch """
    @initializer
1216
    def __init__(self, label, outdir, sftfilepath, theta_prior, tref,
1217
1218
                 tstart, tend, nglitch=1, nsteps=[100, 100, 100], nwalkers=100,
                 ntemps=1, log10temperature_min=-5, theta_initial=None,
1219
                 scatter_val=1e-4, dtglitchmin=1*86400, theta0_idx=0,
1220
                 detector=None, BSGL=False,
1221
                 minCoverFreq=None, maxCoverFreq=None, earth_ephem=None,
Gregory Ashton's avatar
Gregory Ashton committed
1222
1223
1224
1225
1226
                 sun_ephem=None):
        """
        Parameters
        label, outdir: str
            A label and directory to read/write data from/to
1227
1228
_        sftfilepath: str
            File patern to match SFTs
Gregory Ashton's avatar
Gregory Ashton committed
1229
1230
1231
1232
1233
1234
1235
1236
1237
        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.
1238
1239
1240
1241
        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
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
        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
1254
1255
1256
1257
1258
1259
        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).
1260
1261
1262
1263
        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)
1264
1265
1266
        detector: str
            Two character reference to the data to use, specify None for no
            contraint.
Gregory Ashton's avatar
Gregory Ashton committed
1267
1268
1269
1270
1271
1272
1273
1274