result.py 44.7 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
import numpy as np
8
import deepdish
9
import pandas as pd
10
import corner
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 18 19
from .utils import (logger, infer_parameters_from_function,
                    check_directory_exists_and_if_not_mkdir)
from .prior import Prior, PriorDict, DeltaFunction
20

21

22
def result_file_name(outdir, label):
23 24 25 26 27 28 29 30 31 32 33 34 35
    """ 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
    """
36 37 38
    return '{}/{}_result.h5'.format(outdir, label)


39
def read_in_result(filename=None, outdir=None, label=None):
40 41
    """ Wrapper to bilby.core.result.Result.from_hdf5 """
    return Result.from_hdf5(filename=filename, outdir=outdir, label=label)
42 43 44 45 46 47 48 49 50 51


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,
52 53 54 55
                 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):
56
        """ A class to store the results of the sampling run
57 58 59

        Parameters
        ----------
60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80
        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
81 82
        log_prior_evaluations: array_like
            The evaluations of the prior for each sample point
83 84 85 86 87 88 89 90 91 92
        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
93 94 95
        version: str,
            Version information for software used to generate the result. Note,
            this information is generated when the result object is initialized
96

97 98 99 100
        Note
        ---------
        All sampling output parameters, e.g. the samples themselves are
        typically not given at initialisation, but set at a later stage.
101 102

        """
103

104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124
        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
125
        self.log_prior_evaluations = log_prior_evaluations
126
        self.sampling_time = sampling_time
127
        self.version = version
Colm Talbot's avatar
Colm Talbot committed
128
        self.max_autocorrelation_time = max_autocorrelation_time
129

130 131 132
        self.prior_values = None
        self._kde = None

133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159
    @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

        """
        if filename is None:
            if (outdir is None) and (label is None):
                raise ValueError("No information given to load file")
            else:
                filename = result_file_name(outdir, label)
        if os.path.isfile(filename):
Moritz Huebner's avatar
Moritz Huebner committed
160 161 162 163 164 165 166 167 168
            dictionary = deepdish.io.load(filename)
            # Some versions of deepdish/pytables return the dictionanary as
            # a dictionary with a kay 'data'
            if len(dictionary) == 1 and 'data' in dictionary:
                dictionary = dictionary['data']
            try:
                return cls(**dictionary)
            except TypeError as e:
                raise IOError("Unable to load dictionary, error={}".format(e))
169 170 171
        else:
            raise IOError("No result '{}' found".format(filename))

172
    def __str__(self):
173
        """Print a summary """
174 175
        if getattr(self, 'posterior', None) is not None:
            if getattr(self, 'log_noise_evidence', None) is not None:
176 177 178 179
                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"
180
                        .format(len(self.posterior), self.log_noise_evidence, self.log_evidence,
181 182 183 184 185
                                self.log_evidence_err, self.log_bayes_factor,
                                self.log_evidence_err))
            else:
                return ("nsamples: {:d}\n"
                        "log_evidence: {:6.3f} +/- {:6.3f}\n"
186
                        .format(len(self.posterior), self.log_evidence, self.log_evidence_err))
187 188
        else:
            return ''
189

190 191 192 193 194 195
    @property
    def priors(self):
        if self._priors is not None:
            return self._priors
        else:
            raise ValueError('Result object has no priors')
196

197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214
    @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")
215

216 217 218 219 220
    @property
    def samples(self):
        """ An array of samples """
        if self._samples is not None:
            return self._samples
221
        else:
222
            raise ValueError("Result object has no stored samples")
223

224 225 226
    @samples.setter
    def samples(self, samples):
        self._samples = samples
227

228 229 230 231 232 233 234
    @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")
235

236 237 238
    @nested_samples.setter
    def nested_samples(self, nested_samples):
        self._nested_samples = nested_samples
239

240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275
    @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

276 277 278 279 280 281 282 283 284 285 286
    @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

287
    def _get_save_data_dictionary(self):
288
        # This list defines all the parameters saved in the result object
289 290 291 292 293
        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',
294 295
            'log_likelihood_evaluations', 'log_prior_evaluations', 'samples',
            'nested_samples', 'walkers', 'nburn', 'parameter_labels',
296
            'parameter_labels_with_unit', 'version']
297 298 299 300 301 302 303 304
        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
305

306
    def save_to_file(self, overwrite=False, outdir=None):
Colm Talbot's avatar
Colm Talbot committed
307 308 309 310 311 312 313 314
        """
        Writes the Result to a deepdish h5 file

        Parameters
        ----------
        overwrite: bool, optional
            Whether or not to overwrite an existing result file.
            default=False
315 316
        outdir: str, optional
            Path to the outdir. Default is the one stored in the result object.
Colm Talbot's avatar
Colm Talbot committed
317
        """
318 319 320
        outdir = self._safe_outdir_creation(outdir, self.save_to_file)
        file_name = result_file_name(outdir, self.label)

321
        if os.path.isfile(file_name):
Colm Talbot's avatar
Colm Talbot committed
322 323 324 325 326 327 328 329
            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')
330

Gregory Ashton's avatar
Gregory Ashton committed
331
        logger.debug("Saving result to {}".format(file_name))
332 333

        # Convert the prior to a string representation for saving on disk
334
        dictionary = self._get_save_data_dictionary()
335 336 337
        if dictionary.get('priors', False):
            dictionary['priors'] = {key: str(self.priors[key]) for key in self.priors}

338 339 340 341 342
        # 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'])
343

Gregory Ashton's avatar
Fix #49  
Gregory Ashton committed
344
        try:
345
            deepdish.io.save(file_name, dictionary)
Gregory Ashton's avatar
Fix #49  
Gregory Ashton committed
346
        except Exception as e:
Gregory Ashton's avatar
Gregory Ashton committed
347
            logger.error("\n\n Saving the data has failed with the "
MoritzThomasHuebner's avatar
MoritzThomasHuebner committed
348
                         "following message:\n {} \n\n".format(e))
Gregory Ashton's avatar
Gregory Ashton committed
349

350
    def save_posterior_samples(self, outdir=None):
351
        """Saves posterior samples to a file"""
352 353
        outdir = self._safe_outdir_creation(outdir, self.save_posterior_samples)
        filename = '{}/{}_posterior_samples.txt'.format(outdir, self.label)
354 355
        self.posterior.to_csv(filename, index=False, header=True)

Gregory Ashton's avatar
Gregory Ashton committed
356
    def get_latex_labels_from_parameter_keys(self, keys):
357 358 359 360 361 362 363 364 365 366 367 368 369
        """ 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
370 371 372
        for k in keys:
            if k in self.search_parameter_keys:
                idx = self.search_parameter_keys.index(k)
373
                latex_labels.append(self.parameter_labels_with_unit[idx])
Gregory Ashton's avatar
Gregory Ashton committed
374
            elif k in self.parameter_labels:
375
                latex_labels.append(k)
Gregory Ashton's avatar
Gregory Ashton committed
376
            else:
Colm Talbot's avatar
Colm Talbot committed
377
                logger.debug(
378 379
                    'key {} not a parameter label or latex label'.format(k))
                latex_labels.append(' '.join(k.split('_')))
380
        return latex_labels
Gregory Ashton's avatar
Gregory Ashton committed
381

Gregory Ashton's avatar
Gregory Ashton committed
382 383 384 385 386 387 388 389 390
    @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
391 392 393
        if self.covariance_matrix.ndim == 0:
            return np.sqrt(self.covariance_matrix)
        else:
MoritzThomasHuebner's avatar
MoritzThomasHuebner committed
394 395
            return 1 / np.sqrt(np.abs(np.linalg.det(
                1 / self.covariance_matrix)))
Gregory Ashton's avatar
Gregory Ashton committed
396

397 398
    @staticmethod
    def prior_volume(priors):
Gregory Ashton's avatar
Gregory Ashton committed
399 400 401 402 403 404
        """ 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,

405 406 407
        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
408 409 410 411

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

412
    def get_one_dimensional_median_and_error_bar(self, key, fmt='.2f',
413
                                                 quantiles=(0.16, 0.84)):
414 415 416 417 418 419 420 421
        """ 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
422 423
        quantiles: list, tuple
            A length-2 tuple of the lower and upper-quantiles to calculate
424 425 426 427
            the errors bars for.

        Returns
        -------
428 429
        summary: namedtuple
            An object with attributes, median, lower, upper and string
430 431

        """
432 433
        summary = namedtuple('summary', ['median', 'lower', 'upper', 'string'])

434 435 436 437 438
        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)
439 440 441
        summary.median = quants[1]
        summary.plus = quants[2] - summary.median
        summary.minus = summary.median - quants[0]
442 443

        fmt = "{{0:{0}}}".format(fmt).format
444 445 446 447 448
        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
449 450 451
    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,
452 453
                            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
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

        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
482 483
        quantiles: tuple
            A length-2 tuple of the lower and upper-quantiles to calculate
Colm Talbot's avatar
Colm Talbot committed
484 485 486 487 488 489 490 491 492 493 494 495
            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()
496 497 498 499 500 501 502 503
        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
504 505 506 507 508 509 510 511 512 513 514 515 516
        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)
517
            ax.plot(theta, prior.prob(theta), color='C2')
Colm Talbot's avatar
Colm Talbot committed
518 519 520 521 522 523 524 525

        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)
526 527 528
            plt.close(fig)
        else:
            return fig
Colm Talbot's avatar
Colm Talbot committed
529

530 531
    def plot_marginals(self, parameters=None, priors=None, titles=True,
                       file_base_name=None, bins=50, label_fontsize=16,
532 533
                       title_fontsize=16, quantiles=(0.16, 0.84), dpi=300,
                       outdir=None):
534 535 536 537 538 539 540
        """ 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.
541
        priors: {bool (False), bilby.core.prior.PriorDict}
542
            If true, add the stored prior probability density functions to the
543
            one-dimensional marginal distributions. If instead a PriorDict
544 545 546 547 548 549 550 551 552 553 554 555
            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
556 557 558
            The font sizes for the labels and titles
        quantiles: tuple
            A length-2 tuple of the lower and upper-quantiles to calculate
559 560 561
            the errors bars for.
        dpi: int
            Dots per inch resolution of the plot
562 563
        outdir: str, optional
            Path to the outdir. Default is the one store in the result object.
564 565 566 567 568 569

        Returns
        -------
        """
        if isinstance(parameters, dict):
            plot_parameter_keys = list(parameters.keys())
Colm Talbot's avatar
Colm Talbot committed
570
            truths = parameters
571
        elif parameters is None:
Colm Talbot's avatar
Colm Talbot committed
572 573 574 575 576
            plot_parameter_keys = self.posterior.keys()
            if self.injection_parameters is None:
                truths = dict()
            else:
                truths = self.injection_parameters
577 578
        else:
            plot_parameter_keys = list(parameters)
Colm Talbot's avatar
Colm Talbot committed
579 580 581 582
            if self.injection_parameters is None:
                truths = dict()
            else:
                truths = self.injection_parameters
583 584

        if file_base_name is None:
585 586
            outdir = self._safe_outdir_creation(outdir, self.plot_marginals)
            file_base_name = '{}/{}_1d/'.format(outdir, self.label)
Colm Talbot's avatar
Colm Talbot committed
587
            check_directory_exists_and_if_not_mkdir(file_base_name)
588 589

        if priors is True:
Colm Talbot's avatar
Colm Talbot committed
590 591
            priors = getattr(self, 'priors', dict())
        elif isinstance(priors, dict):
592
            pass
Colm Talbot's avatar
Colm Talbot committed
593 594
        elif priors in [False, None]:
            priors = dict()
595 596 597 598
        else:
            raise ValueError('Input priors={} not understood'.format(priors))

        for i, key in enumerate(plot_parameter_keys):
Colm Talbot's avatar
Colm Talbot committed
599 600
            if not isinstance(self.posterior[key].values[0], float):
                continue
Colm Talbot's avatar
Colm Talbot committed
601 602
            prior = priors.get(key, None)
            truth = truths.get(key, None)
Colm Talbot's avatar
Colm Talbot committed
603
            for cumulative in [False, True]:
604
                self.plot_single_density(
Colm Talbot's avatar
Colm Talbot committed
605 606
                    key, prior=prior, cumulative=cumulative, title=titles,
                    truth=truth, save=True, file_base_name=file_base_name,
Colm Talbot's avatar
Colm Talbot committed
607 608
                    bins=bins, label_fontsize=label_fontsize, dpi=dpi,
                    title_fontsize=title_fontsize, quantiles=quantiles)
609

610 611 612
    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
613 614 615

        Parameters
        ----------
616 617 618
        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.
619
        priors: {bool (False), bilby.core.prior.PriorDict}
620
            If true, add the stored prior probability density functions to the
621
            one-dimensional marginal distributions. If instead a PriorDict
622
            is provided, this will be plotted.
623 624 625 626 627
        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.
628 629 630 631 632 633
        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
634 635 636
        **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
637 638
            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
639

640 641 642 643 644 645
        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
646 647 648 649
        Returns
        -------
        fig:
            A matplotlib figure instance
650

Gregory Ashton's avatar
Gregory Ashton committed
651
        """
652 653

        # If in testing mode, not corner plots are generated
654 655
        if utils.command_line_args.test:
            return
Gregory Ashton's avatar
Gregory Ashton committed
656

Colm Talbot's avatar
Colm Talbot committed
657
        # bilby default corner kwargs. Overwritten by anything passed to kwargs
658 659 660
        defaults_kwargs = dict(
            bins=50, smooth=0.9, label_kwargs=dict(fontsize=16),
            title_kwargs=dict(fontsize=16), color='#0072C1',
661
            truth_color='tab:orange', quantiles=[0.16, 0.84],
MoritzThomasHuebner's avatar
MoritzThomasHuebner committed
662
            levels=(1 - np.exp(-0.5), 1 - np.exp(-2), 1 - np.exp(-9 / 2.)),
663
            plot_density=False, plot_datapoints=True, fill_contours=True,
664 665 666 667 668 669
            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)
670

671 672 673 674
        if 'lionize' in kwargs and kwargs['lionize'] is True:
            defaults_kwargs['truth_color'] = 'tab:blue'
            defaults_kwargs['color'] = '#FF8C00'

675 676 677
        defaults_kwargs.update(kwargs)
        kwargs = defaults_kwargs

678 679 680 681 682 683 684 685 686 687 688 689 690 691 692
        # 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
693 694 695 696 697 698 699 700
        # 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}

701 702 703 704 705 706 707 708 709
        # 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)
710

711
        # Get latex formatted strings for the plot labels
712 713
        kwargs['labels'] = kwargs.get(
            'labels', self.get_latex_labels_from_parameter_keys(
714
                plot_parameter_keys))
715

716 717 718 719
        # 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))

720 721
        # Create the data array to plot and pass everything to corner
        xs = self.posterior[plot_parameter_keys].values
722
        fig = corner.corner(xs, **kwargs)
723
        axes = fig.get_axes()
724 725 726

        #  Add the titles
        if titles and kwargs.get('quantiles', None) is not None:
727 728
            for i, par in enumerate(plot_parameter_keys):
                ax = axes[i + i * len(plot_parameter_keys)]
729 730
                if ax.title.get_text() == '':
                    ax.set_title(self.get_one_dimensional_median_and_error_bar(
731
                        par, quantiles=kwargs['quantiles']).string,
732 733 734
                        **kwargs['title_kwargs'])

        #  Add priors to the 1D plots
735 736 737
        if priors is True:
            priors = getattr(self, 'priors', False)
        if isinstance(priors, dict):
738 739
            for i, par in enumerate(plot_parameter_keys):
                ax = axes[i + i * len(plot_parameter_keys)]
740 741
                theta = np.linspace(ax.get_xlim()[0], ax.get_xlim()[1], 300)
                ax.plot(theta, priors[par].prob(theta), color='C2')
742 743 744 745
        elif priors in [False, None]:
            pass
        else:
            raise ValueError('Input priors={} not understood'.format(priors))
746

747
        if save:
748
            if filename is None:
749 750
                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
751
            logger.debug('Saving corner plot to {}'.format(filename))
752
            fig.savefig(filename, dpi=dpi)
753
            plt.close(fig)
754

755
        return fig
756

Gregory Ashton's avatar
Gregory Ashton committed
757
    def plot_walkers(self, **kwargs):
MoritzThomasHuebner's avatar
A typo  
MoritzThomasHuebner committed
758
        """ Method to plot the trace of the walkers in an ensemble MCMC plot """
759
        if hasattr(self, 'walkers') is False:
Gregory Ashton's avatar
Gregory Ashton committed
760
            logger.warning("Cannot plot_walkers as no walkers are saved")
761
            return
762 763 764

        if utils.command_line_args.test:
            return
765 766 767

        nwalkers, nsteps, ndim = self.walkers.shape
        idxs = np.arange(nsteps)
MoritzThomasHuebner's avatar
MoritzThomasHuebner committed
768
        fig, axes = plt.subplots(nrows=ndim, figsize=(6, 3 * ndim))
769 770
        walkers = self.walkers[:, :, :]
        for i, ax in enumerate(axes):
MoritzThomasHuebner's avatar
MoritzThomasHuebner committed
771
            ax.plot(idxs[:self.nburn + 1], walkers[:, :self.nburn + 1, i].T,
772 773 774 775 776 777 778 779 780
                    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()
781 782
        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
783
        logger.debug('Saving walkers plot to {}'.format('filename'))
784
        fig.savefig(filename)
785
        plt.close(fig)
786

787 788 789
    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,
790
                       maxl_label='max likelihood', dpi=300, outdir=None):
791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815
        """ 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.
816 817
        outdir: str, optional
            Path to the outdir. Default is the one store in the result object.
818 819

        """
820 821 822 823 824 825

        # 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]

826 827 828 829
        xsmooth = np.linspace(np.min(x), np.max(x), npoints)
        fig, ax = plt.subplots()
        logger.info('Plotting {} draws'.format(ndraws))
        for _ in range(ndraws):
830
            s = model_posterior.sample().to_dict('records')[0]
831 832
            ax.plot(xsmooth, model(xsmooth, **s), alpha=0.25, lw=0.1, color='r',
                    label=draws_label)
833 834 835
        try:
            if all(~np.isnan(self.posterior.log_likelihood)):
                logger.info('Plotting maximum likelihood')
Colm Talbot's avatar
Colm Talbot committed
836
                s = model_posterior.iloc[self.posterior.log_likelihood.idxmax()]
837 838
                ax.plot(xsmooth, model(xsmooth, **s), lw=1, color='k',
                        label=maxl_label)
839
        except (AttributeError, TypeError):
840 841
            logger.debug(
                "No log likelihood values stored, unable to plot max")
842 843 844 845 846 847 848 849 850 851 852 853 854 855

        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:
856 857
            outdir = self._safe_outdir_creation(outdir, self.plot_with_data)
            filename = '{}/{}_plot_with_data'.format(outdir, self.label)
858
        fig.savefig(filename, dpi=dpi)
859
        plt.close(fig)
860

861 862
    def samples_to_posterior(self, likelihood=None, priors=None,
                             conversion_function=None):
863
        """
864 865 866
        Convert array of samples to posterior (a Pandas data frame)

        Also applies the conversion function to any stored posterior
867

868 869
        Parameters
        ----------
Colm Talbot's avatar
Colm Talbot committed
870
        likelihood: bilby.likelihood.GravitationalWaveTransient, optional
871 872
            GravitationalWaveTransient likelihood used for sampling.
        priors: dict, optional
873
            Dictionary of prior object, used to fill in delta function priors.
874
        conversion_function: function, optional
875 876
            Function which adds in extra parameters to the data frame,
            should take the data_frame, likelihood and prior as arguments.
877
        """
878 879 880
        try:
            data_frame = self.posterior
        except ValueError:
881 882
            data_frame = pd.DataFrame(
                self.samples, columns=self.search_parameter_keys)
883
            for key in priors:
884
                if isinstance(priors[key], DeltaFunction):
885
                    data_frame[key] = priors[key].peak
886 887 888 889
                elif isinstance(priors[key], float):
                    data_frame[key] = priors[key]
            data_frame['log_likelihood'] = getattr(
                self, 'log_likelihood_evaluations', np.nan)
890 891 892 893 894
            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
895
        if conversion_function is not None:
896
            data_frame = conversion_function(data_frame, likelihood, priors)
897
        self.posterior = data_frame
Gregory Ashton's avatar
Gregory Ashton committed
898

Colm Talbot's avatar
Colm Talbot committed
899
    def calculate_prior_values(self, priors):
900 901 902 903 904
        """
        Evaluate prior probability for each parameter for each sample.

        Parameters
        ----------
905
        priors: dict, PriorDict
906 907 908 909 910 911 912 913 914 915 916
            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
917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959
    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 value)

        Parameters
        ----------
        parameter: str
            Parameter to get credible level for
        Returns
        -------
        float: credible level
        """
        if self.injection_parameters is None:
            raise(TypeError, "Result object has no 'injection_parameters'. "
                             "Cannot copmute credible levels.")
        if parameter in self.posterior and\
                parameter in self.injection_parameters:
            credible_level =\
                sum(self.posterior[parameter].values <
                    self.injection_parameters[parameter]) / len(self.posterior)
            return credible_level
        else:
            return np.nan

960
    def _check_attribute_match_to_other_object(self, name, other_object):
961 962 963 964 965 966 967 968 969 970 971 972 973 974
        """ 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

        """
975 976 977 978 979 980 981 982
        a = getattr(self, name, False)
        b = getattr(other_object, name, False)
        logger.debug('Checking {} value: {}=={}'.format(name, a, b))
        if (a is not False) and (b is not False):
            type_a = type(a)
            type_b = type(b)
            if type_a == type_b:
                if type_a in [str, float, int, dict, list]:
Gregory Ashton's avatar
Gregory Ashton committed
983
                    try:
984
                        return a == b
Gregory Ashton's avatar
Gregory Ashton committed
985 986
                    except ValueError:
                        return False
987 988
                elif type_a in [np.ndarray]:
                    return np.all(a == b)
989
        return False
990

991 992 993 994 995 996
    @property
    def kde(self):
        """ Kernel density estimate built from the stored posterior

        Uses `scipy.stats.gaussian_kde` to generate the kernel density
        """
997
        if self._kde:
998
            return self._kde
999
        else:
1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028
            self._kde = scipy.stats.gaussian_kde(
                self.posterior[self.search_parameter_keys].values.T)
            return self._kde

    def posterior_probability(self, sample):
        """ Calculate the posterior probabily for a new sample

        This queries a Kernel Density Estimate of the posterior to calculate
        the posterior probability density for the new sample.

        Parameters
        ----------
        sample: dict, or list of dictionaries
            A dictionary containing all the keys from
            self.search_parameter_keys and corresponding values at which to
            calculate the posterior probability

        Returns
        -------
        p: array-like,
            The posterior probability of the sample

        """
        if isinstance(sample, dict):
            sample = [sample]
        ordered_sample = [[s[key] for key in self.search_parameter_keys]
                          for s in sample]
        return self.kde(ordered_sample)

1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040
    def _safe_outdir_creation(self, outdir=None, caller_func=None):
        if outdir is None:
            outdir = self.outdir
        try:
            utils.check_directory_exists_and_if_not_mkdir(outdir)
        except PermissionError:
            raise FileMovedError("Can not write in the out directory.\n"
                                 "Did you move the here file from another system?\n"
                                 "Try calling " + caller_func.__name__ + " with the 'outdir' "
                                 "keyword argument, e.g. " + caller_func.__name__ + "(outdir='.')")
        return outdir

1041 1042

def plot_multiple(results, filename=None, labels=None, colours=None,
1043
                  save=True, evidences=False, **kwargs):
1044 1045 1046 1047 1048
    """ Generate a corner plot overlaying two sets of results

    Parameters
    ----------
    results: list
Colm Talbot's avatar
Colm Talbot committed
1049
        A list of `bilby.core.result.Result` objects containing the samples to
1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065
        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.
1066 1067 1068
    evidences: bool, optional
        Add the log-evidence calculations to the legend. If available, the
        Bayes factor will be used instead.
1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079