Пример #1
0
def mcmc(
    data,
    start=None,
    nsamples=10000,
    nafc=2,
    sigmoid="logistic",
    core="mw0.1",
    priors=None,
    stepwidths=None,
    sampler="MetropolisHastings",
    gammaislambda=False,
):

    dataset, pmf, nparams = sfu.make_dataset_and_pmf(data, nafc, sigmoid, core, priors, gammaislambda=gammaislambda)

    if start is not None:
        start = sfu.get_start(start, nparams)
    else:
        # use mapestimate
        opt = sfr.PsiOptimizer(pmf, dataset)
        start = opt.optimize(pmf, dataset)

    proposal = sfr.GaussRandom()
    if sampler not in sfu.sampler_dict.keys():
        raise sfu.PsignifitException("The sampler: " + sampler + " is not available.")
    else:
        sampler = sfu.sampler_dict[sampler](pmf, dataset, proposal)
    sampler.setTheta(start)

    if stepwidths != None:
        stepwidths = np.array(stepwidths)
        if len(stepwidths.shape) == 2:
            if isinstance(sampler, sfr.GenericMetropolis):
                sampler.findOptimalStepwidth(sfu.make_pilotsample(stepwidths))
            elif isinstance(sampler, sfr.MetropolisHastings):
                sampler.setStepSize(sfr.vector_double(stepwidths.std(0)))
            else:
                raise sfu.PsignifitException(
                    "You provided a pilot sample but the selected sampler does not support pilot samples"
                )
        elif len(stepwidths) != nparams:
            raise sfu.PsignifitException(
                "You specified '"
                + str(len(stepwidths))
                + "' stepwidth(s), but there are '"
                + str(nparams)
                + "' parameters."
            )
        else:
            if isinstance(sampler, sfr.DefaultMCMC):
                for i, p in enumerate(stepwidths):
                    p = sfu.get_prior(p)
                    sampler.set_proposal(i, p)
            else:
                sampler.setStepSize(sfr.vector_double(stepwidths))

    post = sampler.sample(nsamples)

    nblocks = dataset.getNblocks()

    estimates = np.zeros((nsamples, nparams))
    deviance = np.zeros(nsamples)
    posterior_predictive_data = np.zeros((nsamples, nblocks))
    posterior_predictive_deviances = np.zeros(nsamples)
    posterior_predictive_Rpd = np.zeros(nsamples)
    posterior_predictive_Rkd = np.zeros(nsamples)
    logposterior_ratios = np.zeros((nsamples, nblocks))

    for i in xrange(nsamples):
        for j in xrange(nparams):
            estimates[i, j] = post.getEst(i, j)
        deviance[i] = post.getdeviance(i)
        for j in xrange(nblocks):
            posterior_predictive_data[i, j] = post.getppData(i, j)
            logposterior_ratios[i, j] = post.getlogratio(i, j)
        posterior_predictive_deviances[i] = post.getppDeviance(i)
        posterior_predictive_Rpd[i] = post.getppRpd(i)
        posterior_predictive_Rkd[i] = post.getppRkd(i)

    accept_rate = post.get_accept_rate()

    return (
        estimates,
        deviance,
        posterior_predictive_data,
        posterior_predictive_deviances,
        posterior_predictive_Rpd,
        posterior_predictive_Rkd,
        logposterior_ratios,
        accept_rate,
    )
Пример #2
0
def mcmc(data,
         start=None,
         nsamples=10000,
         nafc=2,
         sigmoid='logistic',
         core='mw0.1',
         priors=None,
         stepwidths=None,
         sampler="MetropolisHastings",
         gammaislambda=False):
    """ Markov Chain Monte Carlo sampling for a psychometric function.

    Parameters
    ----------

    data : A list of lists or an array of data.
        The first column should be stimulus intensity, the second column should
        be number of correct responses (in 2AFC) or number of yes- responses (in
        Yes/No), the third column should be number of trials. See also: the examples
        section below.

    start : sequence of floats of length number of model parameters
        Starting values for the markov chain. If this is None, the MAP estimate
        will be used.

    nsamples : int
        Number of samples to be taken from the posterior (note that due to
        suboptimal sampling, this number may be much lower than the effective
        number of samples.

    nafc : int
        Number of responses alternatives for nAFC tasks. If nafc==1 a Yes/No task is
        assumed.

    sigmoid : string
        Name of the sigmoid to be fitted. Valid sigmoids include:
                logistic
                gauss
                gumbel_l
                gumbel_r
        See `swignifit.utility.available_sigmoids()` for all available sigmoids.

    core : string
        \"core\"-type of the psychometric function. Valid choices include:
                ab       (x-a)/b
                mw%g     midpoint and width
                linear   a+bx
                log      a+b log(x)
        See `swignifit.utility.available_cores()` for all available sigmoids.

    priors : sequence of strings length number of parameters
        Prior distributions on the parameters of the psychometric function.
        These are expressed in the form of a list of prior names.
        Valid prior choices include:
                Uniform(%g,%g)
                Gauss(%g,%g)
                Beta(%g,%g)
                Gamma(%g,%g)
                nGamma(%g,%g)
                if an invalid prior or `None` is selected, no constraints are imposed at all.
        See `swignifit.utility.available_priors()` for all available sigmoids.

        if an invalid prior is selected, no constraints are imposed on that
        parameter resulting in an improper prior distribution.

    stepwidths : sequence of floats of length number of model parameters
        Standard deviations of the proposal distribution. The best choice is
        sometimes a bit tricky here. However, as a rule of thumb we can
        state: if the stepwidths are too small, the samples might not cover
        the whole posterior, if the stepwidths are too large, most steps
        will leave the area of high posterior density and will therefore be
        rejected.  Thus, in general stepwidths should be somewhere in the
        middle.

    sampler : string
        The type of MCMC sampler to use.
        See: `sw.utility.available_samplers()` for a list of available samplers.

    gammaislambda : boolean
        Set the gamma == lambda prior.


    Output
    ------

    (estimates, deviance, posterior_predictive_data,
    posterior_predictive_deviances, posterior_predictive_Rpd,
    posterior_predictive_Rkd, logposterior_ratios, accept_rate)

    estimates : numpy array, shape: (nsamples, nparameters)
        Parameters sampled from the posterior density of parameters given the data.

    deviances : numpy array, length: nsamples
        Associated deviances for each estimate

    posterior_predictive_data : numpy array, shape: (nsamples, nblocks)
        Data that are simulated by sampling from the joint posterior of data and
        parameters. They are important for model checking.

    posterior_predictive_deviances : numpy array, length: nsamples
        The deviances that are associated with the posterior predictive data. A
        particular way of model checking could be to compare the deviances and the
        posterior predicitive deviances. For a good model these should be relatively
        similar.

    posterior_predictive_Rpd : numpy array, length: nsamples
        Correlations between psychometric function and deviance residuals
        associated with posterior predictive data

    posterior_predictive_Rkd : numpy array, length: nsamples
        Correlations between block index and deviance residuals associated with
        posterior predictive data.

    logposterior_ratios :  numpy array, shape: (nsamples, nblocks)
        Ratios between the full posetrior and the posterior for a single block
        for all samples. Used for calculating the KL-Divergence to detrmine
        influential observations in the Bayesian paradigm.

    accept_rate : float
        The number of proposed MCMC samples that were accepted.

    Example
    -------
    >>> x = [float(2*k) for k in xrange(6)]
    >>> k = [34,32,40,48,50,48]
    >>> n = [50]*6
    >>> d = [[xx,kk,nn] for xx,kk,nn in zip(x,k,n)]
    >>> priors = ('Gauss(0,1000)','Gauss(0,1000)','Beta(3,100)')
    >>> stepwidths = (1.,1.,0.01)
    >>> (estimates, deviance, posterior_predictive_data,
         posterior_predictive_deviances, posterior_predictive_Rpd,
         posterior_predictive_Rkd, logposterior_ratios, accept_rate) \
         = mcmc(d,nsamples=10000,priors=priors,stepwidths=stepwidths)
    >>> mean(estimates[:,0])
    2.4811791550665272
    >>> mean(estimates[:,1])
    7.4935217545849184
    """

    dataset, pmf, nparams = sfu.make_dataset_and_pmf(
        data, nafc, sigmoid, core, priors, gammaislambda=gammaislambda)

    if start is not None:
        start = sfu.get_start(start, nparams)
    else:
        # use mapestimate
        opt = sfr.PsiOptimizer(pmf, dataset)
        start = opt.optimize(pmf, dataset)

    proposal = sfr.GaussRandom()
    if sampler not in sfu.sampler_dict.keys():
        raise sfu.PsignifitException("The sampler: " + sampler +
                                     " is not available.")
    else:
        sampler = sfu.sampler_dict[sampler](pmf, dataset, proposal)
    sampler.setTheta(start)

    if stepwidths != None:
        stepwidths = np.array(stepwidths)
        if len(stepwidths.shape) == 2:
            if isinstance(sampler, sfr.GenericMetropolis):
                sampler.findOptimalStepwidth(sfu.make_pilotsample(stepwidths))
            elif isinstance(sampler, sfr.MetropolisHastings):
                sampler.setStepSize(sfr.vector_double(stepwidths.std(0)))
            else:
                raise sfu.PsignifitException(
                    "You provided a pilot sample but the selected sampler does not support pilot samples"
                )
        elif len(stepwidths) != nparams:
            raise sfu.PsignifitException("You specified \'"+str(len(stepwidths))+\
                    "\' stepwidth(s), but there are \'"+str(nparams)+ "\' parameters.")
        else:
            if isinstance(sampler, sfr.DefaultMCMC):
                for i, p in enumerate(stepwidths):
                    p = sfu.get_prior(p)
                    sampler.set_proposal(i, p)
            else:
                sampler.setStepSize(sfr.vector_double(stepwidths))

    post = sampler.sample(nsamples)

    nblocks = dataset.getNblocks()

    estimates = np.zeros((nsamples, nparams))
    deviance = np.zeros(nsamples)
    posterior_predictive_data = np.zeros((nsamples, nblocks))
    posterior_predictive_deviances = np.zeros(nsamples)
    posterior_predictive_Rpd = np.zeros(nsamples)
    posterior_predictive_Rkd = np.zeros(nsamples)
    logposterior_ratios = np.zeros((nsamples, nblocks))

    for i in xrange(nsamples):
        for j in xrange(nparams):
            estimates[i, j] = post.getEst(i, j)
        deviance[i] = post.getdeviance(i)
        for j in xrange(nblocks):
            posterior_predictive_data[i, j] = post.getppData(i, j)
            logposterior_ratios[i, j] = post.getlogratio(i, j)
        posterior_predictive_deviances[i] = post.getppDeviance(i)
        posterior_predictive_Rpd[i] = post.getppRpd(i)
        posterior_predictive_Rkd[i] = post.getppRkd(i)

    accept_rate = post.get_accept_rate()

    return (estimates, deviance, posterior_predictive_data,
            posterior_predictive_deviances, posterior_predictive_Rpd,
            posterior_predictive_Rkd, logposterior_ratios, accept_rate)
Пример #3
0
def mcmc( data, start=None, nsamples=10000, nafc=2, sigmoid='logistic',
        core='mw0.1', priors=None, stepwidths=None, sampler="MetropolisHastings", gammaislambda=False):
    """ Markov Chain Monte Carlo sampling for a psychometric function.

    Parameters
    ----------

    data : A list of lists or an array of data.
        The first column should be stimulus intensity, the second column should
        be number of correct responses (in 2AFC) or number of yes- responses (in
        Yes/No), the third column should be number of trials. See also: the examples
        section below.

    start : sequence of floats of length number of model parameters
        Starting values for the markov chain. If this is None, the MAP estimate
        will be used.

    nsamples : int
        Number of samples to be taken from the posterior (note that due to
        suboptimal sampling, this number may be much lower than the effective
        number of samples.

    nafc : int
        Number of responses alternatives for nAFC tasks. If nafc==1 a Yes/No task is
        assumed.

    sigmoid : string
        Name of the sigmoid to be fitted. Valid sigmoids include:
                logistic    (1+exp(-x))**-1 [Default]
                gauss       Phi(x)
                gumbel_l    1 - exp(-exp(x))
                gumbel_r    exp(-exp(-x))
                exponential x>0: 1 - exp(-x); else: 0
                cauchy      atan(x)/pi + 0.5
                id          x; only useful in conjunction with NakaRushton core
        See `swignifit.utility.available_sigmoids()` for all available sigmoids.

    core : string
        \"core\"-type of the psychometric function. Valid choices include:
                ab          (x-a)/b [Default]
                mw%g        midpoint and width, with "%g" a number larger than 0 and less than 0.5. 
                            mw%g corresponds to a parameterization in terms of midpoint and width of
                            the rising part of the sigmoid. This width is defined as the length of the
                            interval on which the sigmoidal part reaches from "%g" to 1-"%g".
                linear      a+b*x
                log         a+b*log(x)
                weibull     2*s*m*(log(x)-log(m))/log(2) + log(log(2)) 
                            This will give you a weibull if combined with the gumbel_l sigmoid and a
                            reverse weibull if combined with the gumbel_r sigmoid.
                poly        (x/a)**b   Will give you a weibull if combined with an exp sigmoid
                NakaRushton The Naka-Rushton nonlinearity; should only be used with an id core
        See `swignifit.utility.available_cores()` for all available cores.

    priors : sequence of strings length number of parameters
        Prior distributions on the parameters of the psychometric function.
        These are expressed in the form of a list of prior names.
        Valid prior choices include:
                Uniform(%g,%g)   Uniform distribution on an interval
                Gauss(%g,%g)     Gaussian distribution with mean and standard deviation
                Beta(%g,%g)      Beta distribution
                Gamma(%g,%g)     Gamma distribution
                nGamma(%g,%g)    Gamma distribution on the negative axis
                invGamma(%g,%g)  inverse Gamma distribution
                ninvGamma(%g,%g) inverse Gamma distribution on the negative axis
                if an invalid prior or `None` is selected, no constraints are imposed at all.
        See `swignifit.utility.available_priors()` for all available sigmoids.

        if an invalid prior is selected, no constraints are imposed on that
        parameter resulting in an improper prior distribution.

    stepwidths : sequence of floats of length number of model parameters
        Standard deviations of the proposal distribution. The best choice is
        sometimes a bit tricky here. However, as a rule of thumb we can
        state: if the stepwidths are too small, the samples might not cover
        the whole posterior, if the stepwidths are too large, most steps
        will leave the area of high posterior density and will therefore be
        rejected.  Thus, in general stepwidths should be somewhere in the
        middle.

    sampler : string
        The type of MCMC sampler to use.
        See: `sw.utility.available_samplers()` for a list of available samplers.

    gammaislambda : boolean
        Set the gamma == lambda prior.


    Output
    ------

    (estimates, deviance, posterior_predictive_data,
    posterior_predictive_deviances, posterior_predictive_Rpd,
    posterior_predictive_Rkd, logposterior_ratios, accept_rate)

    estimates : numpy array, shape: (nsamples, nparameters)
        Parameters sampled from the posterior density of parameters given the data.

    deviances : numpy array, length: nsamples
        Associated deviances for each estimate

    posterior_predictive_data : numpy array, shape: (nsamples, nblocks)
        Data that are simulated by sampling from the joint posterior of data and
        parameters. They are important for model checking.

    posterior_predictive_deviances : numpy array, length: nsamples
        The deviances that are associated with the posterior predictive data. A
        particular way of model checking could be to compare the deviances and the
        posterior predicitive deviances. For a good model these should be relatively
        similar.

    posterior_predictive_Rpd : numpy array, length: nsamples
        Correlations between psychometric function and deviance residuals
        associated with posterior predictive data

    posterior_predictive_Rkd : numpy array, length: nsamples
        Correlations between block index and deviance residuals associated with
        posterior predictive data.

    logposterior_ratios :  numpy array, shape: (nsamples, nblocks)
        Ratios between the full posetrior and the posterior for a single block
        for all samples. Used for calculating the KL-Divergence to detrmine
        influential observations in the Bayesian paradigm.

    accept_rate : float
        The number of proposed MCMC samples that were accepted.

    Example
    -------
    >>> x = [float(2*k) for k in xrange(6)]
    >>> k = [34,32,40,48,50,48]
    >>> n = [50]*6
    >>> d = [[xx,kk,nn] for xx,kk,nn in zip(x,k,n)]
    >>> priors = ('Gauss(0,1000)','Gauss(0,1000)','Beta(3,100)')
    >>> stepwidths = (1.,1.,0.01)
    >>> (estimates, deviance, posterior_predictive_data,
         posterior_predictive_deviances, posterior_predictive_Rpd,
         posterior_predictive_Rkd, logposterior_ratios, accept_rate) \
         = mcmc(d,nsamples=10000,priors=priors,stepwidths=stepwidths)
    >>> mean(estimates[:,0])
    2.4811791550665272
    >>> mean(estimates[:,1])
    7.4935217545849184
    """

    dataset, pmf, nparams = sfu.make_dataset_and_pmf(data, nafc, sigmoid, core, priors, gammaislambda=gammaislambda)

    if start is not None:
        start = sfu.get_start(start, nparams)
    else:
        # use mapestimate
        opt = sfr.PsiOptimizer(pmf, dataset)
        start = opt.optimize(pmf, dataset)

    proposal = sfr.GaussRandom()
    if sampler not in sfu.sampler_dict.keys():
        raise sfu.PsignifitException("The sampler: " + sampler + " is not available.")
    else:
        sampler  = sfu.sampler_dict[sampler](pmf, dataset, proposal)
    sampler.setTheta(start)

    if stepwidths != None:
        stepwidths = np.array(stepwidths)
        if len(stepwidths.shape)==2:
            if isinstance ( sampler, sfr.GenericMetropolis ):
                sampler.findOptimalStepwidth ( sfu.make_pilotsample ( stepwidths ) )
            elif isinstance ( sampler, sfr.MetropolisHastings ):
                sampler.setStepSize ( sfr.vector_double( stepwidths.std(0) ) )
            else:
                raise sfu.PsignifitException("You provided a pilot sample but the selected sampler does not support pilot samples")
        elif len(stepwidths) != nparams:
            raise sfu.PsignifitException("You specified \'"+str(len(stepwidths))+\
                    "\' stepwidth(s), but there are \'"+str(nparams)+ "\' parameters.")
        else:
            if isinstance ( sampler, sfr.DefaultMCMC ):
                for i,p in enumerate(stepwidths):
                    p = sfu.get_prior(p)
                    sampler.set_proposal(i, p)
            else:
                sampler.setStepSize(sfr.vector_double(stepwidths))

    post = sampler.sample(nsamples)

    nblocks = dataset.getNblocks()

    estimates = np.zeros((nsamples, nparams))
    deviance = np.zeros(nsamples)
    posterior_predictive_data = np.zeros((nsamples, nblocks))
    posterior_predictive_deviances = np.zeros(nsamples)
    posterior_predictive_Rpd = np.zeros(nsamples)
    posterior_predictive_Rkd = np.zeros(nsamples)
    logposterior_ratios = np.zeros((nsamples, nblocks))

    for i in xrange(nsamples):
        for j in xrange(nparams):
            estimates[i, j] = post.getEst(i, j)
        deviance[i] = post.getdeviance(i)
        for j in xrange(nblocks):
            posterior_predictive_data[i, j] = post.getppData(i, j)
            logposterior_ratios[i,j] = post.getlogratio(i,j)
        posterior_predictive_deviances[i] = post.getppDeviance(i)
        posterior_predictive_Rpd[i] = post.getppRpd(i)
        posterior_predictive_Rkd[i] = post.getppRkd(i)

    accept_rate = post.get_accept_rate()

    return (estimates, deviance, posterior_predictive_data,
        posterior_predictive_deviances, posterior_predictive_Rpd,
        posterior_predictive_Rkd, logposterior_ratios, accept_rate)