result.py 48.1 KB
Newer Older
Colm Talbot's avatar
Colm Talbot committed
1 2
from __future__ import division

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

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

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

22

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

    Parameters
    ----------
    outdir: str
        Name of the output directory
    label: str
        Naming scheme of the output file
Sylvia Biscoveanu's avatar
Sylvia Biscoveanu committed
32 33
    extension: str, optional
        Whether to save as `hdf5` or `json`
34 35 36 37 38

    Returns
    -------
    str: File name of the output file
    """
39 40
    if extension in ['json', 'hdf5']:
        return '{}/{}_result.{}'.format(outdir, label, extension)
Sylvia Biscoveanu's avatar
Sylvia Biscoveanu committed
41
    else:
42
        raise ValueError("Extension type {} not understood".format(extension))
43 44


45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79
def _determine_file_name(filename, outdir, label, extension):
    """ 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:
            return result_file_name(outdir, label, extension)


def read_in_result(filename=None, outdir=None, label=None, extension='json'):
    """ 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.

    """
    filename = _determine_file_name(filename, outdir, label, extension)

    # Get the actual extension (may differ from the default extension if the filename is given)
    extension = os.path.splitext(filename)[1].lstrip('.')
    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
80
    return result
81 82 83 84 85 86 87 88 89 90


class Result(object):
    def __init__(self, label='no_label', outdir='.', sampler=None,
                 search_parameter_keys=None, fixed_parameter_keys=None,
                 priors=None, sampler_kwargs=None, injection_parameters=None,
                 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,
91 92 93 94
                 log_prior_evaluations=None, sampling_time=None, nburn=None,
                 walkers=None, max_autocorrelation_time=None,
                 parameter_labels=None, parameter_labels_with_unit=None,
                 version=None):
95
        """ A class to store the results of the sampling run
96 97 98

        Parameters
        ----------
99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119
        label, outdir, sampler: str
            The label, output directory, and sampler used
        search_parameter_keys, fixed_parameter_keys: list
            Lists of the search and fixed parameter keys. Elemenents of the
            list should be of type `str` and matchs the keys of the `prior`
        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
120 121
        log_prior_evaluations: array_like
            The evaluations of the prior for each sample point
122 123 124 125 126 127 128 129 130 131
        sampling_time: float
            The time taken to complete the sampling
        nburn: int
            The number of burn-in steps discarded for MCMC samplers
        walkers: array_like
            The samplers taken by a ensemble MCMC samplers
        max_autocorrelation_time: float
            The estimated maximum autocorrelation time for MCMC samplers
        parameter_labels, parameter_labels_with_unit: list
            Lists of the latex-formatted parameter labels
132 133 134
        version: str,
            Version information for software used to generate the result. Note,
            this information is generated when the result object is initialized
135

136 137 138 139
        Note
        ---------
        All sampling output parameters, e.g. the samples themselves are
        typically not given at initialisation, but set at a later stage.
140 141

        """
142

143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163
        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
        self.parameter_labels = parameter_labels
        self.parameter_labels_with_unit = parameter_labels_with_unit
        self.priors = priors
        self.sampler_kwargs = sampler_kwargs
        self.meta_data = meta_data
        self.injection_parameters = injection_parameters
        self.posterior = posterior
        self.samples = samples
        self.nested_samples = nested_samples
        self.walkers = walkers
        self.nburn = nburn
        self.log_evidence = log_evidence
        self.log_evidence_err = log_evidence_err
        self.log_noise_evidence = log_noise_evidence
        self.log_bayes_factor = log_bayes_factor
        self.log_likelihood_evaluations = log_likelihood_evaluations
164
        self.log_prior_evaluations = log_prior_evaluations
165
        self.sampling_time = sampling_time
166
        self.version = version
Colm Talbot's avatar
Colm Talbot committed
167
        self.max_autocorrelation_time = max_autocorrelation_time
168

169 170 171
        self.prior_values = None
        self._kde = None

172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192
    @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

        """
193
        import deepdish
194 195
        filename = _determine_file_name(filename, outdir, label, 'hdf5')

196
        if os.path.isfile(filename):
Moritz Huebner's avatar
Moritz Huebner committed
197 198
            dictionary = deepdish.io.load(filename)
            # Some versions of deepdish/pytables return the dictionanary as
199
            # a dictionary with a key 'data'
Moritz Huebner's avatar
Moritz Huebner committed
200 201 202
            if len(dictionary) == 1 and 'data' in dictionary:
                dictionary = dictionary['data']
            try:
203 204
                if isinstance(dictionary.get('posterior', None), dict):
                    dictionary['posterior'] = pd.DataFrame(dictionary['posterior'])
Moritz Huebner's avatar
Moritz Huebner committed
205 206 207
                return cls(**dictionary)
            except TypeError as e:
                raise IOError("Unable to load dictionary, error={}".format(e))
208 209 210
        else:
            raise IOError("No result '{}' found".format(filename))

Sylvia Biscoveanu's avatar
Sylvia Biscoveanu committed
211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231
    @classmethod
    def from_json(cls, filename=None, outdir=None, label=None):
        """ 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

        """
232 233
        filename = _determine_file_name(filename, outdir, label, 'json')

Sylvia Biscoveanu's avatar
Sylvia Biscoveanu committed
234
        if os.path.isfile(filename):
235
            with open(filename, 'r') as file:
Colm Talbot's avatar
Colm Talbot committed
236
                dictionary = json.load(file, object_hook=decode_bilby_json)
Sylvia Biscoveanu's avatar
Sylvia Biscoveanu committed
237 238 239 240 241 242 243 244 245 246 247 248 249
            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))

250
    def __str__(self):
251
        """Print a summary """
252 253
        if getattr(self, 'posterior', None) is not None:
            if getattr(self, 'log_noise_evidence', None) is not None:
254 255 256 257
                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"
258
                        .format(len(self.posterior), self.log_noise_evidence, self.log_evidence,
259 260 261 262 263
                                self.log_evidence_err, self.log_bayes_factor,
                                self.log_evidence_err))
            else:
                return ("nsamples: {:d}\n"
                        "log_evidence: {:6.3f} +/- {:6.3f}\n"
264
                        .format(len(self.posterior), self.log_evidence, self.log_evidence_err))
265 266
        else:
            return ''
267

268 269 270 271 272 273
    @property
    def priors(self):
        if self._priors is not None:
            return self._priors
        else:
            raise ValueError('Result object has no priors')
274

275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292
    @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")
293

294 295 296 297 298
    @property
    def samples(self):
        """ An array of samples """
        if self._samples is not None:
            return self._samples
299
        else:
300
            raise ValueError("Result object has no stored samples")
301

302 303 304
    @samples.setter
    def samples(self, samples):
        self._samples = samples
305

306 307 308 309 310 311 312
    @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")
313

314 315 316
    @nested_samples.setter
    def nested_samples(self, nested_samples):
        self._nested_samples = nested_samples
317

318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353
    @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

354 355 356 357 358 359 360 361 362 363 364
    @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

365
    def _get_save_data_dictionary(self):
366
        # This list defines all the parameters saved in the result object
367 368 369 370 371
        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',
            'fixed_parameter_keys', 'sampling_time', 'sampler_kwargs',
372 373
            'log_likelihood_evaluations', 'log_prior_evaluations', 'samples',
            'nested_samples', 'walkers', 'nburn', 'parameter_labels',
374
            'parameter_labels_with_unit', 'version']
375 376 377 378 379 380 381 382
        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
383

Sylvia Biscoveanu's avatar
Sylvia Biscoveanu committed
384
    def save_to_file(self, overwrite=False, outdir=None, extension='json'):
Colm Talbot's avatar
Colm Talbot committed
385
        """
Sylvia Biscoveanu's avatar
Sylvia Biscoveanu committed
386
        Writes the Result to a json or deepdish h5 file
Colm Talbot's avatar
Colm Talbot committed
387 388 389 390 391 392

        Parameters
        ----------
        overwrite: bool, optional
            Whether or not to overwrite an existing result file.
            default=False
393 394
        outdir: str, optional
            Path to the outdir. Default is the one stored in the result object.
395 396
        extension: str, optional {json, hdf5}
            Determines the method to use to store the data
Colm Talbot's avatar
Colm Talbot committed
397
        """
398
        outdir = self._safe_outdir_creation(outdir, self.save_to_file)
Sylvia Biscoveanu's avatar
Sylvia Biscoveanu committed
399
        file_name = result_file_name(outdir, self.label, extension)
400

401
        if os.path.isfile(file_name):
Colm Talbot's avatar
Colm Talbot committed
402 403 404 405 406 407 408 409
            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')
410

Gregory Ashton's avatar
Gregory Ashton committed
411
        logger.debug("Saving result to {}".format(file_name))
412 413

        # Convert the prior to a string representation for saving on disk
414
        dictionary = self._get_save_data_dictionary()
415 416 417
        if dictionary.get('priors', False):
            dictionary['priors'] = {key: str(self.priors[key]) for key in self.priors}

418
        # Convert callable sampler_kwargs to strings
419 420 421 422
        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'])
423

Gregory Ashton's avatar
Fix #49  
Gregory Ashton committed
424
        try:
425 426
            if extension == 'json':
                with open(file_name, 'w') as file:
Colm Talbot's avatar
Colm Talbot committed
427
                    json.dump(dictionary, file, indent=2, cls=BilbyJsonEncoder)
428
            elif extension == 'hdf5':
429
                import deepdish
430 431 432
                for key in dictionary:
                    if isinstance(dictionary[key], pd.DataFrame):
                        dictionary[key] = dictionary[key].to_dict()
Sylvia Biscoveanu's avatar
Sylvia Biscoveanu committed
433 434
                deepdish.io.save(file_name, dictionary)
            else:
435
                raise ValueError("Extension type {} not understood".format(extension))
Gregory Ashton's avatar
Fix #49  
Gregory Ashton committed
436
        except Exception as e:
Gregory Ashton's avatar
Gregory Ashton committed
437
            logger.error("\n\n Saving the data has failed with the "
MoritzThomasHuebner's avatar
MoritzThomasHuebner committed
438
                         "following message:\n {} \n\n".format(e))
Gregory Ashton's avatar
Gregory Ashton committed
439

440
    def save_posterior_samples(self, outdir=None):
441
        """Saves posterior samples to a file"""
442 443
        outdir = self._safe_outdir_creation(outdir, self.save_posterior_samples)
        filename = '{}/{}_posterior_samples.txt'.format(outdir, self.label)
444 445
        self.posterior.to_csv(filename, index=False, header=True)

Gregory Ashton's avatar
Gregory Ashton committed
446
    def get_latex_labels_from_parameter_keys(self, keys):
447 448 449 450 451 452 453 454 455 456 457 458 459
        """ 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
460 461 462
        for k in keys:
            if k in self.search_parameter_keys:
                idx = self.search_parameter_keys.index(k)
463
                latex_labels.append(self.parameter_labels_with_unit[idx])
Gregory Ashton's avatar
Gregory Ashton committed
464
            elif k in self.parameter_labels:
465
                latex_labels.append(k)
Gregory Ashton's avatar
Gregory Ashton committed
466
            else:
Colm Talbot's avatar
Colm Talbot committed
467
                logger.debug(
468 469
                    'key {} not a parameter label or latex label'.format(k))
                latex_labels.append(' '.join(k.split('_')))
470
        return latex_labels
Gregory Ashton's avatar
Gregory Ashton committed
471

Gregory Ashton's avatar
Gregory Ashton committed
472 473 474 475 476 477 478 479 480
    @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
481 482 483
        if self.covariance_matrix.ndim == 0:
            return np.sqrt(self.covariance_matrix)
        else:
MoritzThomasHuebner's avatar
MoritzThomasHuebner committed
484 485
            return 1 / np.sqrt(np.abs(np.linalg.det(
                1 / self.covariance_matrix)))
Gregory Ashton's avatar
Gregory Ashton committed
486

487 488
    @staticmethod
    def prior_volume(priors):
Gregory Ashton's avatar
Gregory Ashton committed
489 490 491 492 493 494
        """ 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,

495 496 497
        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
498 499 500 501

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

502
    def get_one_dimensional_median_and_error_bar(self, key, fmt='.2f',
503
                                                 quantiles=(0.16, 0.84)):
504 505 506 507 508 509 510 511
        """ 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
512 513
        quantiles: list, tuple
            A length-2 tuple of the lower and upper-quantiles to calculate
514 515 516 517
            the errors bars for.

        Returns
        -------
518 519
        summary: namedtuple
            An object with attributes, median, lower, upper and string
520 521

        """
522 523
        summary = namedtuple('summary', ['median', 'lower', 'upper', 'string'])

524 525 526 527 528
        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)
529 530 531
        summary.median = quants[1]
        summary.plus = quants[2] - summary.median
        summary.minus = summary.median - quants[0]
532 533

        fmt = "{{0:{0}}}".format(fmt).format
534 535 536 537 538
        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
539 540 541
    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,
542 543
                            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
544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571

        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
572 573
        quantiles: tuple
            A length-2 tuple of the lower and upper-quantiles to calculate
Colm Talbot's avatar
Colm Talbot committed
574 575 576 577 578 579 580 581 582 583 584 585
            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()
586 587 588 589 590 591 592 593
        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
594 595 596 597 598 599 600 601 602 603 604 605 606
        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)
607
            ax.plot(theta, prior.prob(theta), color='C2')
Colm Talbot's avatar
Colm Talbot committed
608 609 610 611 612 613 614 615

        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)
616 617 618
            plt.close(fig)
        else:
            return fig
Colm Talbot's avatar
Colm Talbot committed
619

620 621
    def plot_marginals(self, parameters=None, priors=None, titles=True,
                       file_base_name=None, bins=50, label_fontsize=16,
622 623
                       title_fontsize=16, quantiles=(0.16, 0.84), dpi=300,
                       outdir=None):
624 625 626 627 628 629 630
        """ 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.
631
        priors: {bool (False), bilby.core.prior.PriorDict}
632
            If true, add the stored prior probability density functions to the
633
            one-dimensional marginal distributions. If instead a PriorDict
634 635 636 637 638 639 640 641 642 643 644 645
            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
646 647 648
            The font sizes for the labels and titles
        quantiles: tuple
            A length-2 tuple of the lower and upper-quantiles to calculate
649 650 651
            the errors bars for.
        dpi: int
            Dots per inch resolution of the plot
652 653
        outdir: str, optional
            Path to the outdir. Default is the one store in the result object.
654 655 656 657 658 659

        Returns
        -------
        """
        if isinstance(parameters, dict):
            plot_parameter_keys = list(parameters.keys())
Colm Talbot's avatar
Colm Talbot committed
660
            truths = parameters
661
        elif parameters is None:
Colm Talbot's avatar
Colm Talbot committed
662 663 664 665 666
            plot_parameter_keys = self.posterior.keys()
            if self.injection_parameters is None:
                truths = dict()
            else:
                truths = self.injection_parameters
667 668
        else:
            plot_parameter_keys = list(parameters)
Colm Talbot's avatar
Colm Talbot committed
669 670 671 672
            if self.injection_parameters is None:
                truths = dict()
            else:
                truths = self.injection_parameters
673 674

        if file_base_name is None:
675 676
            outdir = self._safe_outdir_creation(outdir, self.plot_marginals)
            file_base_name = '{}/{}_1d/'.format(outdir, self.label)
Colm Talbot's avatar
Colm Talbot committed
677
            check_directory_exists_and_if_not_mkdir(file_base_name)
678 679

        if priors is True:
Colm Talbot's avatar
Colm Talbot committed
680 681
            priors = getattr(self, 'priors', dict())
        elif isinstance(priors, dict):
682
            pass
Colm Talbot's avatar
Colm Talbot committed
683 684
        elif priors in [False, None]:
            priors = dict()
685 686 687 688
        else:
            raise ValueError('Input priors={} not understood'.format(priors))

        for i, key in enumerate(plot_parameter_keys):
Colm Talbot's avatar
Colm Talbot committed
689 690
            if not isinstance(self.posterior[key].values[0], float):
                continue
Colm Talbot's avatar
Colm Talbot committed
691 692
            prior = priors.get(key, None)
            truth = truths.get(key, None)
Colm Talbot's avatar
Colm Talbot committed
693
            for cumulative in [False, True]:
694
                self.plot_single_density(
Colm Talbot's avatar
Colm Talbot committed
695 696
                    key, prior=prior, cumulative=cumulative, title=titles,
                    truth=truth, save=True, file_base_name=file_base_name,
Colm Talbot's avatar
Colm Talbot committed
697 698
                    bins=bins, label_fontsize=label_fontsize, dpi=dpi,
                    title_fontsize=title_fontsize, quantiles=quantiles)
699

700 701 702
    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
703 704 705

        Parameters
        ----------
706 707 708
        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.
709
        priors: {bool (False), bilby.core.prior.PriorDict}
710
            If true, add the stored prior probability density functions to the
711
            one-dimensional marginal distributions. If instead a PriorDict
712
            is provided, this will be plotted.
713 714 715 716 717
        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.
718 719 720 721 722 723
        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
724 725 726
        **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
727 728
            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
729

730 731 732 733 734 735
        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
736 737 738 739
        Returns
        -------
        fig:
            A matplotlib figure instance
740

Gregory Ashton's avatar
Gregory Ashton committed
741
        """
742 743

        # If in testing mode, not corner plots are generated
744 745
        if utils.command_line_args.test:
            return
Gregory Ashton's avatar
Gregory Ashton committed
746

Colm Talbot's avatar
Colm Talbot committed
747
        # bilby default corner kwargs. Overwritten by anything passed to kwargs
748 749 750
        defaults_kwargs = dict(
            bins=50, smooth=0.9, label_kwargs=dict(fontsize=16),
            title_kwargs=dict(fontsize=16), color='#0072C1',
751
            truth_color='tab:orange', quantiles=[0.16, 0.84],
MoritzThomasHuebner's avatar
MoritzThomasHuebner committed
752
            levels=(1 - np.exp(-0.5), 1 - np.exp(-2), 1 - np.exp(-9 / 2.)),
753
            plot_density=False, plot_datapoints=True, fill_contours=True,
754 755 756 757 758 759
            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)
760

761 762 763 764
        if 'lionize' in kwargs and kwargs['lionize'] is True:
            defaults_kwargs['truth_color'] = 'tab:blue'
            defaults_kwargs['color'] = '#FF8C00'

765 766 767
        defaults_kwargs.update(kwargs)
        kwargs = defaults_kwargs

768 769 770 771 772 773 774 775 776 777 778 779 780 781 782
        # 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
783 784 785 786 787 788 789 790
        # 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}

791 792 793 794 795 796 797 798 799
        # 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)
800

801
        # Get latex formatted strings for the plot labels
802 803
        kwargs['labels'] = kwargs.get(
            'labels', self.get_latex_labels_from_parameter_keys(
804
                plot_parameter_keys))
805

806 807 808 809
        # 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))

810 811
        # Create the data array to plot and pass everything to corner
        xs = self.posterior[plot_parameter_keys].values
812
        fig = corner.corner(xs, **kwargs)
813
        axes = fig.get_axes()
814 815 816

        #  Add the titles
        if titles and kwargs.get('quantiles', None) is not None:
817 818
            for i, par in enumerate(plot_parameter_keys):
                ax = axes[i + i * len(plot_parameter_keys)]
819 820
                if ax.title.get_text() == '':
                    ax.set_title(self.get_one_dimensional_median_and_error_bar(
821
                        par, quantiles=kwargs['quantiles']).string,
822 823 824
                        **kwargs['title_kwargs'])

        #  Add priors to the 1D plots
825 826 827
        if priors is True:
            priors = getattr(self, 'priors', False)
        if isinstance(priors, dict):
828 829
            for i, par in enumerate(plot_parameter_keys):
                ax = axes[i + i * len(plot_parameter_keys)]
830 831
                theta = np.linspace(ax.get_xlim()[0], ax.get_xlim()[1], 300)
                ax.plot(theta, priors[par].prob(theta), color='C2')
832 833 834 835
        elif priors in [False, None]:
            pass
        else:
            raise ValueError('Input priors={} not understood'.format(priors))
836

837
        if save:
838
            if filename is None:
839 840
                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
841
            logger.debug('Saving corner plot to {}'.format(filename))
842
            fig.savefig(filename, dpi=dpi)
843
            plt.close(fig)
844

845
        return fig
846

Gregory Ashton's avatar
Gregory Ashton committed
847
    def plot_walkers(self, **kwargs):
MoritzThomasHuebner's avatar
A typo  
MoritzThomasHuebner committed
848
        """ Method to plot the trace of the walkers in an ensemble MCMC plot """
849
        if hasattr(self, 'walkers') is False:
Gregory Ashton's avatar
Gregory Ashton committed
850
            logger.warning("Cannot plot_walkers as no walkers are saved")
851
            return
852 853 854

        if utils.command_line_args.test:
            return
855 856 857

        nwalkers, nsteps, ndim = self.walkers.shape
        idxs = np.arange(nsteps)
MoritzThomasHuebner's avatar
MoritzThomasHuebner committed
858
        fig, axes = plt.subplots(nrows=ndim, figsize=(6, 3 * ndim))
859 860
        walkers = self.walkers[:, :, :]
        for i, ax in enumerate(axes):
MoritzThomasHuebner's avatar
MoritzThomasHuebner committed
861
            ax.plot(idxs[:self.nburn + 1], walkers[:, :self.nburn + 1, i].T,
862 863 864 865 866 867 868 869 870
                    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()
871 872
        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
873
        logger.debug('Saving walkers plot to {}'.format('filename'))
874
        fig.savefig(filename)
875
        plt.close(fig)
876

877 878 879
    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,
880
                       maxl_label='max likelihood', dpi=300, outdir=None):
881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905
        """ 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.
906 907
        outdir: str, optional
            Path to the outdir. Default is the one store in the result object.
908 909

        """
910 911 912 913 914 915

        # 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]

916 917 918 919
        xsmooth = np.linspace(np.min(x), np.max(x), npoints)
        fig, ax = plt.subplots()
        logger.info('Plotting {} draws'.format(ndraws))
        for _ in range(ndraws):
920
            s = model_posterior.sample().to_dict('records')[0]
921 922
            ax.plot(xsmooth, model(xsmooth, **s), alpha=0.25, lw=0.1, color='r',
                    label=draws_label)
923 924 925
        try:
            if all(~np.isnan(self.posterior.log_likelihood)):
                logger.info('Plotting maximum likelihood')
Colm Talbot's avatar
Colm Talbot committed
926
                s = model_posterior.iloc[self.posterior.log_likelihood.idxmax()]
927 928
                ax.plot(xsmooth, model(xsmooth, **s), lw=1, color='k',
                        label=maxl_label)
929
        except (AttributeError, TypeError):
930 931
            logger.debug(
                "No log likelihood values stored, unable to plot max")
932 933 934 935 936 937 938 939 940 941 942 943 944 945

        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:
946 947
            outdir = self._safe_outdir_creation(outdir, self.plot_with_data)
            filename = '{}/{}_plot_with_data'.format(outdir, self.label)
948
        fig.savefig(filename, dpi=dpi)
949
        plt.close(fig)
950

951 952
    def samples_to_posterior(self, likelihood=None, priors=None,
                             conversion_function=None):
953
        """
954 955 956
        Convert array of samples to posterior (a Pandas data frame)

        Also applies the conversion function to any stored posterior
957

958 959
        Parameters
        ----------
Colm Talbot's avatar
Colm Talbot committed
960
        likelihood: bilby.likelihood.GravitationalWaveTransient, optional
961 962
            GravitationalWaveTransient likelihood used for sampling.
        priors: dict, optional
963
            Dictionary of prior object, used to fill in delta function priors.
964
        conversion_function: function, optional
965 966
            Function which adds in extra parameters to the data frame,
            should take the data_frame, likelihood and prior as arguments.
967
        """
968 969 970
        try:
            data_frame = self.posterior
        except ValueError:
971 972
            data_frame = pd.DataFrame(
                self.samples, columns=self.search_parameter_keys)
973
            for key in priors:
974
                if isinstance(priors[key], DeltaFunction):
975
                    data_frame[key] = priors[key].peak
976 977 978 979
                elif isinstance(priors[key], float):
                    data_frame[key] = priors[key]
            data_frame['log_likelihood'] = getattr(
                self, 'log_likelihood_evaluations', np.nan)
980 981 982 983 984
            if self.log_prior_evaluations is None:
                data_frame['log_prior'] = self.priors.ln_prob(
                    data_frame[self.search_parameter_keys], axis=0)
            else:
                data_frame['log_prior'] = self.log_prior_evaluations
985
        if conversion_function is not None:
986
            data_frame = conversion_function(data_frame, likelihood, priors)
987
        self.posterior = data_frame
Gregory Ashton's avatar
Gregory Ashton committed
988

Colm Talbot's avatar
Colm Talbot committed
989
    def calculate_prior_values(self, priors):
990 991 992 993 994
        """
        Evaluate prior probability for each parameter for each sample.

        Parameters
        ----------
995
        priors: dict, PriorDict
996 997 998 999 1000 1001 1002 1003 1004 1005 1006
            Prior distributions
        """
        self.prior_values = pd.DataFrame()
        for key in priors:
            if key in self.posterior.keys():
                if isinstance(priors[key], DeltaFunction):
                    continue
                else:
                    self.prior_values[key]\
                        = priors[key].prob(self.posterior[key].values)

Colm Talbot's avatar
Colm Talbot committed
1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049
    def get_all_injection_credible_levels(self):
        """
        Get credible levels for all parameters in self.injection_parameters

        Returns
        -------
        credible_levels: dict
            The credible levels at which the injected parameters are found.
        """
        if self.injection_parameters is None:
            raise(TypeError, "Result object has no 'injection_parameters'. "
                             "Cannot copmute credible levels.")
        credible_levels = {key: self.get_injection_credible_level(key)
                           for key in self.search_parameter_keys
                           if isinstance(self.injection_parameters[key], float)}
        return credible_levels

    def get_injection_credible_level(self, parameter):
        """
        Get the credible level of the injected parameter

        Calculated as CDF(injection v