pyfstat.py 79 KB
Newer Older
1
2
3
4
5
6
7
8
9
10
""" Classes for various types of searches using ComputeFstatistic """
import os
import sys
import itertools
import logging
import argparse
import copy
import glob
import inspect
from functools import wraps
11
import subprocess
12
from collections import OrderedDict
13
14
15

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

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

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

33
34
35
36
37
38
39
config_file = os.path.expanduser('~')+'/.pyfstat.conf'
if os.path.isfile(config_file):
    d = {}
    with open(config_file, 'r') as f:
        for line in f:
            k, v = line.split('=')
            k = k.replace(' ', '')
40
            v = v.replace(' ', '').replace("'", "").replace('"', '').replace('\n', '')
41
42
43
44
45
46
            d[k] = v
    earth_ephem = d['earth_ephem']
    sun_ephem = d['sun_ephem']
else:
    logging.warning('No ~/.pyfstat.conf file found please provide the paths '
                    'when initialising searches')
47
48
49
    earth_ephem = None
    sun_ephem = None

50
51
52
53
54
parser = argparse.ArgumentParser()
parser.add_argument("-q", "--quite", help="Decrease output verbosity",
                    action="store_true")
parser.add_argument("-c", "--clean", help="Don't use cached data",
                    action="store_true")
55
parser.add_argument("-u", "--use-old-data", action="store_true")
56
57
58
59
parser.add_argument('unittest_args', nargs='*')
args, unknown = parser.parse_known_args()
sys.argv[1:] = args.unittest_args

Gregory Ashton's avatar
Gregory Ashton committed
60
61
62
63

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

72
73

def initializer(func):
74
    """ Decorator function to automatically assign the parameters to self """
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
    names, varargs, keywords, defaults = inspect.getargspec(func)

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

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

        func(self, *args, **kargs)

    return wrapper


def read_par(label, outdir):
92
    """ Read in a .par file, returns a dictionary of the values """
93
94
95
96
    filename = '{}/{}.par'.format(outdir, label)
    d = {}
    with open(filename, 'r') as f:
        for line in f:
97
98
99
            if len(line.split('=')) > 1:
                key, val = line.rstrip('\n').split(' = ')
                key = key.strip()
100
                d[key] = np.float64(eval(val.rstrip('; ')))
101
102
103
104
    return d


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

    earth_ephem_default = earth_ephem
    sun_ephem_default = sun_ephem

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

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

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

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

136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
        m = np.zeros((n, n))
        factorial = np.math.factorial
        for i in range(n):
            for j in range(n):
                if i == j:
                    m[i, j] = 1.0
                elif i > j:
                    m[i, j] = 0.0
                else:
                    if i == 0:
                        m[i, j] = 2*np.pi*float(dT)**(j-i) / factorial(j-i)
                    else:
                        m[i, j] = float(dT)**(j-i) / factorial(j-i)
        return m

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

        Parameters
        ----------
        theta: array-like, shape (n,)
            vector of the expansion coefficients to transform starting from the
158
            lowest degree e.g [phi, F0, F1,...].
159
        dT: float
160
            difference between the two reference times as tref_new - tref_old.
161
162
163
164

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

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

172
    def calculate_thetas(self, theta, delta_thetas, tbounds, theta0_idx=0):
173
174
175
        """ Calculates the set of coefficients for the post-glitch signal """
        thetas = [theta]
        for i, dt in enumerate(delta_thetas):
176
177
178
179
180
181
182
183
184
185
186
187
188
            if i < theta0_idx:
                pre_theta_at_ith_glitch = self.shift_coefficients(
                    thetas[0], tbounds[i+1] - self.tref)
                post_theta_at_ith_glitch = pre_theta_at_ith_glitch - dt
                thetas.insert(0, self.shift_coefficients(
                    post_theta_at_ith_glitch, self.tref - tbounds[i+1]))

            elif i >= theta0_idx:
                pre_theta_at_ith_glitch = self.shift_coefficients(
                    thetas[i], tbounds[i+1] - self.tref)
                post_theta_at_ith_glitch = pre_theta_at_ith_glitch + dt
                thetas.append(self.shift_coefficients(
                    post_theta_at_ith_glitch, self.tref - tbounds[i+1]))
189
190
191
        return thetas


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

    earth_ephem_default = earth_ephem
    sun_ephem_default = sun_ephem

    @initializer
199
200
    def __init__(self, tref, sftfilepath=None, minStartTime=None,
                 maxStartTime=None, binary=False, transient=True, BSGL=False,
Gregory Ashton's avatar
Gregory Ashton committed
201
202
203
                 BSGL_PREFACTOR=1, BSGL_FLOOR=None, detector=None,
                 minCoverFreq=None, maxCoverFreq=None, earth_ephem=None,
                 sun_ephem=None,
204
                 ):
205
206
207
208
209
        """
        Parameters
        ----------
        tref: int
            GPS seconds of the reference time.
210
211
        sftfilepath: str
            File patern to match SFTs
212
213
214
215
216
217
218
219
220
221
222
223
224
        minStartTime, maxStartTime: float GPStime
            Only use SFTs with timestemps starting from (including, excluding)
            this epoch
        binary: bool
            If true, search of binary parameters.
        transient: bool
            If true, allow for the Fstat to be computed over a transient range.
        BSGL: bool
            If true, compute the BSGL rather than the twoF value.
        BSGL_PREFACTOR: float
            If BSGL is True, one can specify a prefactor to multiply the
            computed BSGL value by, useful in MCMC searches to amplify the
            peaks.
Gregory Ashton's avatar
Gregory Ashton committed
225
226
        BSGL_FLOOR: float
            IF BSGL < BSGL_FLOOR -> BSGL_FLOOR
227
228
229
        detector: str
            Two character reference to the data to use, specify None for no
            contraint.
230
231
232
233
234
235
236
237
238
239
        minCoverFreq, maxCoverFreq: float
            The min and max cover frequency passed to CreateFstatInput, if
            either is None the range of frequencies in the SFT less 1Hz is
            used.
        earth_ephem, sun_ephem: str
            Paths of the two files containing positions of Earth and Sun,
            respectively at evenly spaced times, as passed to CreateFstatInput.
            If None defaults defined in BaseSearchClass will be used.

        """
Gregory Ashton's avatar
Gregory Ashton committed
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254

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

        self.init_computefstatistic_single_point()

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

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

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

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

        logging.info('Initialising FstatInput')
        dFreq = 0
274
275
276
277
278
        if self.transient:
            self.whatToCompute = lalpulsar.FSTATQ_ATOMS_PER_DET
        else:
            self.whatToCompute = lalpulsar.FSTATQ_2F

Gregory Ashton's avatar
Gregory Ashton committed
279
280
281
282
283
284
285
286
        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
287
288
289
            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
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309

        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()

310
        if self.BSGL:
Gregory Ashton's avatar
Gregory Ashton committed
311
312
            if len(names) < 2:
                raise ValueError("Can't use BSGL with single detector data")
313
314
315
316
317
318
319
320
321
322
            if self.BSGL_FLOOR is None:
                logging.info('Initialising BSGL with prefactor {:2.2f}'
                             .format(self.BSGL_PREFACTOR)
                             )
            else:
                logging.info('Initialising BSGL with prefactor {:0.2f} and '
                             'floor {}'.format(self.BSGL_PREFACTOR,
                                               self.BSGL_FLOOR)
                             )

323
324
            # Tuning parameters - to be reviewed
            numDetectors = 2
Gregory Ashton's avatar
Gregory Ashton committed
325
            Fstar0sc = 15.
326
            oLGX = np.zeros(10)
Gregory Ashton's avatar
Gregory Ashton committed
327
            oLGX[:numDetectors] = 1./numDetectors
328
329
330
            self.BSGLSetup = lalpulsar.CreateBSGLSetup(numDetectors,
                                                       Fstar0sc,
                                                       oLGX,
331
                                                       True,
332
333
                                                       1)
            self.twoFX = np.zeros(10)
Gregory Ashton's avatar
Gregory Ashton committed
334
            self.whatToCompute = (self.whatToCompute +
335
336
                                  lalpulsar.FSTATQ_2F_PER_DET)

337
        if self.transient:
338
            logging.info('Initialising transient parameters')
339
340
341
342
343
344
            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
345

Gregory Ashton's avatar
Gregory Ashton committed
346
    def run_computefstatistic_single_point(self, tstart, tend, F0, F1,
347
348
349
                                           F2, Alpha, Delta, asini=None,
                                           period=None, ecc=None, tp=None,
                                           argp=None):
350
        """ Returns the twoF fully-coherently at a single point """
Gregory Ashton's avatar
Gregory Ashton committed
351
352
353
354

        self.PulsarDopplerParams.fkdot = np.array([F0, F1, F2, 0, 0, 0, 0])
        self.PulsarDopplerParams.Alpha = Alpha
        self.PulsarDopplerParams.Delta = Delta
355
356
357
358
359
360
        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
361
362
363
364

        lalpulsar.ComputeFstat(self.FstatResults,
                               self.FstatInput,
                               self.PulsarDopplerParams,
365
                               1,
Gregory Ashton's avatar
Gregory Ashton committed
366
367
368
                               self.whatToCompute
                               )

369
        if self.transient is False:
370
371
372
373
374
375
376
377
            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)
378
379
            if self.BSGL_FLOOR is not None and BSGL < self.BSGL_FLOOR:
                return self.BSGL_FLOOR
Gregory Ashton's avatar
Gregory Ashton committed
380
381
            else:
                return self.BSGL_PREFACTOR * BSGL/np.log10(np.exp(1))
382

383
384
        self.windowRange.t0 = int(tstart)  # TYPE UINT4
        self.windowRange.tau = int(tend - tstart)  # TYPE UINT4
385

Gregory Ashton's avatar
Gregory Ashton committed
386
        FS = lalpulsar.ComputeTransientFstatMap(
387
            self.FstatResults.multiFatoms[0], self.windowRange, False)
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405

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

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

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

Gregory Ashton's avatar
Gregory Ashton committed
406
407
408
409
        if self.BSGL_FLOOR and BSGL < self.BSGL_FLOOR:
            return self.BSGL_FLOOR
        else:
            return self.BSGL_PREFACTOR * BSGL/np.log10(np.exp(1))
Gregory Ashton's avatar
Gregory Ashton committed
410
411
412


class SemiCoherentGlitchSearch(BaseSearchClass, ComputeFstat):
413
414
415
416
417
418
419
420
421
    """ 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
422
    def __init__(self, label, outdir, tref, tstart, tend, nglitch=0,
423
                 sftfilepath=None, theta0_idx=0, BSGL=False, BSGL_PREFACTOR=1,
Gregory Ashton's avatar
Gregory Ashton committed
424
425
426
                 BSGL_FLOOR=None, minStartTime=None, maxStartTime=None,
                 minCoverFreq=None, maxCoverFreq=None, detector=None,
                 earth_ephem=None, sun_ephem=None):
427
428
429
430
        """
        Parameters
        ----------
        label, outdir: str
431
432
433
434
435
436
            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).
437
438
        sftfilepath: str
            File patern to match SFTs
439
440
441
442
        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)
443
444

        For all other parameters, see pyfstat.ComputeFStat.
445
446
447
448
449
450
451
        """

        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
452
453
        self.transient = True
        self.binary = False
454
455
456
        self.init_computefstatistic_single_point()

    def compute_nglitch_fstat(self, F0, F1, F2, Alpha, Delta, *args):
457
        """ Returns the semi-coherent glitch summed twoF """
458
459
460

        args = list(args)
        tboundaries = [self.tstart] + args[-self.nglitch:] + [self.tend]
461
462
463
464
465
466
467
468
        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)

469
470
        thetas = self.calculate_thetas(theta, delta_thetas, tboundaries,
                                       theta0_idx=self.theta0_idx)
471
472

        twoFSum = 0
473
        for i, theta_i_at_tref in enumerate(thetas):
474
475
476
            ts, te = tboundaries[i], tboundaries[i+1]

            twoFVal = self.run_computefstatistic_single_point(
477
478
                ts, te, theta_i_at_tref[1], theta_i_at_tref[2],
                theta_i_at_tref[3], Alpha, Delta)
479
480
            twoFSum += twoFVal

481
482
483
        if np.isfinite(twoFSum):
            return twoFSum
        else:
484
            return -np.inf
485
486
487

    def compute_glitch_fstat_single(self, F0, F1, F2, Alpha, Delta, delta_F0,
                                    delta_F1, tglitch):
488
489
490
491
        """ Returns the semi-coherent glitch summed twoF for nglitch=1

        Note: used for testing
        """
492
493
494
495
496
497
498
499
500
501
502

        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
503
            self.tstart, tglitch, theta[0], theta[1], theta[2], Alpha,
504
505
506
507
508
509
            Delta)

        if tglitch == self.tend:
            return twoFsegA

        twoFsegB = self.run_computefstatistic_single_point(
Gregory Ashton's avatar
Gregory Ashton committed
510
            tglitch, self.tend, theta_post_glitch[0],
511
512
513
514
515
516
            theta_post_glitch[1], theta_post_glitch[2], Alpha,
            Delta)

        return twoFsegA + twoFsegB


Gregory Ashton's avatar
Gregory Ashton committed
517
518
class MCMCSearch(BaseSearchClass):
    """ MCMC search using ComputeFstat"""
519
    @initializer
520
    def __init__(self, label, outdir, sftfilepath, theta_prior, tref,
521
                 tstart, tend, nsteps=[100, 100, 100], nwalkers=100, ntemps=1,
522
                 log10temperature_min=-5, theta_initial=None, scatter_val=1e-10,
523
524
                 binary=False, BSGL=False, minCoverFreq=None,
                 maxCoverFreq=None, detector=None, earth_ephem=None,
525
                 sun_ephem=None, theta0_idx=0,
Gregory Ashton's avatar
Gregory Ashton committed
526
                 BSGL_PREFACTOR=1, BSGL_FLOOR=None):
527
528
529
530
        """
        Parameters
        label, outdir: str
            A label and directory to read/write data from/to
531
532
        sftfilepath: str
            File patern to match SFTs
533
        theta_prior: dict
534
535
536
537
            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.
538
539
540
541
        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.
542
543
544
545
546
547
548
        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].
549
550
551
552
553
554
555
556
557
558
559
        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.
560
561
562
563
564
565
566
567
568
569
        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

        """

570
571
572
        self.minStartTime = tstart
        self.maxStartTime = tend

Gregory Ashton's avatar
Gregory Ashton committed
573
574
        if os.path.isdir(outdir) is False:
            os.mkdir(outdir)
575
        self.add_log_file()
Gregory Ashton's avatar
Gregory Ashton committed
576
577
        logging.info(
            'Set-up MCMC search for model {} on data {}'.format(
578
                self.label, self.sftfilepath))
579
        self.pickle_path = '{}/{}_saved_data.p'.format(self.outdir, self.label)
Gregory Ashton's avatar
Gregory Ashton committed
580
581
        self.theta_prior['tstart'] = self.tstart
        self.theta_prior['tend'] = self.tend
582
583
        self.unpack_input_theta()
        self.ndim = len(self.theta_keys)
584
585
586
587
        if self.log10temperature_min:
            self.betas = np.logspace(0, self.log10temperature_min, self.ntemps)
        else:
            self.betas = None
588

589
590
591
592
593
594
595
596
597
        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()
598
599
600
        self.log_input()

    def log_input(self):
601
        logging.info('theta_prior = {}'.format(self.theta_prior))
602
        logging.info('nwalkers={}'.format(self.nwalkers))
603
604
605
606
        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(
607
            self.log10temperature_min))
608
609
610

    def inititate_search_object(self):
        logging.info('Setting up search object')
Gregory Ashton's avatar
Gregory Ashton committed
611
        self.search = ComputeFstat(
612
613
614
615
            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,
616
            minStartTime=self.minStartTime, maxStartTime=self.maxStartTime,
Gregory Ashton's avatar
Gregory Ashton committed
617
            BSGL_PREFACTOR=self.BSGL_PREFACTOR, BSGL_FLOOR=self.BSGL_FLOOR)
618
619

    def logp(self, theta_vals, theta_prior, theta_keys, search):
Gregory Ashton's avatar
Gregory Ashton committed
620
        H = [self.generic_lnprior(**theta_prior[key])(p) for p, key in
621
622
623
624
625
626
             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
627
        FS = search.run_computefstatistic_single_point(*self.fixed_theta)
628
629
630
        return FS

    def unpack_input_theta(self):
Gregory Ashton's avatar
Gregory Ashton committed
631
632
        full_theta_keys = ['tstart', 'tend', 'F0', 'F1', 'F2', 'Alpha',
                           'Delta']
633
634
635
        if self.binary:
            full_theta_keys += [
                'asini', 'period', 'ecc', 'tp', 'argp']
636
637
        full_theta_keys_copy = copy.copy(full_theta_keys)

Gregory Ashton's avatar
Gregory Ashton committed
638
639
        full_theta_symbols = ['_', '_', '$f$', '$\dot{f}$', '$\ddot{f}$',
                              r'$\alpha$', r'$\delta$']
640
641
642
643
        if self.binary:
            full_theta_symbols += [
                'asini', 'period', 'period', 'ecc', 'tp', 'argp']

644
645
        self.theta_keys = []
        fixed_theta_dict = {}
646
        for key, val in self.theta_prior.iteritems():
647
648
            if type(val) is dict:
                fixed_theta_dict[key] = 0
Gregory Ashton's avatar
Gregory Ashton committed
649
                self.theta_keys.append(key)
650
651
652
653
654
655
            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
656
            full_theta_keys_copy.pop(full_theta_keys_copy.index(key))
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672

        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):
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
        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
709

Gregory Ashton's avatar
Gregory Ashton committed
710
    def run_sampler_with_progress_bar(self, sampler, ns, p0):
711
712
        for result in tqdm(sampler.sample(p0, iterations=ns), total=ns):
            pass
Gregory Ashton's avatar
Gregory Ashton committed
713
714
715
        return sampler

    def run(self, proposal_scale_factor=2):
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731

        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),
732
            loglargs=(self.search,), betas=self.betas, a=proposal_scale_factor)
733

Gregory Ashton's avatar
Gregory Ashton committed
734
735
        p0 = self.generate_initial_p0()
        p0 = self.apply_corrections_to_p0(p0)
736
737
738
739
740
        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(
741
                j+1, ninit_steps, n))
Gregory Ashton's avatar
Gregory Ashton committed
742
            sampler = self.run_sampler_with_progress_bar(sampler, n, p0)
743
744
            logging.info("Mean acceptance fraction: {}"
                         .format(np.mean(sampler.acceptance_fraction, axis=1)))
745
746
747
            if self.ntemps > 1:
                logging.info("Tswap acceptance fraction: {}"
                             .format(sampler.tswap_acceptance_fraction))
Gregory Ashton's avatar
Gregory Ashton committed
748
            fig, axes = self.plot_walkers(sampler, symbols=self.theta_symbols)
749
750
751
            fig.savefig('{}/{}_init_{}_walkers.png'.format(
                self.outdir, self.label, j))

752
            p0 = self.get_new_p0(sampler)
Gregory Ashton's avatar
Gregory Ashton committed
753
            p0 = self.apply_corrections_to_p0(p0)
754
755
756
            self.check_initial_points(p0)
            sampler.reset()

Gregory Ashton's avatar
Gregory Ashton committed
757
758
759
760
        if len(self.nsteps) > 1:
            nburn = self.nsteps[-2]
        else:
            nburn = 0
761
762
763
        nprod = self.nsteps[-1]
        logging.info('Running final burn and prod with {} steps'.format(
            nburn+nprod))
Gregory Ashton's avatar
Gregory Ashton committed
764
        sampler = self.run_sampler_with_progress_bar(sampler, nburn+nprod, p0)
765
766
        logging.info("Mean acceptance fraction: {}"
                     .format(np.mean(sampler.acceptance_fraction, axis=1)))
767
768
769
        if self.ntemps > 1:
            logging.info("Tswap acceptance fraction: {}"
                         .format(sampler.tswap_acceptance_fraction))
770

Gregory Ashton's avatar
Gregory Ashton committed
771
772
        fig, axes = self.plot_walkers(sampler, symbols=self.theta_symbols,
                                      burnin_idx=nburn)
773
774
775
776
777
778
779
780
781
782
783
        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)

784
    def plot_corner(self, figsize=(7, 7),  tglitch_ratio=False,
785
786
787
788
789
790
791
792
793
                    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)
794
795
            theta_symbols_plt = [s.replace('_{glitch}', r'_\textrm{glitch}')
                                 for s in theta_symbols_plt]
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
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

            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)
845
846
847
848
849
850

    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
851
            prior = self.generic_lnprior(**self.theta_prior[key])
852
853
854
855
856
857
            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)

858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
    def plot_prior_posterior(self, normal_stds=2):
        """ Plot the posterior in the context of the prior """
        fig, axes = plt.subplots(nrows=self.ndim, figsize=(8, 4*self.ndim))
        N = 1000
        from scipy.stats import gaussian_kde

        for i, (ax, key) in enumerate(zip(axes, self.theta_keys)):
            prior_dict = self.theta_prior[key]
            prior_func = self.generic_lnprior(**prior_dict)
            if prior_dict['type'] == 'unif':
                x = np.linspace(prior_dict['lower'], prior_dict['upper'], N)
                prior = prior_func(x)
                prior[0] = 0
                prior[-1] = 0
            elif prior_dict['type'] == 'norm':
                lower = prior_dict['loc'] - normal_stds * prior_dict['scale']
                upper = prior_dict['loc'] + normal_stds * prior_dict['scale']
                x = np.linspace(lower, upper, N)
                prior = prior_func(x)
877
878
879
880
881
            elif prior_dict['type'] == 'halfnorm':
                lower = prior_dict['loc']
                upper = prior_dict['loc'] + normal_stds * prior_dict['scale']
                x = np.linspace(lower, upper, N)
                prior = [prior_func(xi) for xi in x]
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
            else:
                raise ValueError('Not implemented for prior type {}'.format(
                    prior_dict['type']))
            priorln = ax.plot(x, prior, 'r', label='prior')
            ax.set_xlabel(self.theta_symbols[i])

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

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

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

Gregory Ashton's avatar
Gregory Ashton committed
905
    def generic_lnprior(self, **kwargs):
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
        """ 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'])
948
949
        elif kwargs['type'] == 'neghalfnorm':
            return lambda x: halfnorm(-x, kwargs['loc'], kwargs['scale'])
950
951
952
953
954
955
956
        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
957
    def generate_rv(self, **kwargs):
958
959
960
961
962
963
964
965
        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']))
966
967
968
        if dist_type == "neghalfnorm":
            return -1 * np.abs(np.random.normal(loc=kwargs['loc'],
                                                scale=kwargs['scale']))
969
970
971
972
973
974
        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
975
    def plot_walkers(self, sampler, symbols=None, alpha=0.4, color="k", temp=0,
976
                     lw=0.1, burnin_idx=None, add_det_stat_burnin=False):
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
        """ 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
993
994
995
996
            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)]
997

Gregory Ashton's avatar
Gregory Ashton committed
998
            idxs = np.arange(chain.shape[1])
999
1000
            if ndim > 1:
                for i in range(ndim):
1001
                    axes[i].ticklabel_format(useOffset=False, axis='y')
Gregory Ashton's avatar
Gregory Ashton committed
1002
1003
1004
                    cs = chain[:, :, i].T
                    if burnin_idx:
                        axes[i].plot(idxs[:burnin_idx], cs[:burnin_idx],
Gregory Ashton's avatar
Gregory Ashton committed
1005
                                     color="r", alpha=alpha, lw=lw)
Gregory Ashton's avatar
Gregory Ashton committed
1006
                    axes[i].plot(idxs[burnin_idx:], cs[burnin_idx:], color="k",
Gregory Ashton's avatar
Gregory Ashton committed
1007
                                 alpha=alpha, lw=lw)
1008
1009
                    if symbols:
                        axes[i].set_ylabel(symbols[i])
1010
            else:
Gregory Ashton's avatar
Gregory Ashton committed
1011
                cs = chain[:, :, temp].T
1012
1013
                axes.plot(cs, color='k', alpha=alpha)
                axes.ticklabel_format(useOffset=False, axis='y')
1014

Gregory Ashton's avatar
Gregory Ashton committed
1015
1016
        axes.append(fig.add_subplot(ndim+1, 1, ndim+1))
        lnl = sampler.lnlikelihood[temp, :, :]
1017
        if burnin_idx and add_det_stat_burnin:
Gregory Ashton's avatar
Gregory Ashton committed
1018
1019
            axes[-1].hist(lnl[:, :burnin_idx].flatten(), bins=50,
                          histtype='step', color='r')
Gregory Ashton's avatar
Gregory Ashton committed
1020
1021
        axes[-1].hist(lnl[:, burnin_idx:].flatten(), bins=50, histtype='step',
                      color='k')
Gregory Ashton's avatar
Gregory Ashton committed
1022
1023
1024
1025
        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
1026

1027
1028
        return fig, axes

Gregory Ashton's avatar
Gregory Ashton committed
1029
1030
1031
1032
1033
    def apply_corrections_to_p0(self, p0):
        """ Apply any correction to the initial p0 values """
        return p0

    def generate_scattered_p0(self, p):
1034
        """ Generate a set of p0s scattered about p """
Gregory Ashton's avatar
Gregory Ashton committed
1035
        p0 = [[p + self.scatter_val * p * np.random.randn(self.ndim)
1036
1037
1038
1039
               for i in xrange(self.nwalkers)]
              for j in xrange(self.ntemps)]
        return p0

Gregory Ashton's avatar
Gregory Ashton committed
1040
    def generate_initial_p0(self):
1041
1042
1043
        """ Generate a set of init vals for the walkers """

        if type(self.theta_initial) == dict:
1044
            logging.info('Generate initial values from initial dictionary')
1045
            if hasattr(self, 'nglitch') and self.nglitch > 1:
1046
                raise ValueError('Initial dict not implemented for nglitch>1')
Gregory Ashton's avatar
Gregory Ashton committed
1047
            p0 = [[[self.generate_rv(**self.theta_initial[key])
1048
1049
1050
                    for key in self.theta_keys]
                   for i in range(self.nwalkers)]
                  for j in range(self.ntemps)]
1051
1052
1053
1054
1055
1056
        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)]
1057
        elif self.theta_initial is None:
1058
            logging.info('Generate initial values from prior dictionary')
Gregory Ashton's avatar
Gregory Ashton committed
1059
            p0 = [[[self.generate_rv(**self.theta_prior[key])
1060
1061
1062
1063
                    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
1064
            p0 = self.generate_scattered_p0(self.theta_initial)
1065
1066
1067
1068
1069
        else:
            raise ValueError('theta_initial not understood')

        return p0

1070
    def get_new_p0(self, sampler):
1071
1072
1073
1074
1075
1076
        """ 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
1077
1078
1079
1080
        temp_idx = 0
        pF = sampler.chain[temp_idx, :, :, :]
        lnl = sampler.lnlikelihood[temp_idx, :, :]
        lnp = sampler.lnprobability[temp_idx, :, :]
1081
1082

        # General warnings about the state of lnp
Gregory Ashton's avatar
Gregory Ashton committed
1083
        if np.any(np.isnan(lnp)):
1084
1085
            logging.warning(
                "Of {} lnprobs {} are nan".format(
Gregory Ashton's avatar
Gregory Ashton committed
1086
1087
                    np.shape(lnp), np.sum(np.isnan(lnp))))
        if np.any(np.isposinf(lnp)):
1088
1089
            logging.warning(
                "Of {} lnprobs {} are +np.inf".format(
Gregory Ashton's avatar
Gregory Ashton committed
1090
1091
                    np.shape(lnp), np.sum(np.isposinf(lnp))))
        if np.any(np.isneginf(lnp)):
1092
1093
            logging.warning(
                "Of {} lnprobs {} are -np.inf".format(
Gregory Ashton's avatar
Gregory Ashton committed
1094
                    np.shape(lnp), np.sum(np.isneginf(lnp))))
1095

1096
1097
        lnp_finite = copy.copy(lnp)
        lnp_finite[np.isinf(lnp)] = np.nan
Gregory Ashton's avatar
Gregory Ashton committed
1098
1099
        idx = np.unravel_index(np.nanargmax(lnp_finite), lnp_finite.shape)
        p = pF[idx]
1100
        p0 = self.generate_scattered_p0(p)
1101

1102
1103
1104
1105
1106
1107
1108
1109
        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]))

1110
1111
1112
1113
1114
        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
1115
                 theta_prior=self.theta_prior, scatter_val=self.scatter_val,
1116
                 log10temperature_min=self.log10temperature_min,
1117
                 theta0_idx=self.theta0_idx, BSGL=self.BSGL,
Gregory Ashton's avatar
Gregory Ashton committed
1118
1119
                 BSGL_PREFACTOR=self.BSGL_PREFACTOR,
                 BSGL_FLOOR=self.BSGL_FLOOR)
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
        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):
1137
        matches = glob.glob(self.sftfilepath)
1138
1139
1140
1141
        if len(matches) > 0:
            return matches
        else:
            raise IOError('No sfts found matching {}'.format(
1142
                self.sftfilepath))
1143
1144
1145
1146
1147
1148
1149

    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):
1150
1151
1152
1153
        if args.use_old_data:
            logging.info("Forcing use of old data")
            return True

1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
        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:
1178
                raise ValueError('Keys {} not in old dictionary'.format(key))
1179
1180
1181
1182
1183
1184
1185
1186
1187

        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':
1188
                        logging.info("    {} : {} -> {}".format(*key))
1189
                    else:
1190
                        logging.info("    " + key[0])
1191
1192
1193
1194
1195
                else:
                    logging.info(key)
            return False

    def get_max_twoF(self, threshold=0.05):
1196
        """ Returns the max likelihood sample and the corresponding 2F value
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210

        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])
1211
        maxlogl = self.lnlikes[jmax]
1212
        d = OrderedDict()
1213

1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
        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
1224
        repeats = []
1225
        for i, k in enumerate(self.theta_keys):
Gregory Ashton's avatar
Gregory Ashton committed
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
            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
1236
1237
1238
1239
1240
            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 """
1241
        d = OrderedDict()
Gregory Ashton's avatar
Gregory Ashton committed
1242
        repeats = []
1243
        for s, k in zip(self.samples.T, self.theta_keys):
Gregory Ashton's avatar
Gregory Ashton committed
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
            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

1257
1258
1259
1260
1261
1262
1263
1264
            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))
1265
1266
1267
1268

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

Gregory Ashton's avatar
Gregory Ashton committed
1269
        logging.info('Writing par file with max twoF = {}'.format(max_twoF))
1270
1271
1272
        filename = '{}/{}.par'.format(self.outdir, self.label)
        with open(filename, 'w+') as f:
            f.write('MaxtwoF = {}\n'.format(max_twoF))
1273
            f.write('theta0_index = {}\n'.format(self.theta0_idx))
1274
            if method == 'med':
1275
1276
                for key, val in median_std_d.iteritems():
                    f.write('{} = {:1.16e}\n'.format(key, val))
1277
            if method == 'twoFmax':