mcmc_based_searches.py 84.9 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
27
28
29
30
31
32
33

    symbol_dictionary = dict(
        F0='$f$', F1='$\dot{f}$', F2='$\ddot{f}$', alpha=r'$\alpha$',
        delta='$\delta$')
    unit_dictionary = dict(
        F0='Hz', F1='Hz/s', F2='Hz/s$^2$', alpha=r'rad', delta='rad')
    rescale_dictionary = {}


Gregory Ashton's avatar
Gregory Ashton committed
34
    @helper_functions.initializer
Gregory Ashton's avatar
Gregory Ashton committed
35
36
    def __init__(self, label, outdir, theta_prior, tref, minStartTime,
                 maxStartTime, sftfilepath=None, nsteps=[100, 100],
37
38
                 nwalkers=100, ntemps=1, log10temperature_min=-5,
                 theta_initial=None, scatter_val=1e-10,
39
                 binary=False, BSGL=False, minCoverFreq=None,
40
                 maxCoverFreq=None, detectors=None, earth_ephem=None,
41
                 sun_ephem=None, injectSources=None, assumeSqrtSX=None):
42
43
44
45
        """
        Parameters
        label, outdir: str
            A label and directory to read/write data from/to
46
47
        sftfilepath: str
            File patern to match SFTs
48
        theta_prior: dict
49
50
51
52
            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.
53
54
55
56
        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.
57
        tref, minStartTime, maxStartTime: int
58
59
60
61
62
63
            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].
64
65
66
67
68
69
70
71
        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
72
        detectors: str
73
74
            Two character reference to the data to use, specify None for no
            contraint.
75
76
77
78
79
80
81
82
83
84
        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
85
86
        if os.path.isdir(outdir) is False:
            os.mkdir(outdir)
87
        self.add_log_file()
Gregory Ashton's avatar
Gregory Ashton committed
88
89
        logging.info(
            'Set-up MCMC search for model {} on data {}'.format(
90
                self.label, self.sftfilepath))
91
92
93
        self.pickle_path = '{}/{}_saved_data.p'.format(self.outdir, self.label)
        self.unpack_input_theta()
        self.ndim = len(self.theta_keys)
94
95
96
97
        if self.log10temperature_min:
            self.betas = np.logspace(0, self.log10temperature_min, self.ntemps)
        else:
            self.betas = None
98

99
100
101
102
103
104
105
106
        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")

107
108
109
        self.log_input()

    def log_input(self):
110
        logging.info('theta_prior = {}'.format(self.theta_prior))
111
        logging.info('nwalkers={}'.format(self.nwalkers))
112
113
114
115
        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(
116
            self.log10temperature_min))
117

Gregory Ashton's avatar
Gregory Ashton committed
118
    def initiate_search_object(self):
119
        logging.info('Setting up search object')
120
        self.search = core.ComputeFstat(
121
122
123
            tref=self.tref, sftfilepath=self.sftfilepath,
            minCoverFreq=self.minCoverFreq, maxCoverFreq=self.maxCoverFreq,
            earth_ephem=self.earth_ephem, sun_ephem=self.sun_ephem,
124
            detectors=self.detectors, BSGL=self.BSGL, transient=False,
125
            minStartTime=self.minStartTime, maxStartTime=self.maxStartTime,
126
127
            binary=self.binary, injectSources=self.injectSources,
            assumeSqrtSX=self.assumeSqrtSX)
128
129

    def logp(self, theta_vals, theta_prior, theta_keys, search):
Gregory Ashton's avatar
Gregory Ashton committed
130
        H = [self.generic_lnprior(**theta_prior[key])(p) for p, key in
131
132
133
134
135
136
             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]
137
138
        FS = search.compute_fullycoherent_det_stat_single_point(
            *self.fixed_theta)
139
140
141
        return FS

    def unpack_input_theta(self):
142
        full_theta_keys = ['F0', 'F1', 'F2', 'Alpha', 'Delta']
143
144
145
        if self.binary:
            full_theta_keys += [
                'asini', 'period', 'ecc', 'tp', 'argp']
146
147
        full_theta_keys_copy = copy.copy(full_theta_keys)

148
149
        full_theta_symbols = ['$f$', '$\dot{f}$', '$\ddot{f}$', r'$\alpha$',
                              r'$\delta$']
150
151
152
153
        if self.binary:
            full_theta_symbols += [
                'asini', 'period', 'period', 'ecc', 'tp', 'argp']

154
155
        self.theta_keys = []
        fixed_theta_dict = {}
156
        for key, val in self.theta_prior.iteritems():
157
158
            if type(val) is dict:
                fixed_theta_dict[key] = 0
Gregory Ashton's avatar
Gregory Ashton committed
159
                self.theta_keys.append(key)
160
161
162
163
164
165
            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
166
            full_theta_keys_copy.pop(full_theta_keys_copy.index(key))
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182

        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):
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
        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
219

220
    def OLD_run_sampler_with_progress_bar(self, sampler, ns, p0):
221
222
        for result in tqdm(sampler.sample(p0, iterations=ns), total=ns):
            pass
Gregory Ashton's avatar
Gregory Ashton committed
223
224
        return sampler

225
226
    def setup_convergence_testing(
            self, convergence_period=10, convergence_length=10,
227
            convergence_burnin_fraction=0.25, convergence_threshold_number=10,
228
229
            convergence_threshold=1.2, convergence_prod_threshold=2,
            convergence_plot_upper_lim=2):
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
        """
        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
256
257
        convergence_plot_upper_lim: float
            the upper limit to use in the diagnostic plot
258
        """
259
260
261
262
263
264
265

        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
266
        self.convergence_prod_threshold = convergence_prod_threshold
267
268
269
270
271
        self.convergence_diagnostic = []
        self.convergence_diagnosticx = []
        self.convergence_threshold_number = convergence_threshold_number
        self.convergence_threshold = convergence_threshold
        self.convergence_number = 0
272
        self.convergence_plot_upper_lim = convergence_plot_upper_lim
273

274
    def get_convergence_statistic(self, i, sampler):
275
276
277
278
279
280
281
282
283
        s = sampler.chain[0, :, i-self.convergence_length+1:i+1, :]
        within_std = np.mean(np.var(s, axis=1), axis=0)
        per_walker_mean = np.mean(s, axis=1)
        mean = np.mean(per_walker_mean, axis=0)
        between_std = np.sqrt(np.mean((per_walker_mean-mean)**2, axis=0))
        W = within_std
        B_over_n = between_std**2 / self.convergence_period
        Vhat = ((self.convergence_period-1.)/self.convergence_period * W
                + B_over_n + B_over_n / float(self.nwalkers))
284
        c = np.sqrt(Vhat/W)
285
        self.convergence_diagnostic.append(c)
286
        self.convergence_diagnosticx.append(i - self.convergence_length/2)
287
288
        return c

289
    def burnin_convergence_test(self, i, sampler, nburn):
290
291
        if i < self.convergence_burnin_fraction*nburn:
            return False
292
        if np.mod(i+1, self.convergence_period) != 0:
293
294
            return False
        c = self.get_convergence_statistic(i, sampler)
295
296
        if np.all(c < self.convergence_threshold):
            self.convergence_number += 1
297
298
        else:
            self.convergence_number = 0
299
300
        return self.convergence_number > self.convergence_threshold_number

301
302
303
304
305
306
    def prod_convergence_test(self, i, sampler, nburn):
        testA = i > nburn + self.convergence_length
        testB = np.mod(i+1, self.convergence_period) == 0
        if testA and testB:
            self.get_convergence_statistic(i, sampler)

307
308
309
310
311
312
313
314
315
    def check_production_convergence(self, k):
        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)))

316
317
    def run_sampler(self, sampler, p0, nprod=0, nburn=0):
        if hasattr(self, 'convergence_period'):
318
319
320
321
            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):
322
                if self.burnin_convergence_test(i, sampler, nburn):
323
324
325
326
327
328
329
330
331
332
333
                    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):
334
                self.prod_convergence_test(j, sampler, nburn)
335
336
                j += 1
            self.check_production_convergence(k)
337
338
339
340
341
342
            return sampler
        else:
            for result in tqdm(sampler.sample(p0, iterations=nburn+nprod),
                               total=nburn+nprod):
                pass
            return sampler
343

344
    def run(self, proposal_scale_factor=2, create_plots=True, **kwargs):
345

Gregory Ashton's avatar
Gregory Ashton committed
346
        self.old_data_is_okay_to_use = self.check_old_data_is_okay_to_use()
347
348
349
350
351
352
353
354
355
356
        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

Gregory Ashton's avatar
Gregory Ashton committed
357
        self.initiate_search_object()
358
359
360
361

        sampler = emcee.PTSampler(
            self.ntemps, self.nwalkers, self.ndim, self.logl, self.logp,
            logpargs=(self.theta_prior, self.theta_keys, self.search),
362
            loglargs=(self.search,), betas=self.betas, a=proposal_scale_factor)
363

Gregory Ashton's avatar
Gregory Ashton committed
364
365
        p0 = self.generate_initial_p0()
        p0 = self.apply_corrections_to_p0(p0)
366
367
368
369
370
        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(
Gregory Ashton's avatar
Gregory Ashton committed
371
                j, ninit_steps, n))
372
            sampler = self.run_sampler(sampler, p0, nburn=n)
373
374
            logging.info("Mean acceptance fraction: {}"
                         .format(np.mean(sampler.acceptance_fraction, axis=1)))
375
376
377
            if self.ntemps > 1:
                logging.info("Tswap acceptance fraction: {}"
                             .format(sampler.tswap_acceptance_fraction))
378
379
380
381
382
383
            if create_plots:
                fig, axes = self.plot_walkers(sampler,
                                              symbols=self.theta_symbols,
                                              **kwargs)
                fig.tight_layout()
                fig.savefig('{}/{}_init_{}_walkers.png'.format(
384
                    self.outdir, self.label, j), dpi=400)
385

386
            p0 = self.get_new_p0(sampler)
Gregory Ashton's avatar
Gregory Ashton committed
387
            p0 = self.apply_corrections_to_p0(p0)
388
389
390
            self.check_initial_points(p0)
            sampler.reset()

Gregory Ashton's avatar
Gregory Ashton committed
391
392
393
394
        if len(self.nsteps) > 1:
            nburn = self.nsteps[-2]
        else:
            nburn = 0
395
396
397
        nprod = self.nsteps[-1]
        logging.info('Running final burn and prod with {} steps'.format(
            nburn+nprod))
398
        sampler = self.run_sampler(sampler, p0, nburn=nburn, nprod=nprod)
399
400
        logging.info("Mean acceptance fraction: {}"
                     .format(np.mean(sampler.acceptance_fraction, axis=1)))
401
402
403
        if self.ntemps > 1:
            logging.info("Tswap acceptance fraction: {}"
                         .format(sampler.tswap_acceptance_fraction))
404

405
406
        if create_plots:
            fig, axes = self.plot_walkers(sampler, symbols=self.theta_symbols,
407
                                          nprod=nprod, **kwargs)
408
409
410
            fig.tight_layout()
            fig.savefig('{}/{}_walkers.png'.format(self.outdir, self.label),
                        dpi=200)
411
412
413
414
415
416
417
418
419
420

        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)

421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
    def get_rescale_multiplier_for_key(self, key):
        """ 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

    def get_rescale_subtractor_for_key(self, key):
        """ 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

    def scale_samples(self, samples, theta_keys):
        """ Scale the samples using the rescale_dictionary """
473
474
475
476
        for key in theta_keys:
            if key in self.rescale_dictionary:
                idx = theta_keys.index(key)
                s = samples[:, idx]
477
478
479
480
                subtractor = self.get_rescale_subtractor_for_key(key)
                s = s - subtractor
                multiplier = self.get_rescale_multiplier_for_key(key)
                s *= multiplier
481
482
                samples[:, idx] = s

483
484
485
486
        return samples

    def get_labels(self):
        """ Combine the units, symbols and rescaling to give labels """
487

488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
        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
505

506
    def plot_corner(self, figsize=(7, 7),  tglitch_ratio=False,
507
508
509
                    add_prior=False, nstds=None, label_offset=0.4,
                    dpi=300, rc_context={}, **kwargs):

Gregory Ashton's avatar
Gregory Ashton committed
510
511
512
513
514
515
516
517
518
519
        if self.ndim < 2:
            with plt.rc_context(rc_context):
                fig, ax = plt.subplots(figsize=figsize)
                ax.hist(self.samples, bins=50, histtype='stepfilled')
                ax.set_xlabel(self.theta_symbols[0])

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

520
521
522
523
524
        with plt.rc_context(rc_context):
            fig, axes = plt.subplots(self.ndim, self.ndim,
                                     figsize=figsize)

            samples_plt = copy.copy(self.samples)
525
            labels = self.get_labels()
526

527
            samples_plt = self.scale_samples(samples_plt, self.theta_keys)
528
529
530
531
532

            if tglitch_ratio:
                for j, k in enumerate(self.theta_keys):
                    if k == 'tglitch':
                        s = samples_plt[:, j]
533
534
535
                        samples_plt[:, j] = (
                            s - self.minStartTime)/(
                                self.maxStartTime - self.minStartTime)
536
                        labels[j] = r'$R_{\textrm{glitch}}$'
537
538
539
540
541
542
543
544
545
546
547

            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,
548
                                         labels=labels,
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
                                         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)
578
579
580
581
582
583

    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
584
            prior = self.generic_lnprior(**self.theta_prior[key])
585
            x = np.linspace(s.min(), s.max(), 100)
586
587
            multiplier = self.get_rescale_multiplier_for_key(key)
            subtractor = self.get_rescale_subtractor_for_key(key)
588
589
            ax2 = ax.twinx()
            ax2.get_yaxis().set_visible(False)
590
            ax2.plot(x, [(prior(xi)-subtractor)*multiplier for xi in x], '-r')
591
592
            ax.set_xlim(xlim)

593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
    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)
612
613
614
615
616
            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
617
618
619
620
621
            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]
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
            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))

645
    def plot_cumulative_max(self, **kwargs):
Gregory Ashton's avatar
Gregory Ashton committed
646
647
648
649
        d, maxtwoF = self.get_max_twoF()
        for key, val in self.theta_prior.iteritems():
            if key not in d:
                d[key] = val
650
651

        if hasattr(self, 'search') is False:
Gregory Ashton's avatar
Gregory Ashton committed
652
            self.initiate_search_object()
653
654
655
        if self.binary is False:
            self.search.plot_twoF_cumulative(
                self.label, self.outdir, F0=d['F0'], F1=d['F1'], F2=d['F2'],
656
                Alpha=d['Alpha'], Delta=d['Delta'],
657
                tstart=self.minStartTime, tend=self.maxStartTime,
658
                **kwargs)
659
660
661
662
663
        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'],
664
                tstart=self.minStartTime, tend=self.maxStartTime, **kwargs)
Gregory Ashton's avatar
Gregory Ashton committed
665

Gregory Ashton's avatar
Gregory Ashton committed
666
    def generic_lnprior(self, **kwargs):
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
        """ 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):
691
            if x < loc:
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
                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'])
709
710
        elif kwargs['type'] == 'neghalfnorm':
            return lambda x: halfnorm(-x, kwargs['loc'], kwargs['scale'])
711
712
713
714
715
716
717
        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
718
    def generate_rv(self, **kwargs):
719
720
721
722
723
724
725
726
        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']))
727
728
729
        if dist_type == "neghalfnorm":
            return -1 * np.abs(np.random.normal(loc=kwargs['loc'],
                                                scale=kwargs['scale']))
730
731
732
733
734
735
        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
736
    def plot_walkers(self, sampler, symbols=None, alpha=0.4, color="k", temp=0,
737
                     lw=0.1, nprod=0, add_det_stat_burnin=False,
738
                     fig=None, axes=None, xoffset=0, plot_det_stat=False,
739
                     context='classic', subtractions=None, labelpad=0.05):
740
741
        """ Plot all the chains from a sampler """

742
743
744
        if np.ndim(axes) > 1:
            axes = axes.flatten()

745
746
747
748
749
750
751
752
753
754
755
756
757
        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, :, :, :]

758
759
        if subtractions is None:
            subtractions = [0 for i in range(ndim)]
760
761
762
        else:
            if len(subtractions) != self.ndim:
                raise ValueError('subtractions must be of length ndim')
763

764
765
766
767
        if plot_det_stat:
            extra_subplots = 1
        else:
            extra_subplots = 0
768
        with plt.style.context((context)):
Gregory Ashton's avatar
Gregory Ashton committed
769
            plt.rcParams['text.usetex'] = True
Gregory Ashton's avatar
Gregory Ashton committed
770
            if fig is None and axes is None:
771
                fig = plt.figure(figsize=(4, 3.0*ndim))
772
773
                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
774
                               for i in range(2, ndim+1)]
775

Gregory Ashton's avatar
Gregory Ashton committed
776
            idxs = np.arange(chain.shape[1])
777
778
779
780
781
            burnin_idx = chain.shape[1] - nprod
            if hasattr(self, 'convergence_idx'):
                convergence_idx = self.convergence_idx
            else:
                convergence_idx = burnin_idx
782
783
            if ndim > 1:
                for i in range(ndim):
784
                    axes[i].ticklabel_format(useOffset=False, axis='y')
Gregory Ashton's avatar
Gregory Ashton committed
785
                    cs = chain[:, :, i].T
786
787
788
                    if burnin_idx > 0:
                        axes[i].plot(xoffset+idxs[:convergence_idx],
                                     cs[:convergence_idx]-subtractions[i],
789
                                     color="r", alpha=alpha,
Gregory Ashton's avatar
Gregory Ashton committed
790
                                     lw=lw)
791
792
                    axes[i].plot(xoffset+idxs[burnin_idx:],
                                 cs[burnin_idx:]-subtractions[i],
Gregory Ashton's avatar
Gregory Ashton committed
793
                                 color="k", alpha=alpha, lw=lw)
794
                    if symbols:
795
                        if subtractions[i] == 0:
796
                            axes[i].set_ylabel(symbols[i], labelpad=labelpad)
797
798
                        else:
                            axes[i].set_ylabel(
799
800
                                symbols[i]+'$-$'+symbols[i]+'$_0$',
                                labelpad=labelpad)
801

802
803
                    if hasattr(self, 'convergence_diagnostic'):
                        ax = axes[i].twinx()
804
805
                        c_x = np.array(self.convergence_diagnosticx)
                        c_y = np.array(self.convergence_diagnostic)
806
807
808
809
                        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')
810
                        ax.ticklabel_format(useOffset=False)
811
                        ax.set_ylim(1, self.convergence_plot_upper_lim)
812
            else:
Gregory Ashton's avatar
Gregory Ashton committed
813
                axes[0].ticklabel_format(useOffset=False, axis='y')
Gregory Ashton's avatar
Gregory Ashton committed
814
                cs = chain[:, :, temp].T
Gregory Ashton's avatar
Gregory Ashton committed
815
816
817
818
819
820
                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:
821
                    axes[0].set_ylabel(symbols[0], labelpad=labelpad)
822

823
            if plot_det_stat:
824
825
826
                if len(axes) == ndim:
                    axes.append(fig.add_subplot(ndim+1, 1, ndim+1))

827
828
829
                lnl = sampler.lnlikelihood[temp, :, :]
                if burnin_idx and add_det_stat_burnin:
                    burn_in_vals = lnl[:, :burnin_idx].flatten()
830
831
832
833
834
835
836
                    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
837
838
839
                else:
                    burn_in_vals = []
                prod_vals = lnl[:, burnin_idx:].flatten()
840
841
842
843
844
845
846
                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
847
848
849
850
851
852
853
854
855
856
857
858
                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)

859
                xfmt = matplotlib.ticker.ScalarFormatter()
860
                xfmt.set_powerlimits((-4, 4))
861
862
                axes[-1].xaxis.set_major_formatter(xfmt)

863
            axes[-2].set_xlabel(r'$\textrm{Number of steps}$', labelpad=0.2)
864
865
        return fig, axes

Gregory Ashton's avatar
Gregory Ashton committed
866
867
868
869
870
    def apply_corrections_to_p0(self, p0):
        """ Apply any correction to the initial p0 values """
        return p0

    def generate_scattered_p0(self, p):
871
        """ Generate a set of p0s scattered about p """
Gregory Ashton's avatar
Gregory Ashton committed
872
        p0 = [[p + self.scatter_val * p * np.random.randn(self.ndim)
873
874
875
876
               for i in xrange(self.nwalkers)]
              for j in xrange(self.ntemps)]
        return p0

Gregory Ashton's avatar
Gregory Ashton committed
877
    def generate_initial_p0(self):
878
879
880
        """ Generate a set of init vals for the walkers """

        if type(self.theta_initial) == dict:
881
            logging.info('Generate initial values from initial dictionary')
882
            if hasattr(self, 'nglitch') and self.nglitch > 1:
883
                raise ValueError('Initial dict not implemented for nglitch>1')
Gregory Ashton's avatar
Gregory Ashton committed
884
            p0 = [[[self.generate_rv(**self.theta_initial[key])
885
886
887
                    for key in self.theta_keys]
                   for i in range(self.nwalkers)]
                  for j in range(self.ntemps)]
888
889
890
891
892
893
        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)]
894
        elif self.theta_initial is None:
895
            logging.info('Generate initial values from prior dictionary')
Gregory Ashton's avatar
Gregory Ashton committed
896
            p0 = [[[self.generate_rv(**self.theta_prior[key])
897
898
899
900
                    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
901
            p0 = self.generate_scattered_p0(self.theta_initial)
902
903
904
905
906
        else:
            raise ValueError('theta_initial not understood')

        return p0

907
    def get_new_p0(self, sampler):
908
909
910
911
912
913
        """ 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
914
915
916
917
        temp_idx = 0
        pF = sampler.chain[temp_idx, :, :, :]
        lnl = sampler.lnlikelihood[temp_idx, :, :]
        lnp = sampler.lnprobability[temp_idx, :, :]
918
919

        # General warnings about the state of lnp
Gregory Ashton's avatar
Gregory Ashton committed
920
        if np.any(np.isnan(lnp)):
921
922
            logging.warning(
                "Of {} lnprobs {} are nan".format(
Gregory Ashton's avatar
Gregory Ashton committed
923
924
                    np.shape(lnp), np.sum(np.isnan(lnp))))
        if np.any(np.isposinf(lnp)):
925
926
            logging.warning(
                "Of {} lnprobs {} are +np.inf".format(
Gregory Ashton's avatar
Gregory Ashton committed
927
928
                    np.shape(lnp), np.sum(np.isposinf(lnp))))
        if np.any(np.isneginf(lnp)):
929
930
            logging.warning(
                "Of {} lnprobs {} are -np.inf".format(
Gregory Ashton's avatar
Gregory Ashton committed
931
                    np.shape(lnp), np.sum(np.isneginf(lnp))))
932

933
934
        lnp_finite = copy.copy(lnp)
        lnp_finite[np.isinf(lnp)] = np.nan
Gregory Ashton's avatar
Gregory Ashton committed
935
936
        idx = np.unravel_index(np.nanargmax(lnp_finite), lnp_finite.shape)
        p = pF[idx]
937
        p0 = self.generate_scattered_p0(p)
938

939
940
941
942
943
944
945
946
        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]))

947
948
949
950
951
        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
952
                 theta_prior=self.theta_prior, scatter_val=self.scatter_val,
953
                 log10temperature_min=self.log10temperature_min,
954
                 BSGL=self.BSGL)
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
        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_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):
977
978
979
980
        if args.use_old_data:
            logging.info("Forcing use of old data")
            return True

981
982
983
984
        if os.path.isfile(self.pickle_path) is False:
            logging.info('No pickled data found')
            return False

Gregory Ashton's avatar
Gregory Ashton committed
985
986
987
988
989
990
        if self.sftfilepath is not None:
            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
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005

        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:
1006
                raise ValueError('Keys {} not in old dictionary'.format(key))
1007
1008
1009
1010
1011
1012
1013
1014
1015

        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':
1016
                        logging.info("    {} : {} -> {}".format(*key))
1017
                    else:
1018
                        logging.info("    " + key[0])
1019
1020
1021
1022
1023
                else:
                    logging.info(key)
            return False

    def get_max_twoF(self, threshold=0.05):
1024
        """ Returns the max likelihood sample and the corresponding 2F value
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038

        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])
1039
        maxlogl = self.lnlikes[jmax]
1040
        d = OrderedDict()
1041

1042
1043
        if self.BSGL:
            if hasattr(self, 'search') is False:
Gregory Ashton's avatar
Gregory Ashton committed
1044
                self.initiate_search_object()
1045
1046
1047
1048
1049
1050
1051
            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
1052
        repeats = []
1053
        for i, k in enumerate(self.theta_keys):
Gregory Ashton's avatar
Gregory Ashton committed
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
            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
1064
1065
1066
1067
1068
            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 """
1069
        d = OrderedDict()
Gregory Ashton's avatar
Gregory Ashton committed
1070
        repeats = []
1071
        for s, k in zip(self.samples.T, self.theta_keys):
Gregory Ashton's avatar
Gregory Ashton committed
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
            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

1085
1086
1087
1088
            d[k] = np.median(s)
            d[k+'_std'] = np.std(s)
        return d

1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
    def check_if_samples_are_railing(self, threshold=0.01):
        return_flag = False
        for s, k in zip(self.samples.T, self.theta_keys):
            prior = self.theta_prior[k]
            if prior['type'] == 'unif':
                prior_range = prior['upper'] - prior['lower']
                edges = []
                fracs = []
                for l in ['lower', 'upper']:
                    bools = np.abs(s - prior[l])/prior_range < threshold
                    if np.any(bools):
                        edges.append(l)
                        fracs.append(str(100*float(np.sum(bools))/len(bools)))
                if len(edges) > 0:
                    logging.warning(
                        '{}% of the {} posterior is railing on the {} edges'
                        .format('% & '.join(fracs), k, ' & '.join(edges)))
                    return_flag = True
        return return_flag

1109
1110
1111
1112
    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))
1113
1114
1115
1116

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

Gregory Ashton's avatar
Gregory Ashton committed
1117
        logging.info('Writing par file with max twoF = {}'.format(max_twoF))
1118
1119
1120
        filename = '{}/{}.par'.format(self.outdir, self.label)
        with open(filename, 'w+') as f:
            f.write('MaxtwoF = {}\n'.format(max_twoF))
Gregory Ashton's avatar
Gregory Ashton committed
1121
            f.write('tref = {}\n'.format(self.tref))
1122
1123
            if hasattr(self, 'theta0_index'):
                f.write('theta0_index = {}\n'.format(self.theta0_idx))
1124
            if method == 'med':
1125
1126
                for key, val in median_std_d.iteritems():
                    f.write('{} = {:1.16e}\n'.format(key, val))
1127
            if method == 'twoFmax':
1128
1129
1130
                for key, val in max_twoF_d.iteritems():
                    f.write('{} = {:1.16e}\n'.format(key, val))

Gregory Ashton's avatar
Gregory Ashton committed
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
    def write_prior_table(self):
        with open('{}/{}_prior.tex'.format(self.outdir, self.label), 'w') as f:
            f.write(r"\begin{tabular}{c l c} \hline" + '\n'
                    r"Parameter & & &  \\ \hhline{====}")

            for key, prior in self.theta_prior.iteritems():
                if type(prior) is dict:
                    Type = prior['type']
                    if Type == "unif":
                        a = prior['lower']
                        b = prior['upper']
                        line = r"{} & $\mathrm{{Unif}}$({}, {}) & {}\\"
                    elif Type == "norm":
                        a = prior['loc']
                        b = prior['scale']
                        line = r"{} & $\mathcal{{N}}$({}, {}) & {}\\"
                    elif Type == "halfnorm":
                        a = prior['loc']
                        b = prior['scale']
                        line = r"{} & $|\mathcal{{N}}$({}, {})| & {}\\"

                    u = self.unit_dictionary[key]
                    s = self.symbol_dictionary[key]
                    f.write("\n")
                    a = helper_functions.texify_float(a)
                    b = helper_functions.texify_float(b)
                    f.write(" " + line.format(s, a, b, u) + r" \\")
            f.write("\n\end{tabular}\n")

1160
    def print_summary(self):
Gregory Ashton's avatar
Gregory Ashton committed
1161
        max_twoFd, max_twoF = self.get_max_twoF()
1162
        median_std_d = self.get_median_stds()
Gregory Ashton's avatar
Gregory Ashton committed
1163
        logging.info('Summary:')
1164
        if hasattr(self, 'theta0_idx'):
Gregory Ashton's avatar
Gregory Ashton committed
1165
1166
            logging.info('theta0 index: {}'.format(self.theta0_idx))
        logging.info('Max twoF: {} with parameters:'.format(max_twoF))
Gregory Ashton's avatar
Gregory Ashton committed
1167
1168
        for k in np.sort(max_twoFd.keys()):
            print('  {:10s} = {:1.9e}'.format(k, max_twoFd[k]))
Gregory Ashton's avatar
Gregory Ashton committed
1169
        logging.info('Median +/- std for production values')
1170
        for k in np.sort(median_std_d.keys()):
1171
            if 'std' not in k:
Gregory Ashton's avatar
Gregory Ashton committed
1172
                logging.info('  {:10s} = {:1.9e} +/- {:1.9e}'.format(
1173
                    k, median_std_d[k], median_std_d[k+'_std']))
Gregory Ashton's avatar
Gregory Ashton committed
1174
        logging.info('\n')