result.py 33.8 KB
Newer Older
1
import os
2
from distutils.version import LooseVersion
3
import numpy as np
4
import deepdish
5
import pandas as pd
6
import corner
7
import matplotlib
8
import matplotlib.pyplot as plt
9
from collections import OrderedDict, namedtuple
10

11
from . import utils
12
from .utils import logger, infer_parameters_from_function
13
from .prior import PriorDict, DeltaFunction
14

15

16
def result_file_name(outdir, label):
17 18 19 20 21 22 23 24 25 26 27 28 29
    """ 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

    Returns
    -------
    str: File name of the output file
    """
30 31 32
    return '{}/{}_result.h5'.format(outdir, label)


33
def read_in_result(filename=None, outdir=None, label=None):
Gregory Ashton's avatar
Gregory Ashton committed
34 35 36 37 38 39
    """ Read in a saved .h5 data file

    Parameters
    ----------
    filename: str
        If given, try to load from this filename
40 41
    outdir, label: str
        If given, use the default naming convention for saved results file
Gregory Ashton's avatar
Gregory Ashton committed
42

43 44
    Returns
    -------
Colm Talbot's avatar
Colm Talbot committed
45
    result: bilby.core.result.Result
46

Moritz Huebner's avatar
Moritz Huebner committed
47
    Raises
48 49
    -------
    ValueError: If no filename is given and either outdir or label is None
Colm Talbot's avatar
Colm Talbot committed
50
                If no bilby.core.result.Result is found in the path
Gregory Ashton's avatar
Gregory Ashton committed
51 52 53

    """
    if filename is None:
54 55 56 57
        if (outdir is None) and (label is None):
            raise ValueError("No information given to load file")
        else:
            filename = result_file_name(outdir, label)
58
    if os.path.isfile(filename):
59
        return Result(**deepdish.io.load(filename))
60
    else:
61 62 63 64 65 66 67 68 69 70 71 72 73 74 75
        raise IOError("No result '{}' found".format(filename))


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,
                 sampling_time=None, nburn=None, walkers=None,
                 max_autocorrelation_time=None, parameter_labels=None,
                 parameter_labels_with_unit=None):
        """ A class to store the results of the sampling run
76 77 78

        Parameters
        ----------
79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113
        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
        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

        Note:
            All sampling output parameters, e.g. the samples themselves are
            typically not given at initialisation, but set at a later stage.
114 115

        """
116

117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140
        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
        self.sampling_time = sampling_time

    def __str__(self):
141
        """Print a summary """
142 143
        if getattr(self, 'posterior', None) is not None:
            if getattr(self, 'log_noise_evidence', None) is not None:
144 145 146 147
                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"
148
                        .format(len(self.posterior), self.log_noise_evidence, self.log_evidence,
149 150 151 152 153
                                self.log_evidence_err, self.log_bayes_factor,
                                self.log_evidence_err))
            else:
                return ("nsamples: {:d}\n"
                        "log_evidence: {:6.3f} +/- {:6.3f}\n"
154
                        .format(len(self.posterior), self.log_evidence, self.log_evidence_err))
155 156
        else:
            return ''
157

158 159 160 161 162 163
    @property
    def priors(self):
        if self._priors is not None:
            return self._priors
        else:
            raise ValueError('Result object has no priors')
164

165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182
    @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")
183

184 185 186 187 188
    @property
    def samples(self):
        """ An array of samples """
        if self._samples is not None:
            return self._samples
189
        else:
190
            raise ValueError("Result object has no stored samples")
191

192 193 194
    @samples.setter
    def samples(self, samples):
        self._samples = samples
195

196 197 198 199 200 201 202
    @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")
203

204 205 206
    @nested_samples.setter
    def nested_samples(self, nested_samples):
        self._nested_samples = nested_samples
207

208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260
    @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

    def _get_save_data_dictionary(self):
        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',
            'log_likelihood_evaluations', 'samples', 'nested_samples',
            'walkers', 'nburn', 'parameter_labels',
            'parameter_labels_with_unit']
        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
261

Colm Talbot's avatar
Colm Talbot committed
262 263 264 265 266 267 268 269 270 271
    def save_to_file(self, overwrite=False):
        """
        Writes the Result to a deepdish h5 file

        Parameters
        ----------
        overwrite: bool, optional
            Whether or not to overwrite an existing result file.
            default=False
        """
272
        file_name = result_file_name(self.outdir, self.label)
273
        utils.check_directory_exists_and_if_not_mkdir(self.outdir)
274
        if os.path.isfile(file_name):
Colm Talbot's avatar
Colm Talbot committed
275 276 277 278 279 280 281 282
            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')
283

Gregory Ashton's avatar
Gregory Ashton committed
284
        logger.debug("Saving result to {}".format(file_name))
285 286

        # Convert the prior to a string representation for saving on disk
287
        dictionary = self._get_save_data_dictionary()
288 289 290
        if dictionary.get('priors', False):
            dictionary['priors'] = {key: str(self.priors[key]) for key in self.priors}

291 292 293 294 295
        # Convert callable sampler_kwargs to strings to avoid pickling issues
        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'])
296

Gregory Ashton's avatar
Fix #49  
Gregory Ashton committed
297
        try:
298
            deepdish.io.save(file_name, dictionary)
Gregory Ashton's avatar
Fix #49  
Gregory Ashton committed
299
        except Exception as e:
Gregory Ashton's avatar
Gregory Ashton committed
300
            logger.error("\n\n Saving the data has failed with the "
MoritzThomasHuebner's avatar
MoritzThomasHuebner committed
301
                         "following message:\n {} \n\n".format(e))
Gregory Ashton's avatar
Gregory Ashton committed
302

303
    def save_posterior_samples(self):
304
        """Saves posterior samples to a file"""
305
        filename = '{}/{}_posterior_samples.txt'.format(self.outdir, self.label)
306
        utils.check_directory_exists_and_if_not_mkdir(self.outdir)
307 308
        self.posterior.to_csv(filename, index=False, header=True)

Gregory Ashton's avatar
Gregory Ashton committed
309
    def get_latex_labels_from_parameter_keys(self, keys):
310 311 312 313 314 315 316 317 318 319 320 321 322
        """ 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
323 324 325
        for k in keys:
            if k in self.search_parameter_keys:
                idx = self.search_parameter_keys.index(k)
326
                latex_labels.append(self.parameter_labels_with_unit[idx])
Gregory Ashton's avatar
Gregory Ashton committed
327
            elif k in self.parameter_labels:
328
                latex_labels.append(k)
Gregory Ashton's avatar
Gregory Ashton committed
329
            else:
330 331 332
                logger.info(
                    'key {} not a parameter label or latex label'.format(k))
                latex_labels.append(' '.join(k.split('_')))
333
        return latex_labels
Gregory Ashton's avatar
Gregory Ashton committed
334

Gregory Ashton's avatar
Gregory Ashton committed
335 336 337 338 339 340 341 342 343
    @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
344 345 346
        if self.covariance_matrix.ndim == 0:
            return np.sqrt(self.covariance_matrix)
        else:
MoritzThomasHuebner's avatar
MoritzThomasHuebner committed
347 348
            return 1 / np.sqrt(np.abs(np.linalg.det(
                1 / self.covariance_matrix)))
Gregory Ashton's avatar
Gregory Ashton committed
349

350 351
    @staticmethod
    def prior_volume(priors):
Gregory Ashton's avatar
Gregory Ashton committed
352 353 354 355 356 357
        """ 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,

358 359 360
        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
361 362 363 364

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

365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380
    def get_one_dimensional_median_and_error_bar(self, key, fmt='.2f',
                                                 quantiles=[0.16, 0.84]):
        """ 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
        quantiles: list
            A length-2 list of the lower and upper-quantiles to calculate
            the errors bars for.

        Returns
        -------
381 382
        summary: namedtuple
            An object with attributes, median, lower, upper and string
383 384

        """
385 386
        summary = namedtuple('summary', ['median', 'lower', 'upper', 'string'])

387 388 389 390 391
        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)
392 393 394
        summary.median = quants[1]
        summary.plus = quants[2] - summary.median
        summary.minus = summary.median - quants[0]
395 396

        fmt = "{{0:{0}}}".format(fmt).format
397 398 399 400 401 402 403 404 405 406 407 408 409 410 411
        string_template = r"${{{0}}}_{{-{1}}}^{{+{2}}}$"
        summary.string = string_template.format(
            fmt(summary.median), fmt(summary.minus), fmt(summary.plus))
        return summary

    def plot_marginals(self, parameters=None, priors=None, titles=True,
                       file_base_name=None, bins=50, label_fontsize=16,
                       title_fontsize=16, quantiles=[0.16, 0.84], dpi=300):
        """ 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.
412
        priors: {bool (False), bilby.core.prior.PriorDict}
413
            If true, add the stored prior probability density functions to the
414
            one-dimensional marginal distributions. If instead a PriorDict
415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486
            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
            The fontsizes for the labels and titles
        quantiles: list
            A length-2 list of the lower and upper-quantiles to calculate
            the errors bars for.
        dpi: int
            Dots per inch resolution of the plot

        Returns
        -------
        figures: dictionary
            A dictionary of the matplotlib figures

        """

        if isinstance(parameters, dict):
            plot_parameter_keys = list(parameters.keys())
            truths = list(parameters.values())
        elif parameters is None:
            plot_parameter_keys = self.search_parameter_keys
            truths = None
        else:
            plot_parameter_keys = list(parameters)
            truths = None

        labels = self.get_latex_labels_from_parameter_keys(plot_parameter_keys)
        if file_base_name is None:
            file_base_name = '{}/{}_'.format(self.outdir, self.label)

        if priors is True:
            priors = getattr(self, 'priors', False)
        elif isinstance(priors, (dict)) or priors in [False, None]:
            pass
        else:
            raise ValueError('Input priors={} not understood'.format(priors))

        figures = dict()
        for i, key in enumerate(plot_parameter_keys):
            fig, ax = plt.subplots()
            ax.hist(self.posterior[key].values, bins=bins, density=True,
                    histtype='step')
            ax.set_xlabel(labels[i], fontsize=label_fontsize)
            if truths is not None:
                ax.axvline(truths[i], 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 titles:
                ax.set_title(summary.string, fontsize=title_fontsize)

            if isinstance(priors, dict):
                theta = np.linspace(ax.get_xlim()[0], ax.get_xlim()[1], 300)
                ax.plot(theta, priors[key].prob(theta), color='C2')

            fig.tight_layout()
            fig.savefig(file_base_name + key)
            figures[key] = fig

        return figures
487

488 489 490
    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
491 492 493

        Parameters
        ----------
494 495 496
        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.
497
        priors: {bool (False), bilby.core.prior.PriorDict}
498
            If true, add the stored prior probability density functions to the
499
            one-dimensional marginal distributions. If instead a PriorDict
500
            is provided, this will be plotted.
501 502 503 504 505
        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.
506 507 508 509 510 511
        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
512 513 514 515
        **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
            overridden.
Gregory Ashton's avatar
Gregory Ashton committed
516

517 518 519 520 521 522
        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
523 524 525 526
        Returns
        -------
        fig:
            A matplotlib figure instance
527

Gregory Ashton's avatar
Gregory Ashton committed
528
        """
529 530

        # If in testing mode, not corner plots are generated
531 532
        if utils.command_line_args.test:
            return
Gregory Ashton's avatar
Gregory Ashton committed
533

Colm Talbot's avatar
Colm Talbot committed
534
        # bilby default corner kwargs. Overwritten by anything passed to kwargs
535 536 537
        defaults_kwargs = dict(
            bins=50, smooth=0.9, label_kwargs=dict(fontsize=16),
            title_kwargs=dict(fontsize=16), color='#0072C1',
538
            truth_color='tab:orange', quantiles=[0.16, 0.84],
MoritzThomasHuebner's avatar
MoritzThomasHuebner committed
539
            levels=(1 - np.exp(-0.5), 1 - np.exp(-2), 1 - np.exp(-9 / 2.)),
540
            plot_density=False, plot_datapoints=True, fill_contours=True,
541 542 543 544 545 546
            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)
547

548 549 550 551
        if 'lionize' in kwargs and kwargs['lionize'] is True:
            defaults_kwargs['truth_color'] = 'tab:blue'
            defaults_kwargs['color'] = '#FF8C00'

552 553 554
        defaults_kwargs.update(kwargs)
        kwargs = defaults_kwargs

555 556 557 558 559 560 561 562 563 564 565 566 567 568 569
        # 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
570 571 572 573 574 575 576 577
        # 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}

578 579 580 581 582 583 584 585 586
        # 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)
587

588
        # Get latex formatted strings for the plot labels
589 590
        kwargs['labels'] = kwargs.get(
            'labels', self.get_latex_labels_from_parameter_keys(
591
                plot_parameter_keys))
592

593 594
        # Create the data array to plot and pass everything to corner
        xs = self.posterior[plot_parameter_keys].values
595
        fig = corner.corner(xs, **kwargs)
596
        axes = fig.get_axes()
597 598 599

        #  Add the titles
        if titles and kwargs.get('quantiles', None) is not None:
600 601
            for i, par in enumerate(plot_parameter_keys):
                ax = axes[i + i * len(plot_parameter_keys)]
602 603
                if ax.title.get_text() == '':
                    ax.set_title(self.get_one_dimensional_median_and_error_bar(
604
                        par, quantiles=kwargs['quantiles']).string,
605 606 607
                        **kwargs['title_kwargs'])

        #  Add priors to the 1D plots
608 609 610
        if priors is True:
            priors = getattr(self, 'priors', False)
        if isinstance(priors, dict):
611 612
            for i, par in enumerate(plot_parameter_keys):
                ax = axes[i + i * len(plot_parameter_keys)]
613 614
                theta = np.linspace(ax.get_xlim()[0], ax.get_xlim()[1], 300)
                ax.plot(theta, priors[par].prob(theta), color='C2')
615 616 617 618
        elif priors in [False, None]:
            pass
        else:
            raise ValueError('Input priors={} not understood'.format(priors))
619

620
        if save:
621 622 623
            if filename is None:
                utils.check_directory_exists_and_if_not_mkdir(self.outdir)
                filename = '{}/{}_corner.png'.format(self.outdir, self.label)
Gregory Ashton's avatar
Gregory Ashton committed
624
            logger.debug('Saving corner plot to {}'.format(filename))
625
            fig.savefig(filename, dpi=dpi)
626

627
        return fig
628

Gregory Ashton's avatar
Gregory Ashton committed
629
    def plot_walkers(self, **kwargs):
MoritzThomasHuebner's avatar
A typo  
MoritzThomasHuebner committed
630
        """ Method to plot the trace of the walkers in an ensemble MCMC plot """
631
        if hasattr(self, 'walkers') is False:
Gregory Ashton's avatar
Gregory Ashton committed
632
            logger.warning("Cannot plot_walkers as no walkers are saved")
633
            return
634 635 636

        if utils.command_line_args.test:
            return
637 638 639

        nwalkers, nsteps, ndim = self.walkers.shape
        idxs = np.arange(nsteps)
MoritzThomasHuebner's avatar
MoritzThomasHuebner committed
640
        fig, axes = plt.subplots(nrows=ndim, figsize=(6, 3 * ndim))
641 642
        walkers = self.walkers[:, :, :]
        for i, ax in enumerate(axes):
MoritzThomasHuebner's avatar
MoritzThomasHuebner committed
643
            ax.plot(idxs[:self.nburn + 1], walkers[:, :self.nburn + 1, i].T,
644 645 646 647 648 649 650 651 652 653
                    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()
        filename = '{}/{}_walkers.png'.format(self.outdir, self.label)
Gregory Ashton's avatar
Gregory Ashton committed
654
        logger.debug('Saving walkers plot to {}'.format('filename'))
655
        utils.check_directory_exists_and_if_not_mkdir(self.outdir)
656 657
        fig.savefig(filename)

658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688
    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,
                       maxl_label='max likelihood', dpi=300):
        """ 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.

        """
689 690 691 692 693 694

        # 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]

695 696 697 698
        xsmooth = np.linspace(np.min(x), np.max(x), npoints)
        fig, ax = plt.subplots()
        logger.info('Plotting {} draws'.format(ndraws))
        for _ in range(ndraws):
699
            s = model_posterior.sample().to_dict('records')[0]
700 701
            ax.plot(xsmooth, model(xsmooth, **s), alpha=0.25, lw=0.1, color='r',
                    label=draws_label)
702 703 704 705 706 707 708 709 710
        try:
            if all(~np.isnan(self.posterior.log_likelihood)):
                logger.info('Plotting maximum likelihood')
                s = model_posterior.ix[self.posterior.log_likelihood.idxmax()]
                ax.plot(xsmooth, model(xsmooth, **s), lw=1, color='k',
                        label=maxl_label)
        except AttributeError:
            logger.debug(
                "No log likelihood values stored, unable to plot max")
711 712 713 714 715 716 717 718 719 720 721 722 723 724

        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:
725
            utils.check_directory_exists_and_if_not_mkdir(self.outdir)
726 727 728
            filename = '{}/{}_plot_with_data'.format(self.outdir, self.label)
        fig.savefig(filename, dpi=dpi)

729 730
    def samples_to_posterior(self, likelihood=None, priors=None,
                             conversion_function=None):
731
        """
732 733 734
        Convert array of samples to posterior (a Pandas data frame)

        Also applies the conversion function to any stored posterior
735

736 737
        Parameters
        ----------
Colm Talbot's avatar
Colm Talbot committed
738
        likelihood: bilby.likelihood.GravitationalWaveTransient, optional
739 740
            GravitationalWaveTransient likelihood used for sampling.
        priors: dict, optional
741
            Dictionary of prior object, used to fill in delta function priors.
742
        conversion_function: function, optional
743 744
            Function which adds in extra parameters to the data frame,
            should take the data_frame, likelihood and prior as arguments.
745
        """
746 747 748
        try:
            data_frame = self.posterior
        except ValueError:
749 750
            data_frame = pd.DataFrame(
                self.samples, columns=self.search_parameter_keys)
751
            for key in priors:
752
                if isinstance(priors[key], DeltaFunction):
753
                    data_frame[key] = priors[key].peak
754 755 756 757
                elif isinstance(priors[key], float):
                    data_frame[key] = priors[key]
            data_frame['log_likelihood'] = getattr(
                self, 'log_likelihood_evaluations', np.nan)
758
        if conversion_function is not None:
759
            data_frame = conversion_function(data_frame, likelihood, priors)
760
        self.posterior = data_frame
Gregory Ashton's avatar
Gregory Ashton committed
761

Colm Talbot's avatar
Colm Talbot committed
762
    def calculate_prior_values(self, priors):
763 764 765 766 767
        """
        Evaluate prior probability for each parameter for each sample.

        Parameters
        ----------
768
        priors: dict, PriorDict
769 770 771 772 773 774 775 776 777 778 779
            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)

780
    def _check_attribute_match_to_other_object(self, name, other_object):
781 782 783 784 785 786 787 788 789 790 791 792 793 794
        """ Check attribute name exists in other_object and is the same

        Parameters
        ----------
        name: str
            Name of the attribute in this instance
        other_object: object
            Other object with attributes to compare with

        Returns
        -------
        bool: True if attribute name matches with an attribute of other_object, False otherwise

        """
795
        A = getattr(self, name, False)
796
        B = getattr(other_object, name, False)
Gregory Ashton's avatar
Gregory Ashton committed
797
        logger.debug('Checking {} value: {}=={}'.format(name, A, B))
798 799 800 801 802
        if (A is not False) and (B is not False):
            typeA = type(A)
            typeB = type(B)
            if typeA == typeB:
                if typeA in [str, float, int, dict, list]:
Gregory Ashton's avatar
Gregory Ashton committed
803 804 805 806
                    try:
                        return A == B
                    except ValueError:
                        return False
807 808 809
                elif typeA in [np.ndarray]:
                    return np.all(A == B)
        return False
810 811 812


def plot_multiple(results, filename=None, labels=None, colours=None,
813
                  save=True, evidences=False, **kwargs):
814 815 816 817 818
    """ Generate a corner plot overlaying two sets of results

    Parameters
    ----------
    results: list
Colm Talbot's avatar
Colm Talbot committed
819
        A list of `bilby.core.result.Result` objects containing the samples to
820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835
        plot.
    filename: str
        File name to save the figure to. If None (default), a filename is
        constructed from the outdir of the first element of results and then
        the labels for all the result files.
    labels: list
        List of strings to use when generating a legend. If None (default), the
        `label` attribute of each result in `results` is used.
    colours: list
        The colours for each result. If None, default styles are applied.
    save: bool
        If true, save the figure
    kwargs: dict
        All other keyword arguments are passed to `result.plot_corner`.
        However, `show_titles` and `truths` are ignored since they would be
        ambiguous on such a plot.
836 837 838
    evidences: bool, optional
        Add the log-evidence calculations to the legend. If available, the
        Bayes factor will be used instead.
839 840 841 842 843 844 845 846 847 848 849 850

    Returns
    -------
    fig:
        A matplotlib figure instance

    """

    kwargs['show_titles'] = False
    kwargs['truths'] = None

    fig = results[0].plot_corner(save=False, **kwargs)
Gregory Ashton's avatar
Gregory Ashton committed
851
    default_filename = '{}/{}'.format(results[0].outdir, 'combined')
852 853 854 855 856 857 858
    lines = []
    default_labels = []
    for i, result in enumerate(results):
        if colours:
            c = colours[i]
        else:
            c = 'C{}'.format(i)
Gregory Ashton's avatar
Gregory Ashton committed
859 860
        hist_kwargs = kwargs.get('hist_kwargs', dict())
        hist_kwargs['color'] = c
861 862 863 864 865
        fig = result.plot_corner(fig=fig, save=False, color=c, **kwargs)
        default_filename += '_{}'.format(result.label)
        lines.append(matplotlib.lines.Line2D([0], [0], color=c))
        default_labels.append(result.label)

Gregory Ashton's avatar
Gregory Ashton committed
866 867 868 869 870
    # Rescale the axes
    for i, ax in enumerate(fig.axes):
        ax.autoscale()
    plt.draw()

871 872 873
    if labels is None:
        labels = default_labels

874 875
    if evidences:
        if np.isnan(results[0].log_bayes_factor):
876
            template = ' $\mathrm{{ln}}(Z)={lnz:1.3g}$'
877
        else:
878 879 880 881
            template = ' $\mathrm{{ln}}(B)={lnbf:1.3g}$'
        labels = [template.format(lnz=result.log_evidence,
                                  lnbf=result.log_bayes_factor)
                  for ii, result in enumerate(results)]
882

883 884
    axes = fig.get_axes()
    ndim = int(np.sqrt(len(axes)))
MoritzThomasHuebner's avatar
MoritzThomasHuebner committed
885
    axes[ndim - 1].legend(lines, labels)
886 887 888 889 890 891 892

    if filename is None:
        filename = default_filename

    if save:
        fig.savefig(filename)
    return fig