result.py 59 KB
Newer Older
Colm Talbot's avatar
Colm Talbot committed
1 2
from __future__ import division

3
import os
4
from collections import OrderedDict, namedtuple
5
from copy import copy
6
from distutils.version import LooseVersion
Gregory Ashton's avatar
Gregory Ashton committed
7
from itertools import product
MoritzThomasHuebner's avatar
MoritzThomasHuebner committed
8

9
import corner
Sylvia Biscoveanu's avatar
Sylvia Biscoveanu committed
10
import json
11
import matplotlib
12
import matplotlib.pyplot as plt
13
from matplotlib import lines as mpllines
Moritz's avatar
Moritz committed
14 15 16
import numpy as np
import pandas as pd
import scipy.stats
Moritz's avatar
Moritz committed
17
from scipy.special import logsumexp
18

19
from . import utils
Colm Talbot's avatar
Colm Talbot committed
20
from .utils import (logger, infer_parameters_from_function,
Colm Talbot's avatar
Colm Talbot committed
21 22
                    check_directory_exists_and_if_not_mkdir,
                    BilbyJsonEncoder, decode_bilby_json)
Colm Talbot's avatar
Colm Talbot committed
23
from .prior import Prior, PriorDict, DeltaFunction
24

25

26
def result_file_name(outdir, label, extension='json', gzip=False):
27 28 29 30 31 32 33 34
    """ 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
35 36
    extension: str, optional
        Whether to save as `hdf5` or `json`
37 38
    gzip: bool, optional
        Set to True to append `.gz` to the extension for saving in gzipped format
39 40 41 42 43

    Returns
    -------
    str: File name of the output file
    """
44
    if extension in ['json', 'hdf5']:
45 46 47 48
        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
49
    else:
50
        raise ValueError("Extension type {} not understood".format(extension))
51 52


53
def _determine_file_name(filename, outdir, label, extension, gzip):
54 55 56 57 58 59 60
    """ 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:
61
            return result_file_name(outdir, label, extension, gzip)
62 63


64
def read_in_result(filename=None, outdir=None, label=None, extension='json', gzip=False):
65 66 67 68 69 70 71 72 73 74 75
    """ 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.

    """
76
    filename = _determine_file_name(filename, outdir, label, extension, gzip)
77 78 79

    # Get the actual extension (may differ from the default extension if the filename is given)
    extension = os.path.splitext(filename)[1].lstrip('.')
80 81 82
    if extension == 'gz':  # gzipped file
        extension = os.path.splitext(os.path.splitext(filename)[0])[1].lstrip('.')

83 84 85 86 87 88 89 90
    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
91
    return result
92 93 94 95 96


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
97 98
                 constraint_parameter_keys=None, priors=None,
                 sampler_kwargs=None, injection_parameters=None,
99 100 101 102
                 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,
103
                 log_prior_evaluations=None, sampling_time=None, nburn=None,
104
                 walkers=None, max_autocorrelation_time=None, use_ratio=None,
105
                 parameter_labels=None, parameter_labels_with_unit=None,
106
                 gzip=False, version=None):
107
        """ A class to store the results of the sampling run
108 109 110

        Parameters
        ----------
111 112
        label, outdir, sampler: str
            The label, output directory, and sampler used
Colm Talbot's avatar
Colm Talbot committed
113 114 115 116
        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`
117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132
        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
133 134
        log_prior_evaluations: array_like
            The evaluations of the prior for each sample point
135 136 137 138 139 140 141 142
        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
143 144 145
        use_ratio: bool
            A boolean stating whether the likelihood ratio, as opposed to the
            likelihood was used during sampling
146 147
        parameter_labels, parameter_labels_with_unit: list
            Lists of the latex-formatted parameter labels
148 149
        gzip: bool
            Set to True to gzip the results file (if using json format)
150 151 152
        version: str,
            Version information for software used to generate the result. Note,
            this information is generated when the result object is initialized
153

154 155 156 157
        Note
        ---------
        All sampling output parameters, e.g. the samples themselves are
        typically not given at initialisation, but set at a later stage.
158 159

        """
160

161 162 163 164 165
        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
166
        self.constraint_parameter_keys = constraint_parameter_keys
167 168 169 170 171 172 173 174 175 176 177
        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
178
        self.use_ratio = use_ratio
179 180 181 182 183
        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
184
        self.log_prior_evaluations = log_prior_evaluations
185
        self.sampling_time = sampling_time
186
        self.version = version
Colm Talbot's avatar
Colm Talbot committed
187
        self.max_autocorrelation_time = max_autocorrelation_time
188

189 190 191
        self.prior_values = None
        self._kde = None

192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212
    @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

        """
213
        import deepdish
214
        filename = _determine_file_name(filename, outdir, label, 'hdf5', False)
215

216
        if os.path.isfile(filename):
Moritz Huebner's avatar
Moritz Huebner committed
217 218
            dictionary = deepdish.io.load(filename)
            # Some versions of deepdish/pytables return the dictionanary as
219
            # a dictionary with a key 'data'
Moritz Huebner's avatar
Moritz Huebner committed
220 221 222
            if len(dictionary) == 1 and 'data' in dictionary:
                dictionary = dictionary['data']
            try:
223 224
                if isinstance(dictionary.get('posterior', None), dict):
                    dictionary['posterior'] = pd.DataFrame(dictionary['posterior'])
Moritz Huebner's avatar
Moritz Huebner committed
225 226 227
                return cls(**dictionary)
            except TypeError as e:
                raise IOError("Unable to load dictionary, error={}".format(e))
228 229 230
        else:
            raise IOError("No result '{}' found".format(filename))

Sylvia Biscoveanu's avatar
Sylvia Biscoveanu committed
231
    @classmethod
232
    def from_json(cls, filename=None, outdir=None, label=None, gzip=False):
Sylvia Biscoveanu's avatar
Sylvia Biscoveanu committed
233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251
        """ 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

        """
252
        filename = _determine_file_name(filename, outdir, label, 'json', gzip)
253

Sylvia Biscoveanu's avatar
Sylvia Biscoveanu committed
254
        if os.path.isfile(filename):
255 256 257 258 259 260 261 262
            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
263 264 265 266 267 268 269 270 271 272 273 274 275
            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))

276
    def __str__(self):
277
        """Print a summary """
278 279
        if getattr(self, 'posterior', None) is not None:
            if getattr(self, 'log_noise_evidence', None) is not None:
280 281 282 283
                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"
284
                        .format(len(self.posterior), self.log_noise_evidence, self.log_evidence,
285 286 287 288 289
                                self.log_evidence_err, self.log_bayes_factor,
                                self.log_evidence_err))
            else:
                return ("nsamples: {:d}\n"
                        "log_evidence: {:6.3f} +/- {:6.3f}\n"
290
                        .format(len(self.posterior), self.log_evidence, self.log_evidence_err))
291 292
        else:
            return ''
293

294 295 296 297 298 299
    @property
    def priors(self):
        if self._priors is not None:
            return self._priors
        else:
            raise ValueError('Result object has no priors')
300

301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318
    @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")
319

320 321 322 323 324
    @property
    def samples(self):
        """ An array of samples """
        if self._samples is not None:
            return self._samples
325
        else:
326
            raise ValueError("Result object has no stored samples")
327

328 329 330
    @samples.setter
    def samples(self, samples):
        self._samples = samples
331

332 333 334 335 336 337 338
    @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")
339

340 341 342
    @nested_samples.setter
    def nested_samples(self, nested_samples):
        self._nested_samples = nested_samples
343

344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379
    @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

380 381 382 383 384 385 386 387 388 389 390
    @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

391
    def _get_save_data_dictionary(self):
392
        # This list defines all the parameters saved in the result object
393 394 395 396
        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
397
            'fixed_parameter_keys', 'constraint_parameter_keys',
398
            'sampling_time', 'sampler_kwargs', 'use_ratio',
399 400
            'log_likelihood_evaluations', 'log_prior_evaluations', 'samples',
            'nested_samples', 'walkers', 'nburn', 'parameter_labels',
401
            'parameter_labels_with_unit', 'version']
402 403 404 405 406 407 408 409
        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
410

411
    def save_to_file(self, overwrite=False, outdir=None, extension='json', gzip=False):
Colm Talbot's avatar
Colm Talbot committed
412
        """
Sylvia Biscoveanu's avatar
Sylvia Biscoveanu committed
413
        Writes the Result to a json or deepdish h5 file
Colm Talbot's avatar
Colm Talbot committed
414 415 416 417 418 419

        Parameters
        ----------
        overwrite: bool, optional
            Whether or not to overwrite an existing result file.
            default=False
420 421
        outdir: str, optional
            Path to the outdir. Default is the one stored in the result object.
Gregory Ashton's avatar
Gregory Ashton committed
422 423 424
        extension: str, optional {json, hdf5, True}
            Determines the method to use to store the data (if True defaults
            to json)
425 426 427
        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
428
        """
Gregory Ashton's avatar
Gregory Ashton committed
429 430 431 432

        if extension is True:
            extension = "json"

433
        outdir = self._safe_outdir_creation(outdir, self.save_to_file)
434
        file_name = result_file_name(outdir, self.label, extension, gzip)
435

436
        if os.path.isfile(file_name):
Colm Talbot's avatar
Colm Talbot committed
437 438 439 440 441 442 443 444
            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')
445

Gregory Ashton's avatar
Gregory Ashton committed
446
        logger.debug("Saving result to {}".format(file_name))
447 448

        # Convert the prior to a string representation for saving on disk
449
        dictionary = self._get_save_data_dictionary()
450 451 452
        if dictionary.get('priors', False):
            dictionary['priors'] = {key: str(self.priors[key]) for key in self.priors}

453
        # Convert callable sampler_kwargs to strings
454 455 456 457
        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'])
458

Gregory Ashton's avatar
Fix #49  
Gregory Ashton committed
459
        try:
460
            if extension == 'json':
461 462 463 464 465 466 467 468 469
                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)
470
            elif extension == 'hdf5':
471
                import deepdish
472 473 474
                for key in dictionary:
                    if isinstance(dictionary[key], pd.DataFrame):
                        dictionary[key] = dictionary[key].to_dict()
Sylvia Biscoveanu's avatar
Sylvia Biscoveanu committed
475 476
                deepdish.io.save(file_name, dictionary)
            else:
477
                raise ValueError("Extension type {} not understood".format(extension))
Gregory Ashton's avatar
Fix #49  
Gregory Ashton committed
478
        except Exception as e:
Gregory Ashton's avatar
Gregory Ashton committed
479
            logger.error("\n\n Saving the data has failed with the "
MoritzThomasHuebner's avatar
MoritzThomasHuebner committed
480
                         "following message:\n {} \n\n".format(e))
Gregory Ashton's avatar
Gregory Ashton committed
481

482
    def save_posterior_samples(self, outdir=None):
483
        """Saves posterior samples to a file"""
484 485
        outdir = self._safe_outdir_creation(outdir, self.save_posterior_samples)
        filename = '{}/{}_posterior_samples.txt'.format(outdir, self.label)
486 487
        self.posterior.to_csv(filename, index=False, header=True)

Gregory Ashton's avatar
Gregory Ashton committed
488
    def get_latex_labels_from_parameter_keys(self, keys):
489 490 491 492 493 494 495 496 497 498 499 500 501
        """ 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
502 503 504
        for k in keys:
            if k in self.search_parameter_keys:
                idx = self.search_parameter_keys.index(k)
505
                latex_labels.append(self.parameter_labels_with_unit[idx])
Gregory Ashton's avatar
Gregory Ashton committed
506
            elif k in self.parameter_labels:
507
                latex_labels.append(k)
Gregory Ashton's avatar
Gregory Ashton committed
508
            else:
Colm Talbot's avatar
Colm Talbot committed
509
                logger.debug(
510 511
                    'key {} not a parameter label or latex label'.format(k))
                latex_labels.append(' '.join(k.split('_')))
512
        return latex_labels
Gregory Ashton's avatar
Gregory Ashton committed
513

Gregory Ashton's avatar
Gregory Ashton committed
514 515 516 517 518 519 520 521 522
    @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
523 524 525
        if self.covariance_matrix.ndim == 0:
            return np.sqrt(self.covariance_matrix)
        else:
MoritzThomasHuebner's avatar
MoritzThomasHuebner committed
526 527
            return 1 / np.sqrt(np.abs(np.linalg.det(
                1 / self.covariance_matrix)))
Gregory Ashton's avatar
Gregory Ashton committed
528

529 530
    @staticmethod
    def prior_volume(priors):
Gregory Ashton's avatar
Gregory Ashton committed
531 532 533 534 535 536
        """ 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,

537 538 539
        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
540 541 542 543

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

Moritz Huebner's avatar
Moritz Huebner committed
544 545 546 547 548 549 550 551 552 553 554 555 556
    @property
    def bayesian_model_dimensionality(self):
        """ Characterises how many parameters are effectively constraint by the data

        See <https://arxiv.org/abs/1903.06682>

        Returns
        -------
        float: The model dimensionality
        """
        return 2 * (np.mean(self.posterior['log_likelihood']**2) -
                    np.mean(self.posterior['log_likelihood'])**2)

557
    def get_one_dimensional_median_and_error_bar(self, key, fmt='.2f',
558
                                                 quantiles=(0.16, 0.84)):
559 560 561 562 563 564 565 566
        """ 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
567 568
        quantiles: list, tuple
            A length-2 tuple of the lower and upper-quantiles to calculate
569 570 571 572
            the errors bars for.

        Returns
        -------
573 574
        summary: namedtuple
            An object with attributes, median, lower, upper and string
575 576

        """
577 578
        summary = namedtuple('summary', ['median', 'lower', 'upper', 'string'])

579 580 581 582 583
        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)
584 585 586
        summary.median = quants[1]
        summary.plus = quants[2] - summary.median
        summary.minus = summary.median - quants[0]
587 588

        fmt = "{{0:{0}}}".format(fmt).format
589 590 591 592 593
        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
594 595 596
    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,
597 598
                            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
599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626

        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
627 628
        quantiles: tuple
            A length-2 tuple of the lower and upper-quantiles to calculate
Colm Talbot's avatar
Colm Talbot committed
629 630 631 632 633 634 635 636 637 638 639 640
            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()
641 642 643 644 645 646 647 648
        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
649 650 651 652 653 654 655 656 657 658 659 660 661
        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)
662
            ax.plot(theta, prior.prob(theta), color='C2')
Colm Talbot's avatar
Colm Talbot committed
663 664 665 666 667 668 669 670

        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)
671 672 673
            plt.close(fig)
        else:
            return fig
Colm Talbot's avatar
Colm Talbot committed
674

675 676
    def plot_marginals(self, parameters=None, priors=None, titles=True,
                       file_base_name=None, bins=50, label_fontsize=16,
677 678
                       title_fontsize=16, quantiles=(0.16, 0.84), dpi=300,
                       outdir=None):
679 680 681 682 683 684 685
        """ 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.
686
        priors: {bool (False), bilby.core.prior.PriorDict}
687
            If true, add the stored prior probability density functions to the
688
            one-dimensional marginal distributions. If instead a PriorDict
689 690 691 692 693 694 695 696 697 698 699 700
            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
701 702 703
            The font sizes for the labels and titles
        quantiles: tuple
            A length-2 tuple of the lower and upper-quantiles to calculate
704 705 706
            the errors bars for.
        dpi: int
            Dots per inch resolution of the plot
707 708
        outdir: str, optional
            Path to the outdir. Default is the one store in the result object.
709 710 711 712 713 714

        Returns
        -------
        """
        if isinstance(parameters, dict):
            plot_parameter_keys = list(parameters.keys())
Colm Talbot's avatar
Colm Talbot committed
715
            truths = parameters
716
        elif parameters is None:
Colm Talbot's avatar
Colm Talbot committed
717 718 719 720 721
            plot_parameter_keys = self.posterior.keys()
            if self.injection_parameters is None:
                truths = dict()
            else:
                truths = self.injection_parameters
722 723
        else:
            plot_parameter_keys = list(parameters)
Colm Talbot's avatar
Colm Talbot committed
724 725 726 727
            if self.injection_parameters is None:
                truths = dict()
            else:
                truths = self.injection_parameters
728 729

        if file_base_name is None:
730 731
            outdir = self._safe_outdir_creation(outdir, self.plot_marginals)
            file_base_name = '{}/{}_1d/'.format(outdir, self.label)
Colm Talbot's avatar
Colm Talbot committed
732
            check_directory_exists_and_if_not_mkdir(file_base_name)
733 734

        if priors is True:
Colm Talbot's avatar
Colm Talbot committed
735 736
            priors = getattr(self, 'priors', dict())
        elif isinstance(priors, dict):
737
            pass
Colm Talbot's avatar
Colm Talbot committed
738 739
        elif priors in [False, None]:
            priors = dict()
740 741 742 743
        else:
            raise ValueError('Input priors={} not understood'.format(priors))

        for i, key in enumerate(plot_parameter_keys):
Colm Talbot's avatar
Colm Talbot committed
744 745
            if not isinstance(self.posterior[key].values[0], float):
                continue
Colm Talbot's avatar
Colm Talbot committed
746 747
            prior = priors.get(key, None)
            truth = truths.get(key, None)
Colm Talbot's avatar
Colm Talbot committed
748
            for cumulative in [False, True]:
749
                self.plot_single_density(
Colm Talbot's avatar
Colm Talbot committed
750 751
                    key, prior=prior, cumulative=cumulative, title=titles,
                    truth=truth, save=True, file_base_name=file_base_name,
Colm Talbot's avatar
Colm Talbot committed
752 753
                    bins=bins, label_fontsize=label_fontsize, dpi=dpi,
                    title_fontsize=title_fontsize, quantiles=quantiles)
754

755 756 757
    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
758 759 760

        Parameters
        ----------
761 762 763
        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.
764
        priors: {bool (False), bilby.core.prior.PriorDict}
765
            If true, add the stored prior probability density functions to the
766
            one-dimensional marginal distributions. If instead a PriorDict
767
            is provided, this will be plotted.
768 769 770 771 772
        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.
773 774 775 776 777 778
        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
779 780 781
        **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
782 783
            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
784

785 786 787 788 789 790
        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
791 792 793 794
        Returns
        -------
        fig:
            A matplotlib figure instance
795

Gregory Ashton's avatar
Gregory Ashton committed
796
        """
797 798

        # If in testing mode, not corner plots are generated
799 800
        if utils.command_line_args.test:
            return
Gregory Ashton's avatar
Gregory Ashton committed
801

Colm Talbot's avatar
Colm Talbot committed
802
        # bilby default corner kwargs. Overwritten by anything passed to kwargs
803 804 805
        defaults_kwargs = dict(
            bins=50, smooth=0.9, label_kwargs=dict(fontsize=16),
            title_kwargs=dict(fontsize=16), color='#0072C1',
806
            truth_color='tab:orange', quantiles=[0.16, 0.84],
MoritzThomasHuebner's avatar
MoritzThomasHuebner committed
807
            levels=(1 - np.exp(-0.5), 1 - np.exp(-2), 1 - np.exp(-9 / 2.)),
808
            plot_density=False, plot_datapoints=True, fill_contours=True,
809 810 811 812 813 814
            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)
815

816 817 818 819
        if 'lionize' in kwargs and kwargs['lionize'] is True:
            defaults_kwargs['truth_color'] = 'tab:blue'
            defaults_kwargs['color'] = '#FF8C00'

820 821 822
        defaults_kwargs.update(kwargs)
        kwargs = defaults_kwargs

823 824 825 826 827 828 829 830 831 832 833 834 835 836 837
        # 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
838 839 840 841 842 843 844 845
        # 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}

846 847 848 849 850 851 852 853 854
        # 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)
855

856
        # Get latex formatted strings for the plot labels
857 858
        kwargs['labels'] = kwargs.get(
            'labels', self.get_latex_labels_from_parameter_keys(
859
                plot_parameter_keys))
860

861 862 863 864
        # 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))

865 866
        # Create the data array to plot and pass everything to corner
        xs = self.posterior[plot_parameter_keys].values
867
        fig = corner.corner(xs, **kwargs)
868
        axes = fig.get_axes()
869 870 871

        #  Add the titles
        if titles and kwargs.get('quantiles', None) is not None:
872 873
            for i, par in enumerate(plot_parameter_keys):
                ax = axes[i + i * len(plot_parameter_keys)]
874 875
                if ax.title.get_text() == '':
                    ax.set_title(self.get_one_dimensional_median_and_error_bar(
876
                        par, quantiles=kwargs['quantiles']).string,
877 878 879
                        **kwargs['title_kwargs'])

        #  Add priors to the 1D plots
880 881 882
        if priors is True:
            priors = getattr(self, 'priors', False)
        if isinstance(priors, dict):
883 884
            for i, par in enumerate(plot_parameter_keys):
                ax = axes[i + i * len(plot_parameter_keys)]
885 886
                theta = np.linspace(ax.get_xlim()[0], ax.get_xlim()[1], 300)
                ax.plot(theta, priors[par].prob(theta), color='C2')
887 888 889 890
        elif priors in [False, None]:
            pass
        else:
            raise ValueError('Input priors={} not understood'.format(priors))
891

892
        if save:
893
            if filename is None:
894 895
                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
896
            logger.debug('Saving corner plot to {}'.format(filename))
897
            fig.savefig(filename, dpi=dpi)
898
            plt.close(fig)
899

900
        return fig
901

Gregory Ashton's avatar
Gregory Ashton committed
902
    def plot_walkers(self, **kwargs):
MoritzThomasHuebner's avatar
A typo  
MoritzThomasHuebner committed
903
        """ Method to plot the trace of the walkers in an ensemble MCMC plot """
904
        if hasattr(self, 'walkers') is False:
Gregory Ashton's avatar
Gregory Ashton committed
905
            logger.warning("Cannot plot_walkers as no walkers are saved")
906
            return
907 908 909

        if utils.command_line_args.test:
            return
910 911 912

        nwalkers, nsteps, ndim = self.walkers.shape
        idxs = np.arange(nsteps)
MoritzThomasHuebner's avatar
MoritzThomasHuebner committed
913
        fig, axes = plt.subplots(nrows=ndim, figsize=(6, 3 * ndim))
914 915
        walkers = self.walkers[:, :, :]
        for i, ax in enumerate(axes):
MoritzThomasHuebner's avatar
MoritzThomasHuebner committed
916
            ax.plot(idxs[:self.nburn + 1], walkers[:, :self.nburn + 1, i].T,
917 918 919 920 921 922 923 924 925
                    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()
926 927
        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
928
        logger.debug('Saving walkers plot to {}'.format('filename'))
929
        fig.savefig(filename)
930
        plt.close(fig)
931

932 933 934
    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,
935
                       maxl_label='max likelihood', dpi=300, outdir=None):
936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960
        """ 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.
961 962
        outdir: str, optional
            Path to the outdir. Default is the one store in the result object.
963 964

        """
965 966 967 968 969 970

        # 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]

971 972 973 974
        xsmooth = np.linspace(np.min(x), np.max(x), npoints)
        fig, ax = plt.subplots()
        logger.info('Plotting {} draws'.format(ndraws))
        for _ in range(ndraws):
975
            s = model_posterior.sample().to_dict('records')[0]
976 977
            ax.plot(xsmooth, model(xsmooth, **s), alpha=0.25, lw=0.1, color='r',
                    label=draws_label)
978 979 980
        try:
            if all(~np.isnan(self.posterior.log_likelihood)):
                logger.info('Plotting maximum likelihood')
Colm Talbot's avatar
Colm Talbot committed
981
                s = model_posterior.iloc[self.posterior.log_likelihood.idxmax()]
982 983
                ax.plot(xsmooth, model(xsmooth, **s), lw=1, color='k',
                        label=maxl_label)
984
        except (AttributeError, TypeError):
985 986
            logger.debug(
                "No log likelihood values stored, unable to plot max")
987 988 989 990 991 992 993 994 995 996 997 998 999 1000

        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:
1001 1002
            outdir = self._safe_outdir_creation(outdir, self.plot_with_data)
            filename = '{}/{}_plot_with_data'.format(outdir, self.label)
1003
        fig.savefig(filename, dpi=dpi)
1004
        plt.close(fig)
1005

1006 1007 1008 1009 1010 1011