result.py 50 KB
Newer Older
Colm Talbot's avatar
Colm Talbot committed
1 2
from __future__ import division

3
import os
4
from distutils.version import LooseVersion
5
from collections import OrderedDict, namedtuple
MoritzThomasHuebner's avatar
MoritzThomasHuebner committed
6

7 8
import numpy as np
import pandas as pd
9
import corner
Sylvia Biscoveanu's avatar
Sylvia Biscoveanu committed
10
import json
11
import scipy.stats
12
import matplotlib
13
import matplotlib.pyplot as plt
14
from matplotlib import lines as mpllines
15

16
from . import utils
Colm Talbot's avatar
Colm Talbot committed
17
from .utils import (logger, infer_parameters_from_function,
Colm Talbot's avatar
Colm Talbot committed
18 19
                    check_directory_exists_and_if_not_mkdir,
                    BilbyJsonEncoder, decode_bilby_json)
Colm Talbot's avatar
Colm Talbot committed
20
from .prior import Prior, PriorDict, DeltaFunction
21

22

23
def result_file_name(outdir, label, extension='json', gzip=False):
24 25 26 27 28 29 30 31
    """ Returns the standard filename used for a result file

    Parameters
    ----------
    outdir: str
        Name of the output directory
    label: str
        Naming scheme of the output file
Sylvia Biscoveanu's avatar
Sylvia Biscoveanu committed
32 33
    extension: str, optional
        Whether to save as `hdf5` or `json`
34 35
    gzip: bool, optional
        Set to True to append `.gz` to the extension for saving in gzipped format
36 37 38 39 40

    Returns
    -------
    str: File name of the output file
    """
41
    if extension in ['json', 'hdf5']:
42 43 44 45
        if extension == 'json' and gzip:
            return '{}/{}_result.{}.gz'.format(outdir, label, extension)
        else:
            return '{}/{}_result.{}'.format(outdir, label, extension)
Sylvia Biscoveanu's avatar
Sylvia Biscoveanu committed
46
    else:
47
        raise ValueError("Extension type {} not understood".format(extension))
48 49


50
def _determine_file_name(filename, outdir, label, extension, gzip):
51 52 53 54 55 56 57
    """ Helper method to determine the filename """
    if filename is not None:
        return filename
    else:
        if (outdir is None) and (label is None):
            raise ValueError("No information given to load file")
        else:
58
            return result_file_name(outdir, label, extension, gzip)
59 60


61
def read_in_result(filename=None, outdir=None, label=None, extension='json', gzip=False):
62 63 64 65 66 67 68 69 70 71 72
    """ Reads in a stored bilby result object

    Parameters
    ----------
    filename: str
        Path to the file to be read (alternative to giving the outdir and label)
    outdir, label, extension: str
        Name of the output directory, label and extension used for the default
        naming scheme.

    """
73
    filename = _determine_file_name(filename, outdir, label, extension, gzip)
74 75 76

    # Get the actual extension (may differ from the default extension if the filename is given)
    extension = os.path.splitext(filename)[1].lstrip('.')
77 78 79
    if extension == 'gz':  # gzipped file
        extension = os.path.splitext(os.path.splitext(filename)[0])[1].lstrip('.')

80 81 82 83 84 85 86 87
    if 'json' in extension:
        result = Result.from_json(filename=filename)
    elif ('hdf5' in extension) or ('h5' in extension):
        result = Result.from_hdf5(filename=filename)
    elif extension is None:
        raise ValueError("No filetype extension provided")
    else:
        raise ValueError("Filetype {} not understood".format(extension))
Sylvia Biscoveanu's avatar
Sylvia Biscoveanu committed
88
    return result
89 90 91 92 93


class Result(object):
    def __init__(self, label='no_label', outdir='.', sampler=None,
                 search_parameter_keys=None, fixed_parameter_keys=None,
Colm Talbot's avatar
Colm Talbot committed
94 95
                 constraint_parameter_keys=None, priors=None,
                 sampler_kwargs=None, injection_parameters=None,
96 97 98 99
                 meta_data=None, posterior=None, samples=None,
                 nested_samples=None, log_evidence=np.nan,
                 log_evidence_err=np.nan, log_noise_evidence=np.nan,
                 log_bayes_factor=np.nan, log_likelihood_evaluations=None,
100 101 102
                 log_prior_evaluations=None, sampling_time=None, nburn=None,
                 walkers=None, max_autocorrelation_time=None,
                 parameter_labels=None, parameter_labels_with_unit=None,
103
                 gzip=False, version=None):
104
        """ A class to store the results of the sampling run
105 106 107

        Parameters
        ----------
108 109
        label, outdir, sampler: str
            The label, output directory, and sampler used
Colm Talbot's avatar
Colm Talbot committed
110 111 112 113
        search_parameter_keys, fixed_parameter_keys, constraint_parameter_keys: list
            Lists of the search, constraint, and fixed parameter keys.
            Elements of the list should be of type `str` and match the keys
            of the `prior`
114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129
        priors: dict, bilby.core.prior.PriorDict
            A dictionary of the priors used in the run
        sampler_kwargs: dict
            Key word arguments passed to the sampler
        injection_parameters: dict
            A dictionary of the injection parameters
        meta_data: dict
            A dictionary of meta data to store about the run
        posterior: pandas.DataFrame
            A pandas data frame of the posterior
        samples, nested_samples: array_like
            An array of the output posterior samples and the unweighted samples
        log_evidence, log_evidence_err, log_noise_evidence, log_bayes_factor: float
            Natural log evidences
        log_likelihood_evaluations: array_like
            The evaluations of the likelihood for each sample point
130 131
        log_prior_evaluations: array_like
            The evaluations of the prior for each sample point
132 133 134 135 136 137 138 139 140 141
        sampling_time: float
            The time taken to complete the sampling
        nburn: int
            The number of burn-in steps discarded for MCMC samplers
        walkers: array_like
            The samplers taken by a ensemble MCMC samplers
        max_autocorrelation_time: float
            The estimated maximum autocorrelation time for MCMC samplers
        parameter_labels, parameter_labels_with_unit: list
            Lists of the latex-formatted parameter labels
142 143
        gzip: bool
            Set to True to gzip the results file (if using json format)
144 145 146
        version: str,
            Version information for software used to generate the result. Note,
            this information is generated when the result object is initialized
147

148 149 150 151
        Note
        ---------
        All sampling output parameters, e.g. the samples themselves are
        typically not given at initialisation, but set at a later stage.
152 153

        """
154

155 156 157 158 159
        self.label = label
        self.outdir = os.path.abspath(outdir)
        self.sampler = sampler
        self.search_parameter_keys = search_parameter_keys
        self.fixed_parameter_keys = fixed_parameter_keys
Colm Talbot's avatar
Colm Talbot committed
160
        self.constraint_parameter_keys = constraint_parameter_keys
161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176
        self.parameter_labels = parameter_labels
        self.parameter_labels_with_unit = parameter_labels_with_unit
        self.priors = priors
        self.sampler_kwargs = sampler_kwargs
        self.meta_data = meta_data
        self.injection_parameters = injection_parameters
        self.posterior = posterior
        self.samples = samples
        self.nested_samples = nested_samples
        self.walkers = walkers
        self.nburn = nburn
        self.log_evidence = log_evidence
        self.log_evidence_err = log_evidence_err
        self.log_noise_evidence = log_noise_evidence
        self.log_bayes_factor = log_bayes_factor
        self.log_likelihood_evaluations = log_likelihood_evaluations
177
        self.log_prior_evaluations = log_prior_evaluations
178
        self.sampling_time = sampling_time
179
        self.version = version
Colm Talbot's avatar
Colm Talbot committed
180
        self.max_autocorrelation_time = max_autocorrelation_time
181

182 183 184
        self.prior_values = None
        self._kde = None

185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205
    @classmethod
    def from_hdf5(cls, filename=None, outdir=None, label=None):
        """ Read in a saved .h5 data file

        Parameters
        ----------
        filename: str
            If given, try to load from this filename
        outdir, label: str
            If given, use the default naming convention for saved results file

        Returns
        -------
        result: bilby.core.result.Result

        Raises
        -------
        ValueError: If no filename is given and either outdir or label is None
                    If no bilby.core.result.Result is found in the path

        """
206
        import deepdish
207
        filename = _determine_file_name(filename, outdir, label, 'hdf5', False)
208

209
        if os.path.isfile(filename):
Moritz Huebner's avatar
Moritz Huebner committed
210 211
            dictionary = deepdish.io.load(filename)
            # Some versions of deepdish/pytables return the dictionanary as
212
            # a dictionary with a key 'data'
Moritz Huebner's avatar
Moritz Huebner committed
213 214 215
            if len(dictionary) == 1 and 'data' in dictionary:
                dictionary = dictionary['data']
            try:
216 217
                if isinstance(dictionary.get('posterior', None), dict):
                    dictionary['posterior'] = pd.DataFrame(dictionary['posterior'])
Moritz Huebner's avatar
Moritz Huebner committed
218 219 220
                return cls(**dictionary)
            except TypeError as e:
                raise IOError("Unable to load dictionary, error={}".format(e))
221 222 223
        else:
            raise IOError("No result '{}' found".format(filename))

Sylvia Biscoveanu's avatar
Sylvia Biscoveanu committed
224
    @classmethod
225
    def from_json(cls, filename=None, outdir=None, label=None, gzip=False):
Sylvia Biscoveanu's avatar
Sylvia Biscoveanu committed
226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244
        """ Read in a saved .json data file

        Parameters
        ----------
        filename: str
            If given, try to load from this filename
        outdir, label: str
            If given, use the default naming convention for saved results file

        Returns
        -------
        result: bilby.core.result.Result

        Raises
        -------
        ValueError: If no filename is given and either outdir or label is None
                    If no bilby.core.result.Result is found in the path

        """
245
        filename = _determine_file_name(filename, outdir, label, 'json', gzip)
246

Sylvia Biscoveanu's avatar
Sylvia Biscoveanu committed
247
        if os.path.isfile(filename):
248 249 250 251 252 253 254 255
            if gzip or os.path.splitext(filename)[1].lstrip('.') == 'gz':
                import gzip
                with gzip.GzipFile(filename, 'r') as file:
                    json_str = file.read().decode('utf-8')
                dictionary = json.loads(json_str, object_hook=decode_bilby_json)
            else:
                with open(filename, 'r') as file:
                    dictionary = json.load(file, object_hook=decode_bilby_json)
Sylvia Biscoveanu's avatar
Sylvia Biscoveanu committed
256 257 258 259 260 261 262 263 264 265 266 267 268
            for key in dictionary.keys():
                # Convert the loaded priors to bilby prior type
                if key == 'priors':
                    for param in dictionary[key].keys():
                        dictionary[key][param] = str(dictionary[key][param])
                    dictionary[key] = PriorDict(dictionary[key])
            try:
                return cls(**dictionary)
            except TypeError as e:
                raise IOError("Unable to load dictionary, error={}".format(e))
        else:
            raise IOError("No result '{}' found".format(filename))

269
    def __str__(self):
270
        """Print a summary """
271 272
        if getattr(self, 'posterior', None) is not None:
            if getattr(self, 'log_noise_evidence', None) is not None:
273 274 275 276
                return ("nsamples: {:d}\n"
                        "log_noise_evidence: {:6.3f}\n"
                        "log_evidence: {:6.3f} +/- {:6.3f}\n"
                        "log_bayes_factor: {:6.3f} +/- {:6.3f}\n"
277
                        .format(len(self.posterior), self.log_noise_evidence, self.log_evidence,
278 279 280 281 282
                                self.log_evidence_err, self.log_bayes_factor,
                                self.log_evidence_err))
            else:
                return ("nsamples: {:d}\n"
                        "log_evidence: {:6.3f} +/- {:6.3f}\n"
283
                        .format(len(self.posterior), self.log_evidence, self.log_evidence_err))
284 285
        else:
            return ''
286

287 288 289 290 291 292
    @property
    def priors(self):
        if self._priors is not None:
            return self._priors
        else:
            raise ValueError('Result object has no priors')
293

294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311
    @priors.setter
    def priors(self, priors):
        if isinstance(priors, dict):
            self._priors = PriorDict(priors)
            if self.parameter_labels is None:
                self.parameter_labels = [self.priors[k].latex_label for k in
                                         self.search_parameter_keys]
            if self.parameter_labels_with_unit is None:
                self.parameter_labels_with_unit = [
                    self.priors[k].latex_label_with_unit for k in
                    self.search_parameter_keys]

        elif priors is None:
            self._priors = priors
            self.parameter_labels = self.search_parameter_keys
            self.parameter_labels_with_unit = self.search_parameter_keys
        else:
            raise ValueError("Input priors not understood")
312

313 314 315 316 317
    @property
    def samples(self):
        """ An array of samples """
        if self._samples is not None:
            return self._samples
318
        else:
319
            raise ValueError("Result object has no stored samples")
320

321 322 323
    @samples.setter
    def samples(self, samples):
        self._samples = samples
324

325 326 327 328 329 330 331
    @property
    def nested_samples(self):
        """" An array of unweighted samples """
        if self._nested_samples is not None:
            return self._nested_samples
        else:
            raise ValueError("Result object has no stored nested samples")
332

333 334 335
    @nested_samples.setter
    def nested_samples(self, nested_samples):
        self._nested_samples = nested_samples
336

337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372
    @property
    def walkers(self):
        """" An array of the ensemble walkers """
        if self._walkers is not None:
            return self._walkers
        else:
            raise ValueError("Result object has no stored walkers")

    @walkers.setter
    def walkers(self, walkers):
        self._walkers = walkers

    @property
    def nburn(self):
        """" An array of the ensemble walkers """
        if self._nburn is not None:
            return self._nburn
        else:
            raise ValueError("Result object has no stored nburn")

    @nburn.setter
    def nburn(self, nburn):
        self._nburn = nburn

    @property
    def posterior(self):
        """ A pandas data frame of the posterior """
        if self._posterior is not None:
            return self._posterior
        else:
            raise ValueError("Result object has no stored posterior")

    @posterior.setter
    def posterior(self, posterior):
        self._posterior = posterior

373 374 375 376 377 378 379 380 381 382 383
    @property
    def version(self):
        return self._version

    @version.setter
    def version(self, version):
        if version is None:
            self._version = 'bilby={}'.format(utils.get_version_information())
        else:
            self._version = version

384
    def _get_save_data_dictionary(self):
385
        # This list defines all the parameters saved in the result object
386 387 388 389
        save_attrs = [
            'label', 'outdir', 'sampler', 'log_evidence', 'log_evidence_err',
            'log_noise_evidence', 'log_bayes_factor', 'priors', 'posterior',
            'injection_parameters', 'meta_data', 'search_parameter_keys',
Colm Talbot's avatar
Colm Talbot committed
390 391
            'fixed_parameter_keys', 'constraint_parameter_keys',
            'sampling_time', 'sampler_kwargs',
392 393
            'log_likelihood_evaluations', 'log_prior_evaluations', 'samples',
            'nested_samples', 'walkers', 'nburn', 'parameter_labels',
394
            'parameter_labels_with_unit', 'version']
395 396 397 398 399 400 401 402
        dictionary = OrderedDict()
        for attr in save_attrs:
            try:
                dictionary[attr] = getattr(self, attr)
            except ValueError as e:
                logger.debug("Unable to save {}, message: {}".format(attr, e))
                pass
        return dictionary
403

404
    def save_to_file(self, overwrite=False, outdir=None, extension='json', gzip=False):
Colm Talbot's avatar
Colm Talbot committed
405
        """
Sylvia Biscoveanu's avatar
Sylvia Biscoveanu committed
406
        Writes the Result to a json or deepdish h5 file
Colm Talbot's avatar
Colm Talbot committed
407 408 409 410 411 412

        Parameters
        ----------
        overwrite: bool, optional
            Whether or not to overwrite an existing result file.
            default=False
413 414
        outdir: str, optional
            Path to the outdir. Default is the one stored in the result object.
Gregory Ashton's avatar
Gregory Ashton committed
415 416 417
        extension: str, optional {json, hdf5, True}
            Determines the method to use to store the data (if True defaults
            to json)
418 419 420
        gzip: bool, optional
            If true, and outputing to a json file, this will gzip the resulting
            file and add '.gz' to the file extension.
Colm Talbot's avatar
Colm Talbot committed
421
        """
Gregory Ashton's avatar
Gregory Ashton committed
422 423 424 425

        if extension is True:
            extension = "json"

426
        outdir = self._safe_outdir_creation(outdir, self.save_to_file)
427
        file_name = result_file_name(outdir, self.label, extension, gzip)
428

429
        if os.path.isfile(file_name):
Colm Talbot's avatar
Colm Talbot committed
430 431 432 433 434 435 436 437
            if overwrite:
                logger.debug('Removing existing file {}'.format(file_name))
                os.remove(file_name)
            else:
                logger.debug(
                    'Renaming existing file {} to {}.old'.format(file_name,
                                                                 file_name))
                os.rename(file_name, file_name + '.old')
438

Gregory Ashton's avatar
Gregory Ashton committed
439
        logger.debug("Saving result to {}".format(file_name))
440 441

        # Convert the prior to a string representation for saving on disk
442
        dictionary = self._get_save_data_dictionary()
443 444 445
        if dictionary.get('priors', False):
            dictionary['priors'] = {key: str(self.priors[key]) for key in self.priors}

446
        # Convert callable sampler_kwargs to strings
447 448 449 450
        if dictionary.get('sampler_kwargs', None) is not None:
            for key in dictionary['sampler_kwargs']:
                if hasattr(dictionary['sampler_kwargs'][key], '__call__'):
                    dictionary['sampler_kwargs'][key] = str(dictionary['sampler_kwargs'])
451

Gregory Ashton's avatar
Fix #49  
Gregory Ashton committed
452
        try:
453
            if extension == 'json':
454 455 456 457 458 459 460 461 462
                if gzip:
                    import gzip
                    # encode to a string
                    json_str = json.dumps(dictionary, cls=BilbyJsonEncoder).encode('utf-8')
                    with gzip.GzipFile(file_name, 'w') as file:
                        file.write(json_str)
                else:
                    with open(file_name, 'w') as file:
                        json.dump(dictionary, file, indent=2, cls=BilbyJsonEncoder)
463
            elif extension == 'hdf5':
464
                import deepdish
465 466 467
                for key in dictionary:
                    if isinstance(dictionary[key], pd.DataFrame):
                        dictionary[key] = dictionary[key].to_dict()
Sylvia Biscoveanu's avatar
Sylvia Biscoveanu committed
468 469
                deepdish.io.save(file_name, dictionary)
            else:
470
                raise ValueError("Extension type {} not understood".format(extension))
Gregory Ashton's avatar
Fix #49  
Gregory Ashton committed
471
        except Exception as e:
Gregory Ashton's avatar
Gregory Ashton committed
472
            logger.error("\n\n Saving the data has failed with the "
MoritzThomasHuebner's avatar
MoritzThomasHuebner committed
473
                         "following message:\n {} \n\n".format(e))
Gregory Ashton's avatar
Gregory Ashton committed
474

475
    def save_posterior_samples(self, outdir=None):
476
        """Saves posterior samples to a file"""
477 478
        outdir = self._safe_outdir_creation(outdir, self.save_posterior_samples)
        filename = '{}/{}_posterior_samples.txt'.format(outdir, self.label)
479 480
        self.posterior.to_csv(filename, index=False, header=True)

Gregory Ashton's avatar
Gregory Ashton committed
481
    def get_latex_labels_from_parameter_keys(self, keys):
482 483 484 485 486 487 488 489 490 491 492 493 494
        """ Returns a list of latex_labels corresponding to the given keys

        Parameters
        ----------
        keys: list
            List of strings corresponding to the desired latex_labels

        Returns
        -------
        list: The desired latex_labels

        """
        latex_labels = []
Gregory Ashton's avatar
Gregory Ashton committed
495 496 497
        for k in keys:
            if k in self.search_parameter_keys:
                idx = self.search_parameter_keys.index(k)
498
                latex_labels.append(self.parameter_labels_with_unit[idx])
Gregory Ashton's avatar
Gregory Ashton committed
499
            elif k in self.parameter_labels:
500
                latex_labels.append(k)
Gregory Ashton's avatar
Gregory Ashton committed
501
            else:
Colm Talbot's avatar
Colm Talbot committed
502
                logger.debug(
503 504
                    'key {} not a parameter label or latex label'.format(k))
                latex_labels.append(' '.join(k.split('_')))
505
        return latex_labels
Gregory Ashton's avatar
Gregory Ashton committed
506

Gregory Ashton's avatar
Gregory Ashton committed
507 508 509 510 511 512 513 514 515
    @property
    def covariance_matrix(self):
        """ The covariance matrix of the samples the posterior """
        samples = self.posterior[self.search_parameter_keys].values
        return np.cov(samples.T)

    @property
    def posterior_volume(self):
        """ The posterior volume """
Gregory Ashton's avatar
Gregory Ashton committed
516 517 518
        if self.covariance_matrix.ndim == 0:
            return np.sqrt(self.covariance_matrix)
        else:
MoritzThomasHuebner's avatar
MoritzThomasHuebner committed
519 520
            return 1 / np.sqrt(np.abs(np.linalg.det(
                1 / self.covariance_matrix)))
Gregory Ashton's avatar
Gregory Ashton committed
521

522 523
    @staticmethod
    def prior_volume(priors):
Gregory Ashton's avatar
Gregory Ashton committed
524 525 526 527 528 529
        """ The prior volume, given a set of priors """
        return np.prod([priors[k].maximum - priors[k].minimum for k in priors])

    def occam_factor(self, priors):
        """ The Occam factor,

530 531 532
        See Chapter 28, `Mackay "Information Theory, Inference, and Learning
        Algorithms" <http://www.inference.org.uk/itprnn/book.html>`_ Cambridge
        University Press (2003).
Gregory Ashton's avatar
Gregory Ashton committed
533 534 535 536

        """
        return self.posterior_volume / self.prior_volume(priors)

537
    def get_one_dimensional_median_and_error_bar(self, key, fmt='.2f',
538
                                                 quantiles=(0.16, 0.84)):
539 540 541 542 543 544 545 546
        """ Calculate the median and error bar for a given key

        Parameters
        ----------
        key: str
            The parameter key for which to calculate the median and error bar
        fmt: str, ('.2f')
            A format string
547 548
        quantiles: list, tuple
            A length-2 tuple of the lower and upper-quantiles to calculate
549 550 551 552
            the errors bars for.

        Returns
        -------
553 554
        summary: namedtuple
            An object with attributes, median, lower, upper and string
555 556

        """
557 558
        summary = namedtuple('summary', ['median', 'lower', 'upper', 'string'])

559 560 561 562 563
        if len(quantiles) != 2:
            raise ValueError("quantiles must be of length 2")

        quants_to_compute = np.array([quantiles[0], 0.5, quantiles[1]])
        quants = np.percentile(self.posterior[key], quants_to_compute * 100)
564 565 566
        summary.median = quants[1]
        summary.plus = quants[2] - summary.median
        summary.minus = summary.median - quants[0]
567 568

        fmt = "{{0:{0}}}".format(fmt).format
569 570 571 572 573
        string_template = r"${{{0}}}_{{-{1}}}^{{+{2}}}$"
        summary.string = string_template.format(
            fmt(summary.median), fmt(summary.minus), fmt(summary.plus))
        return summary

Colm Talbot's avatar
Colm Talbot committed
574 575 576
    def plot_single_density(self, key, prior=None, cumulative=False,
                            title=None, truth=None, save=True,
                            file_base_name=None, bins=50, label_fontsize=16,
577 578
                            title_fontsize=16, quantiles=(0.16, 0.84), dpi=300):
        """ Plot a 1D marginal density, either probability or cumulative.
Colm Talbot's avatar
Colm Talbot committed
579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606

        Parameters
        ----------
        key: str
            Name of the parameter to plot
        prior: {bool (True), bilby.core.prior.Prior}
            If true, add the stored prior probability density function to the
            one-dimensional marginal distributions. If instead a Prior
            is provided, this will be plotted.
        cumulative: bool
            If true plot the CDF
        title: bool
            If true, add 1D title of the median and (by default 1-sigma)
            error bars. To change the error bars, pass in the quantiles kwarg.
            See method `get_one_dimensional_median_and_error_bar` for further
            details). If `quantiles=None` is passed in, no title is added.
        truth: {bool, float}
            If true, plot self.injection_parameters[parameter].
            If float, plot this value.
        save: bool:
            If true, save plot to disk.
        file_base_name: str, optional
            If given, the base file name to use (by default `outdir/label_` is
            used)
        bins: int
            The number of histogram bins
        label_fontsize, title_fontsize: int
            The fontsizes for the labels and titles
607 608
        quantiles: tuple
            A length-2 tuple of the lower and upper-quantiles to calculate
Colm Talbot's avatar
Colm Talbot committed
609 610 611 612 613 614 615 616 617 618 619 620
            the errors bars for.
        dpi: int
            Dots per inch resolution of the plot

        Returns
        -------
        figure: matplotlib.pyplot.figure
            A matplotlib figure object
        """
        logger.info('Plotting {} marginal distribution'.format(key))
        label = self.get_latex_labels_from_parameter_keys([key])[0]
        fig, ax = plt.subplots()
621 622 623 624 625 626 627 628
        try:
            ax.hist(self.posterior[key].values, bins=bins, density=True,
                    histtype='step', cumulative=cumulative)
        except ValueError as e:
            logger.info(
                'Failed to generate 1d plot for {}, error message: {}'
                .format(key, e))
            return
Colm Talbot's avatar
Colm Talbot committed
629 630 631 632 633 634 635 636 637 638 639 640 641
        ax.set_xlabel(label, fontsize=label_fontsize)
        if truth is not None:
            ax.axvline(truth, ls='-', color='orange')

        summary = self.get_one_dimensional_median_and_error_bar(
            key, quantiles=quantiles)
        ax.axvline(summary.median - summary.minus, ls='--', color='C0')
        ax.axvline(summary.median + summary.plus, ls='--', color='C0')
        if title:
            ax.set_title(summary.string, fontsize=title_fontsize)

        if isinstance(prior, Prior):
            theta = np.linspace(ax.get_xlim()[0], ax.get_xlim()[1], 300)
642
            ax.plot(theta, prior.prob(theta), color='C2')
Colm Talbot's avatar
Colm Talbot committed
643 644 645 646 647 648 649 650

        if save:
            fig.tight_layout()
            if cumulative:
                file_name = file_base_name + key + '_cdf'
            else:
                file_name = file_base_name + key + '_pdf'
            fig.savefig(file_name, dpi=dpi)
651 652 653
            plt.close(fig)
        else:
            return fig
Colm Talbot's avatar
Colm Talbot committed
654

655 656
    def plot_marginals(self, parameters=None, priors=None, titles=True,
                       file_base_name=None, bins=50, label_fontsize=16,
657 658
                       title_fontsize=16, quantiles=(0.16, 0.84), dpi=300,
                       outdir=None):
659 660 661 662 663 664 665
        """ Plot 1D marginal distributions

        Parameters
        ----------
        parameters: (list, dict), optional
            If given, either a list of the parameter names to include, or a
            dictionary of parameter names and their "true" values to plot.
666
        priors: {bool (False), bilby.core.prior.PriorDict}
667
            If true, add the stored prior probability density functions to the
668
            one-dimensional marginal distributions. If instead a PriorDict
669 670 671 672 673 674 675 676 677 678 679 680
            is provided, this will be plotted.
        titles: bool
            If true, add 1D titles of the median and (by default 1-sigma)
            error bars. To change the error bars, pass in the quantiles kwarg.
            See method `get_one_dimensional_median_and_error_bar` for further
            details). If `quantiles=None` is passed in, no title is added.
        file_base_name: str, optional
            If given, the base file name to use (by default `outdir/label_` is
            used)
        bins: int
            The number of histogram bins
        label_fontsize, title_fontsize: int
681 682 683
            The font sizes for the labels and titles
        quantiles: tuple
            A length-2 tuple of the lower and upper-quantiles to calculate
684 685 686
            the errors bars for.
        dpi: int
            Dots per inch resolution of the plot
687 688
        outdir: str, optional
            Path to the outdir. Default is the one store in the result object.
689 690 691 692 693 694

        Returns
        -------
        """
        if isinstance(parameters, dict):
            plot_parameter_keys = list(parameters.keys())
Colm Talbot's avatar
Colm Talbot committed
695
            truths = parameters
696
        elif parameters is None:
Colm Talbot's avatar
Colm Talbot committed
697 698 699 700 701
            plot_parameter_keys = self.posterior.keys()
            if self.injection_parameters is None:
                truths = dict()
            else:
                truths = self.injection_parameters
702 703
        else:
            plot_parameter_keys = list(parameters)
Colm Talbot's avatar
Colm Talbot committed
704 705 706 707
            if self.injection_parameters is None:
                truths = dict()
            else:
                truths = self.injection_parameters
708 709

        if file_base_name is None:
710 711
            outdir = self._safe_outdir_creation(outdir, self.plot_marginals)
            file_base_name = '{}/{}_1d/'.format(outdir, self.label)
Colm Talbot's avatar
Colm Talbot committed
712
            check_directory_exists_and_if_not_mkdir(file_base_name)
713 714

        if priors is True:
Colm Talbot's avatar
Colm Talbot committed
715 716
            priors = getattr(self, 'priors', dict())
        elif isinstance(priors, dict):
717
            pass
Colm Talbot's avatar
Colm Talbot committed
718 719
        elif priors in [False, None]:
            priors = dict()
720 721 722 723
        else:
            raise ValueError('Input priors={} not understood'.format(priors))

        for i, key in enumerate(plot_parameter_keys):
Colm Talbot's avatar
Colm Talbot committed
724 725
            if not isinstance(self.posterior[key].values[0], float):
                continue
Colm Talbot's avatar
Colm Talbot committed
726 727
            prior = priors.get(key, None)
            truth = truths.get(key, None)
Colm Talbot's avatar
Colm Talbot committed
728
            for cumulative in [False, True]:
729
                self.plot_single_density(
Colm Talbot's avatar
Colm Talbot committed
730 731
                    key, prior=prior, cumulative=cumulative, title=titles,
                    truth=truth, save=True, file_base_name=file_base_name,
Colm Talbot's avatar
Colm Talbot committed
732 733
                    bins=bins, label_fontsize=label_fontsize, dpi=dpi,
                    title_fontsize=title_fontsize, quantiles=quantiles)
734

735 736 737
    def plot_corner(self, parameters=None, priors=None, titles=True, save=True,
                    filename=None, dpi=300, **kwargs):
        """ Plot a corner-plot
Gregory Ashton's avatar
Gregory Ashton committed
738 739 740

        Parameters
        ----------
741 742 743
        parameters: (list, dict), optional
            If given, either a list of the parameter names to include, or a
            dictionary of parameter names and their "true" values to plot.
744
        priors: {bool (False), bilby.core.prior.PriorDict}
745
            If true, add the stored prior probability density functions to the
746
            one-dimensional marginal distributions. If instead a PriorDict
747
            is provided, this will be plotted.
748 749 750 751 752
        titles: bool
            If true, add 1D titles of the median and (by default 1-sigma)
            error bars. To change the error bars, pass in the quantiles kwarg.
            See method `get_one_dimensional_median_and_error_bar` for further
            details). If `quantiles=None` is passed in, no title is added.
753 754 755 756 757 758
        save: bool, optional
            If true, save the image using the given label and outdir
        filename: str, optional
            If given, overwrite the default filename
        dpi: int, optional
            Dots per inch resolution of the plot
759 760 761
        **kwargs:
            Other keyword arguments are passed to `corner.corner`. We set some
            defaults to improve the basic look and feel, but these can all be
762 763
            overridden. Also optional an 'outdir' argument which can be used
            to override the outdir set by the absolute path of the result object.
Gregory Ashton's avatar
Gregory Ashton committed
764

765 766 767 768 769 770
        Notes
        -----
            The generation of the corner plot themselves is done by the corner
            python module, see https://corner.readthedocs.io for more
            information.

Gregory Ashton's avatar
Gregory Ashton committed
771 772 773 774
        Returns
        -------
        fig:
            A matplotlib figure instance
775

Gregory Ashton's avatar
Gregory Ashton committed
776
        """
777 778

        # If in testing mode, not corner plots are generated
779 780
        if utils.command_line_args.test:
            return
Gregory Ashton's avatar
Gregory Ashton committed
781

Colm Talbot's avatar
Colm Talbot committed
782
        # bilby default corner kwargs. Overwritten by anything passed to kwargs
783 784 785
        defaults_kwargs = dict(
            bins=50, smooth=0.9, label_kwargs=dict(fontsize=16),
            title_kwargs=dict(fontsize=16), color='#0072C1',
786
            truth_color='tab:orange', quantiles=[0.16, 0.84],
MoritzThomasHuebner's avatar
MoritzThomasHuebner committed
787
            levels=(1 - np.exp(-0.5), 1 - np.exp(-2), 1 - np.exp(-9 / 2.)),
788
            plot_density=False, plot_datapoints=True, fill_contours=True,
789 790 791 792 793 794
            max_n_ticks=3)

        if LooseVersion(matplotlib.__version__) < "2.1":
            defaults_kwargs['hist_kwargs'] = dict(normed=True)
        else:
            defaults_kwargs['hist_kwargs'] = dict(density=True)
795

796 797 798 799
        if 'lionize' in kwargs and kwargs['lionize'] is True:
            defaults_kwargs['truth_color'] = 'tab:blue'
            defaults_kwargs['color'] = '#FF8C00'

800 801 802
        defaults_kwargs.update(kwargs)
        kwargs = defaults_kwargs

803 804 805 806 807 808 809 810 811 812 813 814 815 816 817
        # Handle if truths was passed in
        if 'truth' in kwargs:
            kwargs['truths'] = kwargs.pop('truth')
        if kwargs.get('truths'):
            truths = kwargs.get('truths')
            if isinstance(parameters, list) and isinstance(truths, list):
                if len(parameters) != len(truths):
                    raise ValueError(
                        "Length of parameters and truths don't match")
            elif isinstance(truths, dict) and parameters is None:
                parameters = kwargs.pop('truths')
            else:
                raise ValueError(
                    "Combination of parameters and truths not understood")

Gregory Ashton's avatar
Gregory Ashton committed
818 819 820 821 822 823 824 825
        # If injection parameters where stored, use these as parameter values
        # but do not overwrite input parameters (or truths)
        cond1 = getattr(self, 'injection_parameters', None) is not None
        cond2 = parameters is None
        if cond1 and cond2:
            parameters = {key: self.injection_parameters[key] for key in
                          self.search_parameter_keys}

826 827 828 829 830 831 832 833 834
        # If parameters is a dictionary, use the keys to determine which
        # parameters to plot and the values as truths.
        if isinstance(parameters, dict):
            plot_parameter_keys = list(parameters.keys())
            kwargs['truths'] = list(parameters.values())
        elif parameters is None:
            plot_parameter_keys = self.search_parameter_keys
        else:
            plot_parameter_keys = list(parameters)
835

836
        # Get latex formatted strings for the plot labels
837 838
        kwargs['labels'] = kwargs.get(
            'labels', self.get_latex_labels_from_parameter_keys(
839
                plot_parameter_keys))
840

841 842 843 844
        # Unless already set, set the range to include all samples
        # This prevents ValueErrors being raised for parameters with no range
        kwargs['range'] = kwargs.get('range', [1] * len(plot_parameter_keys))

845 846
        # Create the data array to plot and pass everything to corner
        xs = self.posterior[plot_parameter_keys].values
847
        fig = corner.corner(xs, **kwargs)
848
        axes = fig.get_axes()
849 850 851

        #  Add the titles
        if titles and kwargs.get('quantiles', None) is not None:
852 853
            for i, par in enumerate(plot_parameter_keys):
                ax = axes[i + i * len(plot_parameter_keys)]
854 855
                if ax.title.get_text() == '':
                    ax.set_title(self.get_one_dimensional_median_and_error_bar(
856
                        par, quantiles=kwargs['quantiles']).string,
857 858 859
                        **kwargs['title_kwargs'])

        #  Add priors to the 1D plots
860 861 862
        if priors is True:
            priors = getattr(self, 'priors', False)
        if isinstance(priors, dict):
863 864
            for i, par in enumerate(plot_parameter_keys):
                ax = axes[i + i * len(plot_parameter_keys)]
865 866
                theta = np.linspace(ax.get_xlim()[0], ax.get_xlim()[1], 300)
                ax.plot(theta, priors[par].prob(theta), color='C2')
867 868 869 870
        elif priors in [False, None]:
            pass
        else:
            raise ValueError('Input priors={} not understood'.format(priors))
871

872
        if save:
873
            if filename is None:
874 875
                outdir = self._safe_outdir_creation(kwargs.get('outdir'), self.plot_corner)
                filename = '{}/{}_corner.png'.format(outdir, self.label)
Gregory Ashton's avatar
Gregory Ashton committed
876
            logger.debug('Saving corner plot to {}'.format(filename))
877
            fig.savefig(filename, dpi=dpi)
878
            plt.close(fig)
879

880
        return fig
881

Gregory Ashton's avatar
Gregory Ashton committed
882
    def plot_walkers(self, **kwargs):
MoritzThomasHuebner's avatar
A typo  
MoritzThomasHuebner committed
883
        """ Method to plot the trace of the walkers in an ensemble MCMC plot """
884
        if hasattr(self, 'walkers') is False:
Gregory Ashton's avatar
Gregory Ashton committed
885
            logger.warning("Cannot plot_walkers as no walkers are saved")
886
            return
887 888 889

        if utils.command_line_args.test:
            return
890 891 892

        nwalkers, nsteps, ndim = self.walkers.shape
        idxs = np.arange(nsteps)
MoritzThomasHuebner's avatar
MoritzThomasHuebner committed
893
        fig, axes = plt.subplots(nrows=ndim, figsize=(6, 3 * ndim))
894 895
        walkers = self.walkers[:, :, :]
        for i, ax in enumerate(axes):
MoritzThomasHuebner's avatar
MoritzThomasHuebner committed
896
            ax.plot(idxs[:self.nburn + 1], walkers[:, :self.nburn + 1, i].T,
897 898 899 900 901 902 903 904 905
                    lw=0.1, color='r')
            ax.set_ylabel(self.parameter_labels[i])

        for i, ax in enumerate(axes):
            ax.plot(idxs[self.nburn:], walkers[:, self.nburn:, i].T, lw=0.1,
                    color='k')
            ax.set_ylabel(self.parameter_labels[i])

        fig.tight_layout()
906 907
        outdir = self._safe_outdir_creation(kwargs.get('outdir'), self.plot_walkers)
        filename = '{}/{}_walkers.png'.format(outdir, self.label)
Gregory Ashton's avatar
Gregory Ashton committed
908
        logger.debug('Saving walkers plot to {}'.format('filename'))
909
        fig.savefig(filename)
910
        plt.close(fig)
911

912 913 914
    def plot_with_data(self, model, x, y, ndraws=1000, npoints=1000,
                       xlabel=None, ylabel=None, data_label='data',
                       data_fmt='o', draws_label=None, filename=None,
915
                       maxl_label='max likelihood', dpi=300, outdir=None):
916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940
        """ Generate a figure showing the data and fits to the data

        Parameters
        ----------
        model: function
            A python function which when called as `model(x, **kwargs)` returns
            the model prediction (here `kwargs` is a dictionary of key-value
            pairs of the model parameters.
        x, y: np.ndarray
            The independent and dependent data to plot
        ndraws: int
            Number of draws from the posterior to plot
        npoints: int
            Number of points used to plot the smoothed fit to the data
        xlabel, ylabel: str
            Labels for the axes
        data_label, draws_label, maxl_label: str
            Label for the data, draws, and max likelihood legend
        data_fmt: str
            Matpltolib fmt code, defaults to `'-o'`
        dpi: int
            Passed to `plt.savefig`
        filename: str
            If given, the filename to use. Otherwise, the filename is generated
            from the outdir and label attributes.
941 942
        outdir: str, optional
            Path to the outdir. Default is the one store in the result object.
943 944

        """
945 946 947 948 949 950

        # Determine model_posterior, the subset of the full posterior which
        # should be passed into the model
        model_keys = infer_parameters_from_function(model)
        model_posterior = self.posterior[model_keys]

951 952 953 954
        xsmooth = np.linspace(np.min(x), np.max(x), npoints)
        fig, ax = plt.subplots()
        logger.info('Plotting {} draws'.format(ndraws))
        for _ in range(ndraws):
955
            s = model_posterior.sample().to_dict('records')[0]
956 957
            ax.plot(xsmooth, model(xsmooth, **s), alpha=0.25, lw=0.1, color='r',
                    label=draws_label)
958 959 960
        try:
            if all(~np.isnan(self.posterior.log_likelihood)):
                logger.info('Plotting maximum likelihood')
Colm Talbot's avatar
Colm Talbot committed
961
                s = model_posterior.iloc[self.posterior.log_likelihood.idxmax()]
962 963
                ax.plot(xsmooth, model(xsmooth, **s), lw=1, color='k',
                        label=maxl_label)
964
        except (AttributeError, TypeError):
965 966
            logger.debug(
                "No log likelihood values stored, unable to plot max")
967 968 969 970 971 972 973 974 975 976 977 978 979 980

        ax.plot(x, y, data_fmt, markersize=2, label=data_label)

        if xlabel is not None:
            ax.set_xlabel(xlabel)
        if ylabel is not None:
            ax.set_ylabel(ylabel)

        handles, labels = plt.gca().get_legend_handles_labels()
        by_label = OrderedDict(zip(labels, handles))
        plt.legend(by_label.values(), by_label.keys())
        ax.legend(numpoints=3)
        fig.tight_layout()
        if filename is None:
981 982
            outdir = self._safe_outdir_creation(outdir, self.plot_with_data)
            filename = '{}/{}_plot_with_data'.format(outdir, self.label)
983
        fig.savefig(filename, dpi=dpi)
984
        plt.close(fig)
985

986 987
    def samples_to_posterior(self, likelihood=None, priors=None,
                             conversion_function=None):
988
        """
989 990 991
        Convert array of samples to posterior (a Pandas data frame)

        Also applies the conversion function to any stored posterior
992

993 994
        Parameters
        ----------
Colm Talbot's avatar
Colm Talbot committed
995
        likelihood: bilby.likelihood.GravitationalWaveTransient, optional
996 997
            GravitationalWaveTransient likelihood used for sampling.
        priors: dict, optional
998
            Dictionary of prior object, used to fill in delta function priors.
999
        conversion_function: function, optional
1000 1001
            Function which adds in extra parameters to the data frame,
            should take the data_frame, likelihood and prior as arguments.
1002
        """
1003 1004 1005
        try:
            data_frame = self.posterior
        except ValueError: