result.py 56.8 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
Matthew David Pitkin's avatar
Matthew David Pitkin committed
6
from functools import reduce
MoritzThomasHuebner's avatar
MoritzThomasHuebner committed
7

8 9
import numpy as np
import pandas as pd
10
import corner
Sylvia Biscoveanu's avatar
Sylvia Biscoveanu committed
11
import json
12
import scipy.stats
13
import matplotlib
14
import matplotlib.pyplot as plt
15
from matplotlib import lines as mpllines
16

17
from . import utils
Colm Talbot's avatar
Colm Talbot committed
18
from .utils import (logger, infer_parameters_from_function,
Colm Talbot's avatar
Colm Talbot committed
19 20
                    check_directory_exists_and_if_not_mkdir,
                    BilbyJsonEncoder, decode_bilby_json)
Colm Talbot's avatar
Colm Talbot committed
21
from .prior import Prior, PriorDict, DeltaFunction
22

23

24
def result_file_name(outdir, label, extension='json', gzip=False):
25 26 27 28 29 30 31 32
    """ 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
33 34
    extension: str, optional
        Whether to save as `hdf5` or `json`
35 36
    gzip: bool, optional
        Set to True to append `.gz` to the extension for saving in gzipped format
37 38 39 40 41

    Returns
    -------
    str: File name of the output file
    """
42
    if extension in ['json', 'hdf5']:
43 44 45 46
        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
47
    else:
48
        raise ValueError("Extension type {} not understood".format(extension))
49 50


51
def _determine_file_name(filename, outdir, label, extension, gzip):
52 53 54 55 56 57 58
    """ 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:
59
            return result_file_name(outdir, label, extension, gzip)
60 61


62
def read_in_result(filename=None, outdir=None, label=None, extension='json', gzip=False):
63 64 65 66 67 68 69 70 71 72 73
    """ 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.

    """
74
    filename = _determine_file_name(filename, outdir, label, extension, gzip)
75 76 77

    # Get the actual extension (may differ from the default extension if the filename is given)
    extension = os.path.splitext(filename)[1].lstrip('.')
78 79 80
    if extension == 'gz':  # gzipped file
        extension = os.path.splitext(os.path.splitext(filename)[0])[1].lstrip('.')

81 82 83 84 85 86 87 88
    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
89
    return result
90 91 92 93 94


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
95 96
                 constraint_parameter_keys=None, priors=None,
                 sampler_kwargs=None, injection_parameters=None,
97 98 99 100
                 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,
101
                 log_prior_evaluations=None, sampling_time=None, nburn=None,
102
                 walkers=None, max_autocorrelation_time=None, use_ratio=None,
103
                 parameter_labels=None, parameter_labels_with_unit=None,
104
                 gzip=False, version=None):
105
        """ A class to store the results of the sampling run
106 107 108

        Parameters
        ----------
109 110
        label, outdir, sampler: str
            The label, output directory, and sampler used
Colm Talbot's avatar
Colm Talbot committed
111 112 113 114
        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`
115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130
        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
131 132
        log_prior_evaluations: array_like
            The evaluations of the prior for each sample point
133 134 135 136 137 138 139 140
        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
141 142 143
        use_ratio: bool
            A boolean stating whether the likelihood ratio, as opposed to the
            likelihood was used during sampling
144 145
        parameter_labels, parameter_labels_with_unit: list
            Lists of the latex-formatted parameter labels
146 147
        gzip: bool
            Set to True to gzip the results file (if using json format)
148 149 150
        version: str,
            Version information for software used to generate the result. Note,
            this information is generated when the result object is initialized
151

152 153 154 155
        Note
        ---------
        All sampling output parameters, e.g. the samples themselves are
        typically not given at initialisation, but set at a later stage.
156 157

        """
158

159 160 161 162 163
        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
164
        self.constraint_parameter_keys = constraint_parameter_keys
165 166 167 168 169 170 171 172 173 174 175
        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
176
        self.use_ratio = use_ratio
177 178 179 180 181
        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
182
        self.log_prior_evaluations = log_prior_evaluations
183
        self.sampling_time = sampling_time
184
        self.version = version
Colm Talbot's avatar
Colm Talbot committed
185
        self.max_autocorrelation_time = max_autocorrelation_time
186

187 188 189
        self.prior_values = None
        self._kde = None

190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210
    @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

        """
211
        import deepdish
212
        filename = _determine_file_name(filename, outdir, label, 'hdf5', False)
213

214
        if os.path.isfile(filename):
Moritz Huebner's avatar
Moritz Huebner committed
215 216
            dictionary = deepdish.io.load(filename)
            # Some versions of deepdish/pytables return the dictionanary as
217
            # a dictionary with a key 'data'
Moritz Huebner's avatar
Moritz Huebner committed
218 219 220
            if len(dictionary) == 1 and 'data' in dictionary:
                dictionary = dictionary['data']
            try:
221 222
                if isinstance(dictionary.get('posterior', None), dict):
                    dictionary['posterior'] = pd.DataFrame(dictionary['posterior'])
Moritz Huebner's avatar
Moritz Huebner committed
223 224 225
                return cls(**dictionary)
            except TypeError as e:
                raise IOError("Unable to load dictionary, error={}".format(e))
226 227 228
        else:
            raise IOError("No result '{}' found".format(filename))

Sylvia Biscoveanu's avatar
Sylvia Biscoveanu committed
229
    @classmethod
230
    def from_json(cls, filename=None, outdir=None, label=None, gzip=False):
Sylvia Biscoveanu's avatar
Sylvia Biscoveanu committed
231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249
        """ 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

        """
250
        filename = _determine_file_name(filename, outdir, label, 'json', gzip)
251

Sylvia Biscoveanu's avatar
Sylvia Biscoveanu committed
252
        if os.path.isfile(filename):
253 254 255 256 257 258 259 260
            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
261 262 263 264 265 266 267 268 269 270 271 272 273
            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))

274
    def __str__(self):
275
        """Print a summary """
276 277
        if getattr(self, 'posterior', None) is not None:
            if getattr(self, 'log_noise_evidence', None) is not None:
278 279 280 281
                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"
282
                        .format(len(self.posterior), self.log_noise_evidence, self.log_evidence,
283 284 285 286 287
                                self.log_evidence_err, self.log_bayes_factor,
                                self.log_evidence_err))
            else:
                return ("nsamples: {:d}\n"
                        "log_evidence: {:6.3f} +/- {:6.3f}\n"
288
                        .format(len(self.posterior), self.log_evidence, self.log_evidence_err))
289 290
        else:
            return ''
291

292 293 294 295 296 297
    @property
    def priors(self):
        if self._priors is not None:
            return self._priors
        else:
            raise ValueError('Result object has no priors')
298

299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316
    @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")
317

318 319 320 321 322
    @property
    def samples(self):
        """ An array of samples """
        if self._samples is not None:
            return self._samples
323
        else:
324
            raise ValueError("Result object has no stored samples")
325

326 327 328
    @samples.setter
    def samples(self, samples):
        self._samples = samples
329

330 331 332 333 334 335 336
    @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")
337

338 339 340
    @nested_samples.setter
    def nested_samples(self, nested_samples):
        self._nested_samples = nested_samples
341

342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377
    @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

378 379 380 381 382 383 384 385 386 387 388
    @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

389
    def _get_save_data_dictionary(self):
390
        # This list defines all the parameters saved in the result object
391 392 393 394
        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
395
            'fixed_parameter_keys', 'constraint_parameter_keys',
396
            'sampling_time', 'sampler_kwargs', 'use_ratio',
397 398
            'log_likelihood_evaluations', 'log_prior_evaluations', 'samples',
            'nested_samples', 'walkers', 'nburn', 'parameter_labels',
399
            'parameter_labels_with_unit', 'version']
400 401 402 403 404 405 406 407
        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
408

409
    def save_to_file(self, overwrite=False, outdir=None, extension='json', gzip=False):
Colm Talbot's avatar
Colm Talbot committed
410
        """
Sylvia Biscoveanu's avatar
Sylvia Biscoveanu committed
411
        Writes the Result to a json or deepdish h5 file
Colm Talbot's avatar
Colm Talbot committed
412 413 414 415 416 417

        Parameters
        ----------
        overwrite: bool, optional
            Whether or not to overwrite an existing result file.
            default=False
418 419
        outdir: str, optional
            Path to the outdir. Default is the one stored in the result object.
Gregory Ashton's avatar
Gregory Ashton committed
420 421 422
        extension: str, optional {json, hdf5, True}
            Determines the method to use to store the data (if True defaults
            to json)
423 424 425
        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
426
        """
Gregory Ashton's avatar
Gregory Ashton committed
427 428 429 430

        if extension is True:
            extension = "json"

431
        outdir = self._safe_outdir_creation(outdir, self.save_to_file)
432
        file_name = result_file_name(outdir, self.label, extension, gzip)
433

434
        if os.path.isfile(file_name):
Colm Talbot's avatar
Colm Talbot committed
435 436 437 438 439 440 441 442
            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')
443

Gregory Ashton's avatar
Gregory Ashton committed
444
        logger.debug("Saving result to {}".format(file_name))
445 446

        # Convert the prior to a string representation for saving on disk
447
        dictionary = self._get_save_data_dictionary()
448 449 450
        if dictionary.get('priors', False):
            dictionary['priors'] = {key: str(self.priors[key]) for key in self.priors}

451
        # Convert callable sampler_kwargs to strings
452 453 454 455
        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'])
456

Gregory Ashton's avatar
Fix #49  
Gregory Ashton committed
457
        try:
458
            if extension == 'json':
459 460 461 462 463 464 465 466 467
                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)
468
            elif extension == 'hdf5':
469
                import deepdish
470 471 472
                for key in dictionary:
                    if isinstance(dictionary[key], pd.DataFrame):
                        dictionary[key] = dictionary[key].to_dict()
Sylvia Biscoveanu's avatar
Sylvia Biscoveanu committed
473 474
                deepdish.io.save(file_name, dictionary)
            else:
475
                raise ValueError("Extension type {} not understood".format(extension))
Gregory Ashton's avatar
Fix #49  
Gregory Ashton committed
476
        except Exception as e:
Gregory Ashton's avatar
Gregory Ashton committed
477
            logger.error("\n\n Saving the data has failed with the "
MoritzThomasHuebner's avatar
MoritzThomasHuebner committed
478
                         "following message:\n {} \n\n".format(e))
Gregory Ashton's avatar
Gregory Ashton committed
479

480
    def save_posterior_samples(self, outdir=None):
481
        """Saves posterior samples to a file"""
482 483
        outdir = self._safe_outdir_creation(outdir, self.save_posterior_samples)
        filename = '{}/{}_posterior_samples.txt'.format(outdir, self.label)
484 485
        self.posterior.to_csv(filename, index=False, header=True)

Gregory Ashton's avatar
Gregory Ashton committed
486
    def get_latex_labels_from_parameter_keys(self, keys):
487 488 489 490 491 492 493 494 495 496 497 498 499
        """ 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
500 501 502
        for k in keys:
            if k in self.search_parameter_keys:
                idx = self.search_parameter_keys.index(k)
503
                latex_labels.append(self.parameter_labels_with_unit[idx])
Gregory Ashton's avatar
Gregory Ashton committed
504
            elif k in self.parameter_labels:
505
                latex_labels.append(k)
Gregory Ashton's avatar
Gregory Ashton committed
506
            else:
Colm Talbot's avatar
Colm Talbot committed
507
                logger.debug(
508 509
                    'key {} not a parameter label or latex label'.format(k))
                latex_labels.append(' '.join(k.split('_')))
510
        return latex_labels
Gregory Ashton's avatar
Gregory Ashton committed
511

Gregory Ashton's avatar
Gregory Ashton committed
512 513 514 515 516 517 518 519 520
    @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
521 522 523
        if self.covariance_matrix.ndim == 0:
            return np.sqrt(self.covariance_matrix)
        else:
MoritzThomasHuebner's avatar
MoritzThomasHuebner committed
524 525
            return 1 / np.sqrt(np.abs(np.linalg.det(
                1 / self.covariance_matrix)))
Gregory Ashton's avatar
Gregory Ashton committed
526

527 528
    @staticmethod
    def prior_volume(priors):
Gregory Ashton's avatar
Gregory Ashton committed
529 530 531 532 533 534
        """ 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,

535 536 537
        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
538 539 540 541

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

542
    def get_one_dimensional_median_and_error_bar(self, key, fmt='.2f',
543
                                                 quantiles=(0.16, 0.84)):
544 545 546 547 548 549 550 551
        """ 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
552 553
        quantiles: list, tuple
            A length-2 tuple of the lower and upper-quantiles to calculate
554 555 556 557
            the errors bars for.

        Returns
        -------
558 559
        summary: namedtuple
            An object with attributes, median, lower, upper and string
560 561

        """
562 563
        summary = namedtuple('summary', ['median', 'lower', 'upper', 'string'])

564 565 566 567 568
        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)
569 570 571
        summary.median = quants[1]
        summary.plus = quants[2] - summary.median
        summary.minus = summary.median - quants[0]
572 573

        fmt = "{{0:{0}}}".format(fmt).format
574 575 576 577 578
        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
579 580 581
    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,
582 583
                            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
584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611

        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
612 613
        quantiles: tuple
            A length-2 tuple of the lower and upper-quantiles to calculate
Colm Talbot's avatar
Colm Talbot committed
614 615 616 617 618 619 620 621 622 623 624 625
            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()
626 627 628 629 630 631 632 633
        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
634 635 636 637 638 639 640 641 642 643 644 645 646
        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)
647
            ax.plot(theta, prior.prob(theta), color='C2')
Colm Talbot's avatar
Colm Talbot committed
648 649 650 651 652 653 654 655

        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)
656 657 658
            plt.close(fig)
        else:
            return fig
Colm Talbot's avatar
Colm Talbot committed
659

660 661
    def plot_marginals(self, parameters=None, priors=None, titles=True,
                       file_base_name=None, bins=50, label_fontsize=16,
662 663
                       title_fontsize=16, quantiles=(0.16, 0.84), dpi=300,
                       outdir=None):
664 665 666 667 668 669 670
        """ 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.
671
        priors: {bool (False), bilby.core.prior.PriorDict}
672
            If true, add the stored prior probability density functions to the
673
            one-dimensional marginal distributions. If instead a PriorDict
674 675 676 677 678 679 680 681 682 683 684 685
            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
686 687 688
            The font sizes for the labels and titles
        quantiles: tuple
            A length-2 tuple of the lower and upper-quantiles to calculate
689 690 691
            the errors bars for.
        dpi: int
            Dots per inch resolution of the plot
692 693
        outdir: str, optional
            Path to the outdir. Default is the one store in the result object.
694 695 696 697 698 699

        Returns
        -------
        """
        if isinstance(parameters, dict):
            plot_parameter_keys = list(parameters.keys())
Colm Talbot's avatar
Colm Talbot committed
700
            truths = parameters
701
        elif parameters is None:
Colm Talbot's avatar
Colm Talbot committed
702 703 704 705 706
            plot_parameter_keys = self.posterior.keys()
            if self.injection_parameters is None:
                truths = dict()
            else:
                truths = self.injection_parameters
707 708
        else:
            plot_parameter_keys = list(parameters)
Colm Talbot's avatar
Colm Talbot committed
709 710 711 712
            if self.injection_parameters is None:
                truths = dict()
            else:
                truths = self.injection_parameters
713 714

        if file_base_name is None:
715 716
            outdir = self._safe_outdir_creation(outdir, self.plot_marginals)
            file_base_name = '{}/{}_1d/'.format(outdir, self.label)
Colm Talbot's avatar
Colm Talbot committed
717
            check_directory_exists_and_if_not_mkdir(file_base_name)
718 719

        if priors is True:
Colm Talbot's avatar
Colm Talbot committed
720 721
            priors = getattr(self, 'priors', dict())
        elif isinstance(priors, dict):
722
            pass
Colm Talbot's avatar
Colm Talbot committed
723 724
        elif priors in [False, None]:
            priors = dict()
725 726 727 728
        else:
            raise ValueError('Input priors={} not understood'.format(priors))

        for i, key in enumerate(plot_parameter_keys):
Colm Talbot's avatar
Colm Talbot committed
729 730
            if not isinstance(self.posterior[key].values[0], float):
                continue
Colm Talbot's avatar
Colm Talbot committed
731 732
            prior = priors.get(key, None)
            truth = truths.get(key, None)
Colm Talbot's avatar
Colm Talbot committed
733
            for cumulative in [False, True]:
734
                self.plot_single_density(
Colm Talbot's avatar
Colm Talbot committed
735 736
                    key, prior=prior, cumulative=cumulative, title=titles,
                    truth=truth, save=True, file_base_name=file_base_name,
Colm Talbot's avatar
Colm Talbot committed
737 738
                    bins=bins, label_fontsize=label_fontsize, dpi=dpi,
                    title_fontsize=title_fontsize, quantiles=quantiles)
739

740 741 742
    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
743 744 745

        Parameters
        ----------
746 747 748
        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.
749
        priors: {bool (False), bilby.core.prior.PriorDict}
750
            If true, add the stored prior probability density functions to the
751
            one-dimensional marginal distributions. If instead a PriorDict
752
            is provided, this will be plotted.
753 754 755 756 757
        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.
758 759 760 761 762 763
        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
764 765 766
        **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
767 768
            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
769

770 771 772 773 774 775
        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
776 777 778 779
        Returns
        -------
        fig:
            A matplotlib figure instance
780

Gregory Ashton's avatar
Gregory Ashton committed
781
        """
782 783

        # If in testing mode, not corner plots are generated
784 785
        if utils.command_line_args.test:
            return
Gregory Ashton's avatar
Gregory Ashton committed
786

Colm Talbot's avatar
Colm Talbot committed
787
        # bilby default corner kwargs. Overwritten by anything passed to kwargs
788 789 790
        defaults_kwargs = dict(
            bins=50, smooth=0.9, label_kwargs=dict(fontsize=16),
            title_kwargs=dict(fontsize=16), color='#0072C1',
791
            truth_color='tab:orange', quantiles=[0.16, 0.84],
MoritzThomasHuebner's avatar
MoritzThomasHuebner committed
792
            levels=(1 - np.exp(-0.5), 1 - np.exp(-2), 1 - np.exp(-9 / 2.)),
793
            plot_density=False, plot_datapoints=True, fill_contours=True,
794 795 796 797 798 799
            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)
800

801 802 803 804
        if 'lionize' in kwargs and kwargs['lionize'] is True:
            defaults_kwargs['truth_color'] = 'tab:blue'
            defaults_kwargs['color'] = '#FF8C00'

805 806 807
        defaults_kwargs.update(kwargs)
        kwargs = defaults_kwargs

808 809 810 811 812 813 814 815 816 817 818 819 820 821 822
        # 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
823 824 825 826 827 828 829 830
        # 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}

831 832 833 834 835 836 837 838 839
        # 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)
840

841
        # Get latex formatted strings for the plot labels
842 843
        kwargs['labels'] = kwargs.get(
            'labels', self.get_latex_labels_from_parameter_keys(
844
                plot_parameter_keys))
845

846 847 848 849
        # 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))

850 851
        # Create the data array to plot and pass everything to corner
        xs = self.posterior[plot_parameter_keys].values
852
        fig = corner.corner(xs, **kwargs)
853
        axes = fig.get_axes()
854 855 856

        #  Add the titles
        if titles and kwargs.get('quantiles', None) is not None:
857 858
            for i, par in enumerate(plot_parameter_keys):
                ax = axes[i + i * len(plot_parameter_keys)]
859 860
                if ax.title.get_text() == '':
                    ax.set_title(self.get_one_dimensional_median_and_error_bar(
861
                        par, quantiles=kwargs['quantiles']).string,
862 863 864
                        **kwargs['title_kwargs'])

        #  Add priors to the 1D plots
865 866 867
        if priors is True:
            priors = getattr(self, 'priors', False)
        if isinstance(priors, dict):
868 869
            for i, par in enumerate(plot_parameter_keys):
                ax = axes[i + i * len(plot_parameter_keys)]
870 871
                theta = np.linspace(ax.get_xlim()[0], ax.get_xlim()[1], 300)
                ax.plot(theta, priors[par].prob(theta), color='C2')
872 873 874 875
        elif priors in [False, None]:
            pass
        else:
            raise ValueError('Input priors={} not understood'.format(priors))
876

877
        if save:
878
            if filename is None:
879 880
                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
881
            logger.debug('Saving corner plot to {}'.format(filename))
882
            fig.savefig(filename, dpi=dpi)
883
            plt.close(fig)
884

885
        return fig
886

Gregory Ashton's avatar
Gregory Ashton committed
887
    def plot_walkers(self, **kwargs):
MoritzThomasHuebner's avatar
A typo  
MoritzThomasHuebner committed
888
        """ Method to plot the trace of the walkers in an ensemble MCMC plot """
889
        if hasattr(self, 'walkers') is False:
Gregory Ashton's avatar
Gregory Ashton committed
890
            logger.warning("Cannot plot_walkers as no walkers are saved")
891
            return
892 893 894

        if utils.command_line_args.test:
            return
895 896 897

        nwalkers, nsteps, ndim = self.walkers.shape
        idxs = np.arange(nsteps)
MoritzThomasHuebner's avatar
MoritzThomasHuebner committed
898
        fig, axes = plt.subplots(nrows=ndim, figsize=(6, 3 * ndim))
899 900
        walkers = self.walkers[:, :, :]
        for i, ax in enumerate(axes):
MoritzThomasHuebner's avatar
MoritzThomasHuebner committed
901
            ax.plot(idxs[:self.nburn + 1], walkers[:, :self.nburn + 1, i].T,
902 903 904 905 906 907 908 909 910
                    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()
911 912
        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
913
        logger.debug('Saving walkers plot to {}'.format('filename'))
914
        fig.savefig(filename)
915
        plt.close(fig)
916

917 918 919
    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,
920
                       maxl_label='max likelihood', dpi=300, outdir=None):
921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945
        """ 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.
946 947
        outdir: str, optional
            Path to the outdir. Default is the one store in the result object.
948 949

        """
950 951 952 953 954 955

        # 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]

956 957 958 959
        xsmooth = np.linspace(np.min(x), np.max(x), npoints)
        fig, ax = plt.subplots()
        logger.info('Plotting {} draws'.format(ndraws))
        for _ in range(ndraws):
960
            s = model_posterior.sample().to_dict('records')[0]
961 962
            ax.plot(xsmooth, model(xsmooth, **s), alpha=0.25, lw=0.1, color='r',
                    label=draws_label)
963 964 965
        try:
            if all(~np.isnan(self.posterior.log_likelihood)):
                logger.info('Plotting maximum likelihood')
Colm Talbot's avatar
Colm Talbot committed
966
                s = model_posterior.iloc[self.posterior.log_likelihood.idxmax()]
967 968
                ax.plot(xsmooth, model(xsmooth, **s), lw=1, color='k',
                        label=maxl_label)
969
        except (AttributeError, TypeError):
970 971
            logger.debug(
                "No log likelihood values stored, unable to plot max")
972 973 974 975 976 977 978 979 980 981 982 983 984 985

        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:
986 987
            outdir = self._safe_outdir_creation(outdir, self.plot_with_data)
            filename = '{}/{}_plot_with_data'.format(outdir, self.label)
988
        fig.savefig(filename, dpi=dpi)
989
        plt.close(fig)
990

991 992 993 994 995 996 997 998 999 1000 1001
    @staticmethod
    def _add_prior_fixed_values_to_posterior(posterior, priors):
        if priors is None:
            return posterior
        for key in priors:
            if isinstance(priors[key], DeltaFunction):
                posterior[key] = priors[key].peak
            elif isinstance(priors[key], float):
                posterior[key] = priors[key]
        return posterior

1002 1003
    def samples_to_posterior(self, likelihood=None, priors=None,
                             conversion_function=None):
1004
        """