mcmc_based_searches.py 88.2 KB
Newer Older
Gregory Ashton's avatar
Gregory Ashton committed
1
2
""" Searches using MCMC-based methods """

3
import sys
Gregory Ashton's avatar
Gregory Ashton committed
4
import os
5
import copy
Gregory Ashton's avatar
Gregory Ashton committed
6
import logging
7
from collections import OrderedDict
8
9
10
11
12
13
14
15

import numpy as np
import matplotlib
import matplotlib.pyplot as plt
import emcee
import corner
import dill as pickle

16
import core
Gregory Ashton's avatar
Gregory Ashton committed
17
from core import tqdm, args, earth_ephem, sun_ephem
18
from optimal_setup_functions import get_V_estimate
Gregory Ashton's avatar
Gregory Ashton committed
19
20
from optimal_setup_functions import get_optimal_setup
import helper_functions
21
22


23
class MCMCSearch(core.BaseSearchClass):
Gregory Ashton's avatar
Gregory Ashton committed
24
    """ MCMC search using ComputeFstat"""
25
26

    symbol_dictionary = dict(
27
        F0='$f$', F1='$\dot{f}$', F2='$\ddot{f}$', Alpha=r'$\alpha$',
28
29
        Delta='$\delta$', asini='asini', period='P', ecc='ecc', tp='tp',
        argp='argp')
30
    unit_dictionary = dict(
31
32
        F0='Hz', F1='Hz/s', F2='Hz/s$^2$', Alpha=r'rad', Delta='rad',
        asini='', period='s', ecc='', tp='', argp='')
33
34
35
    rescale_dictionary = {}


Gregory Ashton's avatar
Gregory Ashton committed
36
    @helper_functions.initializer
Gregory Ashton's avatar
Gregory Ashton committed
37
38
    def __init__(self, label, outdir, theta_prior, tref, minStartTime,
                 maxStartTime, sftfilepath=None, nsteps=[100, 100],
39
40
                 nwalkers=100, ntemps=1, log10temperature_min=-5,
                 theta_initial=None, scatter_val=1e-10,
41
                 binary=False, BSGL=False, minCoverFreq=None,
42
                 maxCoverFreq=None, detectors=None, earth_ephem=None,
43
                 sun_ephem=None, injectSources=None, assumeSqrtSX=None):
44
45
46
47
        """
        Parameters
        label, outdir: str
            A label and directory to read/write data from/to
48
        sftfilepath: str
49
50
            Pattern to match SFTs using wildcards (*?) and ranges [0-9];
            mutiple patterns can be given separated by colons.
51
        theta_prior: dict
52
53
54
55
            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.
56
57
58
59
        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.
60
        tref, minStartTime, maxStartTime: int
61
62
63
64
65
66
            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].
67
68
69
70
71
72
73
74
        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
75
        detectors: str
76
77
            Two character reference to the data to use, specify None for no
            contraint.
78
79
80
81
82
83
84
85
86
87
        minCoverFreq, maxCoverFreq: float
            Minimum and maximum instantaneous frequency which will be covered
            over the SFT time span as passed to CreateFstatInput
        earth_ephem, sun_ephem: str
            Paths of the two files containing positions of Earth and Sun,
            respectively at evenly spaced times, as passed to CreateFstatInput
            If None defaults defined in BaseSearchClass will be used

        """

Gregory Ashton's avatar
Gregory Ashton committed
88
89
        if os.path.isdir(outdir) is False:
            os.mkdir(outdir)
90
        self._add_log_file()
Gregory Ashton's avatar
Gregory Ashton committed
91
92
        logging.info(
            'Set-up MCMC search for model {} on data {}'.format(
93
                self.label, self.sftfilepath))
94
        self.pickle_path = '{}/{}_saved_data.p'.format(self.outdir, self.label)
95
        self._unpack_input_theta()
96
        self.ndim = len(self.theta_keys)
97
98
99
100
        if self.log10temperature_min:
            self.betas = np.logspace(0, self.log10temperature_min, self.ntemps)
        else:
            self.betas = None
101

102
103
104
105
106
107
108
109
        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")

110
        self._log_input()
111

112
    def _log_input(self):
113
        logging.info('theta_prior = {}'.format(self.theta_prior))
114
        logging.info('nwalkers={}'.format(self.nwalkers))
115
116
117
118
        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(
119
            self.log10temperature_min))
120

121
    def _initiate_search_object(self):
122
        logging.info('Setting up search object')
123
        self.search = core.ComputeFstat(
124
125
126
            tref=self.tref, sftfilepath=self.sftfilepath,
            minCoverFreq=self.minCoverFreq, maxCoverFreq=self.maxCoverFreq,
            earth_ephem=self.earth_ephem, sun_ephem=self.sun_ephem,
127
            detectors=self.detectors, BSGL=self.BSGL, transient=False,
128
            minStartTime=self.minStartTime, maxStartTime=self.maxStartTime,
129
130
            binary=self.binary, injectSources=self.injectSources,
            assumeSqrtSX=self.assumeSqrtSX)
131
132

    def logp(self, theta_vals, theta_prior, theta_keys, search):
133
        H = [self._generic_lnprior(**theta_prior[key])(p) for p, key in
134
135
136
137
138
139
             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]
140
141
        FS = search.compute_fullycoherent_det_stat_single_point(
            *self.fixed_theta)
142
143
        return FS

144
    def _unpack_input_theta(self):
145
        full_theta_keys = ['F0', 'F1', 'F2', 'Alpha', 'Delta']
146
147
148
        if self.binary:
            full_theta_keys += [
                'asini', 'period', 'ecc', 'tp', 'argp']
149
150
        full_theta_keys_copy = copy.copy(full_theta_keys)

151
152
        full_theta_symbols = ['$f$', '$\dot{f}$', '$\ddot{f}$', r'$\alpha$',
                              r'$\delta$']
153
154
        if self.binary:
            full_theta_symbols += [
155
                'asini', 'period', 'ecc', 'tp', 'argp']
156

157
158
        self.theta_keys = []
        fixed_theta_dict = {}
159
        for key, val in self.theta_prior.iteritems():
160
161
            if type(val) is dict:
                fixed_theta_dict[key] = 0
Gregory Ashton's avatar
Gregory Ashton committed
162
                self.theta_keys.append(key)
163
164
165
166
167
168
            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
169
            full_theta_keys_copy.pop(full_theta_keys_copy.index(key))
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184

        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]

185
    def _check_initial_points(self, p0):
186
187
188
189
190
191
192
193
194
195
196
197
198
        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))

199
                p0 = self._generate_new_p0_to_fix_initial_points(
200
201
                    p0, nt, initial_priors)

202
    def _generate_new_p0_to_fix_initial_points(self, p0, nt, initial_priors):
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
        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
222

223
    def _OLD_run_sampler_with_progress_bar(self, sampler, ns, p0):
224
225
        for result in tqdm(sampler.sample(p0, iterations=ns), total=ns):
            pass
Gregory Ashton's avatar
Gregory Ashton committed
226
227
        return sampler

228
229
    def setup_convergence_testing(
            self, convergence_period=10, convergence_length=10,
230
            convergence_burnin_fraction=0.25, convergence_threshold_number=10,
231
            convergence_threshold=1.2, convergence_prod_threshold=2,
232
            convergence_plot_upper_lim=2, convergence_early_stopping=True):
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
        """
        If called, convergence testing is used during the MCMC simulation

        This uses the Gelmanr-Rubin statistic based on the ratio of between and
        within walkers variance. The original statistic was developed for
        multiple (independent) MCMC simulations, in this context we simply use
        the walkers

        Parameters
        ----------
        convergence_period: int
            period (in number of steps) at which to test convergence
        convergence_length: int
            number of steps to use in testing convergence - this should be
            large enough to measure the variance, but if it is too long
            this will result in incorect early convergence tests
        convergence_burnin_fraction: float [0, 1]
            the fraction of the burn-in period after which to start testing
        convergence_threshold_number: int
            the number of consecutive times where the test passes after which
            to break the burn-in and go to production
        convergence_threshold: float
            the threshold to use in diagnosing convergence. Gelman & Rubin
            recomend a value of 1.2, 1.1 for strict convergence
        convergence_prod_threshold: float
            the threshold to test the production values with
259
260
        convergence_plot_upper_lim: float
            the upper limit to use in the diagnostic plot
261
262
        convergence_early_stopping: bool
            if true, stop the burnin early if convergence is reached
263
        """
264
265
266
267
268
269
270

        if convergence_length > convergence_period:
            raise ValueError('convergence_length must be < convergence_period')
        logging.info('Setting up convergence testing')
        self.convergence_length = convergence_length
        self.convergence_period = convergence_period
        self.convergence_burnin_fraction = convergence_burnin_fraction
271
        self.convergence_prod_threshold = convergence_prod_threshold
272
273
274
275
276
        self.convergence_diagnostic = []
        self.convergence_diagnosticx = []
        self.convergence_threshold_number = convergence_threshold_number
        self.convergence_threshold = convergence_threshold
        self.convergence_number = 0
277
        self.convergence_plot_upper_lim = convergence_plot_upper_lim
278
        self.convergence_early_stopping = convergence_early_stopping
279

280
    def _get_convergence_statistic(self, i, sampler):
281
        s = sampler.chain[0, :, i-self.convergence_length+1:i+1, :]
282
283
284
        N = float(self.convergence_length)
        M = float(self.nwalkers)
        W = np.mean(np.var(s, axis=1), axis=0)
285
286
        per_walker_mean = np.mean(s, axis=1)
        mean = np.mean(per_walker_mean, axis=0)
287
288
289
        B = N / (M-1.) * np.sum((per_walker_mean-mean)**2, axis=0)
        Vhat = (N-1)/N * W + (M+1)/(M*N) * B
        c = Vhat/W
290
        self.convergence_diagnostic.append(c)
291
        self.convergence_diagnosticx.append(i - self.convergence_length/2)
292
293
        return c

294
    def _burnin_convergence_test(self, i, sampler, nburn):
295
296
        if i < self.convergence_burnin_fraction*nburn:
            return False
297
        if np.mod(i+1, self.convergence_period) != 0:
298
            return False
299
        c = self._get_convergence_statistic(i, sampler)
300
301
        if np.all(c < self.convergence_threshold):
            self.convergence_number += 1
302
303
        else:
            self.convergence_number = 0
304
305
        if self.convergence_early_stopping:
            return self.convergence_number > self.convergence_threshold_number
306

307
    def _prod_convergence_test(self, i, sampler, nburn):
308
309
310
        testA = i > nburn + self.convergence_length
        testB = np.mod(i+1, self.convergence_period) == 0
        if testA and testB:
311
            self._get_convergence_statistic(i, sampler)
312

313
    def _check_production_convergence(self, k):
314
315
316
317
318
319
320
321
        bools = np.any(
            np.array(self.convergence_diagnostic)[k:, :]
            > self.convergence_prod_threshold, axis=1)
        if np.any(bools):
            logging.warning(
                '{} convergence tests in the production run of {} failed'
                .format(np.sum(bools), len(bools)))

322
    def _run_sampler(self, sampler, p0, nprod=0, nburn=0):
323
        if hasattr(self, 'convergence_period'):
324
325
326
327
            logging.info('Running {} burn-in steps with convergence testing'
                         .format(nburn))
            iterator = tqdm(sampler.sample(p0, iterations=nburn), total=nburn)
            for i, output in enumerate(iterator):
328
                if self._burnin_convergence_test(i, sampler, nburn):
329
330
331
332
333
334
335
336
337
338
339
                    logging.info(
                        'Converged at {} before max number {} of steps reached'
                        .format(i, nburn))
                    self.convergence_idx = i
                    break
            iterator.close()
            logging.info('Running {} production steps'.format(nprod))
            j = nburn
            k = len(self.convergence_diagnostic)
            for result in tqdm(sampler.sample(output[0], iterations=nprod),
                               total=nprod):
340
                self._prod_convergence_test(j, sampler, nburn)
341
                j += 1
342
            self._check_production_convergence(k)
343
344
345
346
347
348
            return sampler
        else:
            for result in tqdm(sampler.sample(p0, iterations=nburn+nprod),
                               total=nburn+nprod):
                pass
            return sampler
349

350
    def run(self, proposal_scale_factor=2, create_plots=True, **kwargs):
351
        """ Run the MCMC simulatation """
352

353
        self.old_data_is_okay_to_use = self._check_old_data_is_okay_to_use()
354
355
356
        if self.old_data_is_okay_to_use is True:
            logging.warning('Using saved data from {}'.format(
                self.pickle_path))
357
            d = self.get_saved_data_dictionary()
358
359
360
            self.samples = d['samples']
            self.lnprobs = d['lnprobs']
            self.lnlikes = d['lnlikes']
361
            self.all_lnlikelihood = d['all_lnlikelihood']
362
363
            return

364
        self._initiate_search_object()
365
366
367
368

        sampler = emcee.PTSampler(
            self.ntemps, self.nwalkers, self.ndim, self.logl, self.logp,
            logpargs=(self.theta_prior, self.theta_keys, self.search),
369
            loglargs=(self.search,), betas=self.betas, a=proposal_scale_factor)
370

371
372
373
        p0 = self._generate_initial_p0()
        p0 = self._apply_corrections_to_p0(p0)
        self._check_initial_points(p0)
374
375
376
377

        ninit_steps = len(self.nsteps) - 2
        for j, n in enumerate(self.nsteps[:-2]):
            logging.info('Running {}/{} initialisation with {} steps'.format(
Gregory Ashton's avatar
Gregory Ashton committed
378
                j, ninit_steps, n))
379
            sampler = self._run_sampler(sampler, p0, nburn=n)
380
381
            logging.info("Mean acceptance fraction: {}"
                         .format(np.mean(sampler.acceptance_fraction, axis=1)))
382
383
384
            if self.ntemps > 1:
                logging.info("Tswap acceptance fraction: {}"
                             .format(sampler.tswap_acceptance_fraction))
385
            if create_plots:
386
                fig, axes = self._plot_walkers(sampler,
387
388
389
390
                                              symbols=self.theta_symbols,
                                              **kwargs)
                fig.tight_layout()
                fig.savefig('{}/{}_init_{}_walkers.png'.format(
391
                    self.outdir, self.label, j), dpi=400)
392

393
394
395
            p0 = self._get_new_p0(sampler)
            p0 = self._apply_corrections_to_p0(p0)
            self._check_initial_points(p0)
396
397
            sampler.reset()

Gregory Ashton's avatar
Gregory Ashton committed
398
399
400
401
        if len(self.nsteps) > 1:
            nburn = self.nsteps[-2]
        else:
            nburn = 0
402
403
404
        nprod = self.nsteps[-1]
        logging.info('Running final burn and prod with {} steps'.format(
            nburn+nprod))
405
        sampler = self._run_sampler(sampler, p0, nburn=nburn, nprod=nprod)
406
407
        logging.info("Mean acceptance fraction: {}"
                     .format(np.mean(sampler.acceptance_fraction, axis=1)))
408
409
410
        if self.ntemps > 1:
            logging.info("Tswap acceptance fraction: {}"
                         .format(sampler.tswap_acceptance_fraction))
411

412
        if create_plots:
413
            fig, axes = self._plot_walkers(sampler, symbols=self.theta_symbols,
414
                                          nprod=nprod, **kwargs)
415
416
417
            fig.tight_layout()
            fig.savefig('{}/{}_walkers.png'.format(self.outdir, self.label),
                        dpi=200)
418
419
420
421

        samples = sampler.chain[0, :, nburn:, :].reshape((-1, self.ndim))
        lnprobs = sampler.lnprobability[0, :, nburn:].reshape((-1))
        lnlikes = sampler.lnlikelihood[0, :, nburn:].reshape((-1))
422
        all_lnlikelihood = sampler.lnlikelihood[:, :, nburn:]
423
424
425
        self.samples = samples
        self.lnprobs = lnprobs
        self.lnlikes = lnlikes
426
427
        self.all_lnlikelihood = all_lnlikelihood
        self._save_data(sampler, samples, lnprobs, lnlikes, all_lnlikelihood)
428

429
    def _get_rescale_multiplier_for_key(self, key):
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
        """ Get the rescale multiplier from the rescale_dictionary

        Can either be a float, a string (in which case it is interpretted as
        a attribute of the MCMCSearch class, e.g. minStartTime, or non-existent
        in which case 0 is returned
        """
        if key not in self.rescale_dictionary:
            return 1

        if 'multiplier' in self.rescale_dictionary[key]:
            val = self.rescale_dictionary[key]['multiplier']
            if type(val) == str:
                if hasattr(self, val):
                    multiplier = getattr(
                        self, self.rescale_dictionary[key]['multiplier'])
                else:
                    raise ValueError(
                        "multiplier {} not a class attribute".format(val))
            else:
                multiplier = val
        else:
            multiplier = 1
        return multiplier

454
    def _get_rescale_subtractor_for_key(self, key):
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
        """ Get the rescale subtractor from the rescale_dictionary

        Can either be a float, a string (in which case it is interpretted as
        a attribute of the MCMCSearch class, e.g. minStartTime, or non-existent
        in which case 0 is returned
        """
        if key not in self.rescale_dictionary:
            return 0

        if 'subtractor' in self.rescale_dictionary[key]:
            val = self.rescale_dictionary[key]['subtractor']
            if type(val) == str:
                if hasattr(self, val):
                    subtractor = getattr(
                        self, self.rescale_dictionary[key]['subtractor'])
                else:
                    raise ValueError(
                        "subtractor {} not a class attribute".format(val))
            else:
                subtractor = val
        else:
            subtractor = 0
        return subtractor

479
    def _scale_samples(self, samples, theta_keys):
480
        """ Scale the samples using the rescale_dictionary """
481
482
483
484
        for key in theta_keys:
            if key in self.rescale_dictionary:
                idx = theta_keys.index(key)
                s = samples[:, idx]
485
                subtractor = self._get_rescale_subtractor_for_key(key)
486
                s = s - subtractor
487
                multiplier = self._get_rescale_multiplier_for_key(key)
488
                s *= multiplier
489
490
                samples[:, idx] = s

491
492
        return samples

493
    def _get_labels(self):
494
        """ Combine the units, symbols and rescaling to give labels """
495

496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
        labels = []
        for key in self.theta_keys:
            label = None
            s = self.symbol_dictionary[key]
            s.replace('_{glitch}', r'_\textrm{glitch}')
            u = self.unit_dictionary[key]
            if key in self.rescale_dictionary:
                if 'symbol' in self.rescale_dictionary[key]:
                    s = self.rescale_dictionary[key]['symbol']
                if 'label' in self.rescale_dictionary[key]:
                    label = self.rescale_dictionary[key]['label']
                if 'unit' in self.rescale_dictionary[key]:
                    u = self.rescale_dictionary[key]['unit']
            if label is None:
                label = '{} \n [{}]'.format(s, u)
            labels.append(label)
        return labels
513

514
515
    def plot_corner(self, figsize=(7, 7), add_prior=False, nstds=None,
                    label_offset=0.4, dpi=300, rc_context={},
516
                    tglitch_ratio=False, fig_and_axes=None, save_fig=True,
517
                    **kwargs):
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
        """ Generate a corner plot of the posterior

        Using the `corner` package (https://pypi.python.org/pypi/corner/),
        generate estimates of the posterior from the production samples.

        Parameters
        ----------
        figsize: tuple (7, 7)
            Figure size in inches (passed to plt.subplots)
        add_prior: bool
            If true, plot the prior as a red line
        nstds: float
            The number of standard deviations to plot centered on the mean
        label_offset: float
            Offset the labels from the plot: useful to precent overlapping the
            tick labels with the axis labels
        dpi: int
            Passed to plt.savefig
        rc_context: dict
            Dictionary of rc values to set while generating the figure (see
            matplotlib rc for more details)
        tglitch_ratio: bool
            If true, and tglitch is a parameter, plot posteriors as the
            fractional time at which the glitch occurs instead of the actual
            time
543
544
545
546
547
        fig_and_axes: tuple
            fig and axes to plot on, the axes must be of the right shape,
            namely (ndim, ndim)
        save_fig: bool
            If true, save the figure, else return the fig, axes
548
549
550
551

        Note: kwargs are passed on to corner.coner

        """
552

553
554
555
556
        if 'truths' in kwargs and len(kwargs['truths']) != self.ndim:
            logging.warning('len(Truths) != ndim, Truths will be ignored')
            kwargs['truths'] = None

Gregory Ashton's avatar
Gregory Ashton committed
557
558
        if self.ndim < 2:
            with plt.rc_context(rc_context):
559
560
561
562
                if fig_and_axes is None:
                    fig, ax = plt.subplots(figsize=figsize)
                else:
                    fig, ax = fig_and_axes
Gregory Ashton's avatar
Gregory Ashton committed
563
564
565
566
567
568
569
                ax.hist(self.samples, bins=50, histtype='stepfilled')
                ax.set_xlabel(self.theta_symbols[0])

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

570
        with plt.rc_context(rc_context):
571
572
573
574
575
            if fig_and_axes is None:
                fig, axes = plt.subplots(self.ndim, self.ndim,
                                         figsize=figsize)
            else:
                fig, axes = fig_and_axes
576
577

            samples_plt = copy.copy(self.samples)
578
            labels = self._get_labels()
579

580
            samples_plt = self._scale_samples(samples_plt, self.theta_keys)
581
582
583
584
585

            if tglitch_ratio:
                for j, k in enumerate(self.theta_keys):
                    if k == 'tglitch':
                        s = samples_plt[:, j]
586
587
588
                        samples_plt[:, j] = (
                            s - self.minStartTime)/(
                                self.maxStartTime - self.minStartTime)
589
                        labels[j] = r'$R_{\textrm{glitch}}$'
590
591
592
593
594
595
596

            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))
597
598
            elif 'range' in kwargs:
                _range = kwargs.pop('range')
599
600
601
602
            else:
                _range = None

            fig_triangle = corner.corner(samples_plt,
603
                                         labels=labels,
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
                                         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:
629
                self._add_prior_to_corner(axes, self.samples)
630

631
632
633
634
635
            if save_fig:
                fig_triangle.savefig('{}/{}_corner.png'.format(
                    self.outdir, self.label), dpi=dpi)
            else:
                return fig, axes
636

637
    def _add_prior_to_corner(self, axes, samples):
638
639
640
641
        for i, key in enumerate(self.theta_keys):
            ax = axes[i][i]
            xlim = ax.get_xlim()
            s = samples[:, i]
642
            prior = self._generic_lnprior(**self.theta_prior[key])
643
            x = np.linspace(s.min(), s.max(), 100)
644
645
            multiplier = self._get_rescale_multiplier_for_key(key)
            subtractor = self._get_rescale_subtractor_for_key(key)
646
647
            ax2 = ax.twinx()
            ax2.get_yaxis().set_visible(False)
648
649
            ax2.plot((x-subtractor)*multiplier, [prior(xi) for xi in x], '-r')
            ax2.set_xlim(xlim)
650

651
652
653
654
655
656
657
658
    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]
659
            prior_func = self._generic_lnprior(**prior_dict)
660
661
662
663
664
665
666
667
668
669
            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)
670
671
672
673
674
            elif prior_dict['type'] == 'halfnorm':
                lower = prior_dict['loc']
                upper = prior_dict['loc'] + normal_stds * prior_dict['scale']
                x = np.linspace(lower, upper, N)
                prior = [prior_func(xi) for xi in x]
Gregory Ashton's avatar
Gregory Ashton committed
675
676
677
678
679
            elif prior_dict['type'] == 'neghalfnorm':
                upper = prior_dict['loc']
                lower = prior_dict['loc'] - normal_stds * prior_dict['scale']
                x = np.linspace(lower, upper, N)
                prior = [prior_func(xi) for xi in x]
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
            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))

703
    def plot_cumulative_max(self, **kwargs):
704
705
706
707
        """ Plot the cumulative twoF for the maximum posterior estimate

        See the pyfstat.core.plot_twoF_cumulative function for further details
        """
Gregory Ashton's avatar
Gregory Ashton committed
708
709
710
711
        d, maxtwoF = self.get_max_twoF()
        for key, val in self.theta_prior.iteritems():
            if key not in d:
                d[key] = val
712
713

        if hasattr(self, 'search') is False:
714
            self._initiate_search_object()
715
716
717
        if self.binary is False:
            self.search.plot_twoF_cumulative(
                self.label, self.outdir, F0=d['F0'], F1=d['F1'], F2=d['F2'],
718
                Alpha=d['Alpha'], Delta=d['Delta'],
719
                tstart=self.minStartTime, tend=self.maxStartTime,
720
                **kwargs)
721
722
723
724
725
        else:
            self.search.plot_twoF_cumulative(
                self.label, self.outdir, F0=d['F0'], F1=d['F1'], F2=d['F2'],
                Alpha=d['Alpha'], Delta=d['Delta'], asini=d['asini'],
                period=d['period'], ecc=d['ecc'], argp=d['argp'], tp=d['argp'],
726
                tstart=self.minStartTime, tend=self.maxStartTime, **kwargs)
Gregory Ashton's avatar
Gregory Ashton committed
727

728
    def _generic_lnprior(self, **kwargs):
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
        """ 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):
753
            if x < loc:
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
                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'])
771
772
        elif kwargs['type'] == 'neghalfnorm':
            return lambda x: halfnorm(-x, kwargs['loc'], kwargs['scale'])
773
774
775
776
777
778
779
        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")

780
    def _generate_rv(self, **kwargs):
781
782
783
784
785
786
787
788
        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']))
789
790
791
        if dist_type == "neghalfnorm":
            return -1 * np.abs(np.random.normal(loc=kwargs['loc'],
                                                scale=kwargs['scale']))
792
793
794
795
796
797
        if dist_type == "lognorm":
            return np.random.lognormal(
                mean=kwargs['loc'], sigma=kwargs['scale'])
        else:
            raise ValueError("dist_type {} unknown".format(dist_type))

798
799
800
    def _plot_walkers(self, sampler, symbols=None, alpha=0.4, color="k",
                      temp=0, lw=0.1, nprod=0, add_det_stat_burnin=False,
                      fig=None, axes=None, xoffset=0, plot_det_stat=False,
801
                      context='ggplot', subtractions=None, labelpad=0.05):
802
803
        """ Plot all the chains from a sampler """

804
805
806
807
808
        if context not in plt.style.available:
            raise ValueError((
                'The requested context {} is not available; please select a'
                ' context from `plt.style.available`').format(context))

809
810
811
        if np.ndim(axes) > 1:
            axes = axes.flatten()

812
813
814
815
816
817
818
819
820
821
822
823
824
        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, :, :, :]

825
826
        if subtractions is None:
            subtractions = [0 for i in range(ndim)]
827
828
829
        else:
            if len(subtractions) != self.ndim:
                raise ValueError('subtractions must be of length ndim')
830

831
832
833
834
        if plot_det_stat:
            extra_subplots = 1
        else:
            extra_subplots = 0
835
        with plt.style.context((context)):
Gregory Ashton's avatar
Gregory Ashton committed
836
            plt.rcParams['text.usetex'] = True
Gregory Ashton's avatar
Gregory Ashton committed
837
            if fig is None and axes is None:
838
                fig = plt.figure(figsize=(4, 3.0*ndim))
839
840
                ax = fig.add_subplot(ndim+extra_subplots, 1, 1)
                axes = [ax] + [fig.add_subplot(ndim+extra_subplots, 1, i)
Gregory Ashton's avatar
Gregory Ashton committed
841
                               for i in range(2, ndim+1)]
842

Gregory Ashton's avatar
Gregory Ashton committed
843
            idxs = np.arange(chain.shape[1])
844
845
846
847
848
            burnin_idx = chain.shape[1] - nprod
            if hasattr(self, 'convergence_idx'):
                convergence_idx = self.convergence_idx
            else:
                convergence_idx = burnin_idx
849
850
            if ndim > 1:
                for i in range(ndim):
851
                    axes[i].ticklabel_format(useOffset=False, axis='y')
Gregory Ashton's avatar
Gregory Ashton committed
852
                    cs = chain[:, :, i].T
853
                    if burnin_idx > 0:
854
855
                        axes[i].plot(xoffset+idxs[:convergence_idx+1],
                                     cs[:convergence_idx+1]-subtractions[i],
856
                                     color="r", alpha=alpha,
Gregory Ashton's avatar
Gregory Ashton committed
857
                                     lw=lw)
858
                        axes[i].axvline(xoffset+convergence_idx,
859
                                        color='k', ls='--', lw=0.25)
860
861
                    axes[i].plot(xoffset+idxs[burnin_idx:],
                                 cs[burnin_idx:]-subtractions[i],
Gregory Ashton's avatar
Gregory Ashton committed
862
                                 color="k", alpha=alpha, lw=lw)
863
                    if symbols:
864
                        if subtractions[i] == 0:
865
                            axes[i].set_ylabel(symbols[i], labelpad=labelpad)
866
867
                        else:
                            axes[i].set_ylabel(
868
869
                                symbols[i]+'$-$'+symbols[i]+'$_0$',
                                labelpad=labelpad)
870

871
872
                    if hasattr(self, 'convergence_diagnostic'):
                        ax = axes[i].twinx()
873
874
                        c_x = np.array(self.convergence_diagnosticx)
                        c_y = np.array(self.convergence_diagnostic)
875
876
877
878
                        break_idx = np.argmin(np.abs(c_x - burnin_idx))
                        ax.plot(c_x[:break_idx], c_y[:break_idx, i], '-b')
                        ax.plot(c_x[break_idx:], c_y[break_idx:, i], '-b')
                        ax.set_ylabel('PSRF')
879
                        ax.ticklabel_format(useOffset=False)
880
                        ax.set_ylim(0.5, self.convergence_plot_upper_lim)
881
            else:
Gregory Ashton's avatar
Gregory Ashton committed
882
                axes[0].ticklabel_format(useOffset=False, axis='y')
Gregory Ashton's avatar
Gregory Ashton committed
883
                cs = chain[:, :, temp].T
Gregory Ashton's avatar
Gregory Ashton committed
884
885
886
887
888
889
                if burnin_idx:
                    axes[0].plot(idxs[:burnin_idx], cs[:burnin_idx],
                                 color="r", alpha=alpha, lw=lw)
                axes[0].plot(idxs[burnin_idx:], cs[burnin_idx:], color="k",
                             alpha=alpha, lw=lw)
                if symbols:
890
                    axes[0].set_ylabel(symbols[0], labelpad=labelpad)
891

892
            if plot_det_stat:
893
894
895
                if len(axes) == ndim:
                    axes.append(fig.add_subplot(ndim+1, 1, ndim+1))

896
897
898
                lnl = sampler.lnlikelihood[temp, :, :]
                if burnin_idx and add_det_stat_burnin:
                    burn_in_vals = lnl[:, :burnin_idx].flatten()
899
900
901
902
903
904
905
                    try:
                        axes[-1].hist(burn_in_vals[~np.isnan(burn_in_vals)],
                                      bins=50, histtype='step', color='r')
                    except ValueError:
                        logging.info('Det. Stat. hist failed, most likely all '
                                     'values where the same')
                        pass
906
907
908
                else:
                    burn_in_vals = []
                prod_vals = lnl[:, burnin_idx:].flatten()
909
910
911
912
913
914
915
                try:
                    axes[-1].hist(prod_vals[~np.isnan(prod_vals)], bins=50,
                                  histtype='step', color='k')
                except ValueError:
                    logging.info('Det. Stat. hist failed, most likely all '
                                 'values where the same')
                    pass
916
917
918
919
920
921
922
923
924
925
926
927
                if self.BSGL:
                    axes[-1].set_xlabel(r'$\mathcal{B}_\mathrm{S/GL}$')
                else:
                    axes[-1].set_xlabel(r'$\widetilde{2\mathcal{F}}$')
                axes[-1].set_ylabel(r'$\textrm{Counts}$')
                combined_vals = np.append(burn_in_vals, prod_vals)
                if len(combined_vals) > 0:
                    minv = np.min(combined_vals)
                    maxv = np.max(combined_vals)
                    Range = abs(maxv-minv)
                    axes[-1].set_xlim(minv-0.1*Range, maxv+0.1*Range)

928
                xfmt = matplotlib.ticker.ScalarFormatter()
929
                xfmt.set_powerlimits((-4, 4))
930
931
                axes[-1].xaxis.set_major_formatter(xfmt)

932
            axes[-2].set_xlabel(r'$\textrm{Number of steps}$', labelpad=0.2)
933
934
        return fig, axes

935
    def _apply_corrections_to_p0(self, p0):
Gregory Ashton's avatar
Gregory Ashton committed
936
937
938
        """ Apply any correction to the initial p0 values """
        return p0

939
    def _generate_scattered_p0(self, p):
940
        """ Generate a set of p0s scattered about p """
Gregory Ashton's avatar
Gregory Ashton committed
941
        p0 = [[p + self.scatter_val * p * np.random.randn(self.ndim)
942
943
944
945
               for i in xrange(self.nwalkers)]
              for j in xrange(self.ntemps)]
        return p0

946
    def _generate_initial_p0(self):
947
948
949
        """ Generate a set of init vals for the walkers """

        if type(self.theta_initial) == dict:
950
            logging.info('Generate initial values from initial dictionary')
951
            if hasattr(self, 'nglitch') and self.nglitch > 1:
952
                raise ValueError('Initial dict not implemented for nglitch>1')
953
            p0 = [[[self._generate_rv(**self.theta_initial[key])
954
955
956
                    for key in self.theta_keys]
                   for i in range(self.nwalkers)]
                  for j in range(self.ntemps)]
957
958
        elif type(self.theta_initial) == list:
            logging.info('Generate initial values from list of theta_initial')
959
            p0 = [[[self._generate_rv(**val)
960
961
962
                    for val in self.theta_initial]
                   for i in range(self.nwalkers)]
                  for j in range(self.ntemps)]
963
        elif self.theta_initial is None:
964
            logging.info('Generate initial values from prior dictionary')
965
            p0 = [[[self._generate_rv(**self.theta_prior[key])
966
967
968
969
                    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:
970
            p0 = self._generate_scattered_p0(self.theta_initial)
971
972
973
974
975
        else:
            raise ValueError('theta_initial not understood')

        return p0

976
    def _get_new_p0(self, sampler):
977
978
979
980
981
982
        """ 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
983
984
985
986
        temp_idx = 0
        pF = sampler.chain[temp_idx, :, :, :]
        lnl = sampler.lnlikelihood[temp_idx, :, :]
        lnp = sampler.lnprobability[temp_idx, :, :]
987
988

        # General warnings about the state of lnp
Gregory Ashton's avatar
Gregory Ashton committed
989
        if np.any(np.isnan(lnp)):
990
991
            logging.warning(
                "Of {} lnprobs {} are nan".format(
Gregory Ashton's avatar
Gregory Ashton committed
992
993
                    np.shape(lnp), np.sum(np.isnan(lnp))))
        if np.any(np.isposinf(lnp)):
994
995
            logging.warning(
                "Of {} lnprobs {} are +np.inf".format(
Gregory Ashton's avatar
Gregory Ashton committed
996
997
                    np.shape(lnp), np.sum(np.isposinf(lnp))))
        if np.any(np.isneginf(lnp)):
998
999
            logging.warning(
                "Of {} lnprobs {} are -np.inf".format(
Gregory Ashton's avatar
Gregory Ashton committed
1000
                    np.shape(lnp), np.sum(np.isneginf(lnp))))
1001

1002
1003
        lnp_finite = copy.copy(lnp)
        lnp_finite[np.isinf(lnp)] = np.nan
Gregory Ashton's avatar
Gregory Ashton committed
1004
1005
        idx = np.unravel_index(np.nanargmax(lnp_finite), lnp_finite.shape)
        p = pF[idx]
1006
        p0 = self._generate_scattered_p0(p)
1007

1008
1009
1010
1011
1012
1013
1014
1015
        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]))

1016
1017
        return p0

1018
    def _get_data_dictionary_to_save(self):
1019
1020
        d = dict(nsteps=self.nsteps, nwalkers=self.nwalkers,
                 ntemps=self.ntemps, theta_keys=self.theta_keys,
Gregory Ashton's avatar
Gregory Ashton committed
1021
                 theta_prior=self.theta_prior, scatter_val=self.scatter_val,
1022
                 log10temperature_min=self.log10temperature_min,
1023
                 BSGL=self.BSGL)
1024
1025
        return d

1026
    def _save_data(self, sampler, samples, lnprobs, lnlikes, all_lnlikelihood):
1027
        d = self._get_data_dictionary_to_save()
1028
1029
1030
        d['samples'] = samples
        d['lnprobs'] = lnprobs
        d['lnlikes'] = lnlikes
1031
        d['all_lnlikelihood'] = all_lnlikelihood
1032
1033
1034
1035
1036
1037
1038
1039

        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)

1040
1041
    def get_saved_data_dictionary(self):
        """ Returns dictionary of the data saved as pickle """
1042
1043
1044
1045
        with open(self.pickle_path, "r") as File:
            d = pickle.load(File)
        return d

1046
    def _check_old_data_is_okay_to_use(self):
1047
1048
1049
1050
        if args.use_old_data:
            logging.info("Forcing use of old data")
            return True