Пример #1
1
def _dpmm(coords, alpha, null_density, dof, prior_precision, prior_h0,
          subjects, sampling_coords=None, n_iter=1000, burnin=100,
          co_clust=False):
    """Apply the dpmm analysis to compute clusters from regions coordinates
    """
    from nipy.algorithms.clustering.imm import MixedIMM

    dim = coords.shape[1]
    migmm = MixedIMM(alpha, dim)
    migmm.set_priors(coords)
    migmm.set_constant_densities(
        null_dens=null_density, prior_dens=null_density)
    migmm._prior_dof = dof
    migmm._prior_scale = np.diag(prior_precision[0] / dof)
    migmm._inv_prior_scale_ = [np.diag(dof * 1. / (prior_precision[0]))]
    migmm.sample(coords, null_class_proba=prior_h0, niter=burnin, init=False,
                 kfold=subjects)

    # sampling
    like, pproba, co_clustering = migmm.sample(
        coords, null_class_proba=prior_h0, niter=n_iter, kfold=subjects,
        sampling_points=sampling_coords, co_clustering=True)

    if co_clust:
        return like, 1 - pproba, co_clustering
    else:
        return like, 1 - pproba
Пример #2
0
def _dpmm(coords,
          alpha,
          null_density,
          dof,
          prior_precision,
          prior_h0,
          subjects,
          sampling_coords=None,
          n_iter=1000,
          burnin=100,
          co_clust=False):
    """Apply the dpmm analysis to compute clusters from regions coordinates
    """
    from nipy.algorithms.clustering.imm import MixedIMM

    dim = coords.shape[1]
    migmm = MixedIMM(alpha, dim)
    migmm.set_priors(coords)
    migmm.set_constant_densities(null_dens=null_density,
                                 prior_dens=null_density)
    migmm._prior_dof = dof
    migmm._prior_scale = np.diag(prior_precision[0] / dof)
    migmm._inv_prior_scale_ = [np.diag(dof * 1. / (prior_precision[0]))]
    migmm.sample(coords,
                 null_class_proba=prior_h0,
                 niter=burnin,
                 init=False,
                 kfold=subjects)

    # sampling
    like, pproba, co_clustering = migmm.sample(coords,
                                               null_class_proba=prior_h0,
                                               niter=n_iter,
                                               kfold=subjects,
                                               sampling_points=sampling_coords,
                                               co_clustering=True)

    if co_clust:
        return like, 1 - pproba, co_clustering
    else:
        return like, 1 - pproba
def dpmm(gfc, alpha, g0, g1, dof, prior_precision, gf1, sub, burnin,
         spatial_coords=None, nis=1000, co_clust=False, verbose=False):
    """Apply the dpmm analysis to compute clusters from regions coordinates
    """
    from nipy.algorithms.clustering.imm import MixedIMM

    dim = gfc.shape[1]
    migmm = MixedIMM(alpha, dim)
    migmm.set_priors(gfc)
    migmm.set_constant_densities(null_dens=g0, prior_dens=g1)
    migmm._prior_dof = dof
    migmm._prior_scale = np.diag(prior_precision[0] / dof)
    migmm._inv_prior_scale_ = [np.diag(dof * 1. / (prior_precision[0]))]
    migmm.sample(gfc, null_class_proba=1 - gf1, niter=burnin, init=False,
                 kfold=sub)
    if verbose:
        print 'number of components: ', migmm.k

    # sampling
    if co_clust:
        like, pproba, co_clust = migmm.sample(
            gfc, null_class_proba=1 - gf1, niter=nis,
            sampling_points=spatial_coords, kfold=sub, co_clustering=co_clust)
        if verbose:
            print 'number of components: ', migmm.k

        return like, 1 - pproba, co_clust
    else:
        like, pproba = migmm.sample(
            gfc, null_class_proba=1 - gf1, niter=nis,
            sampling_points=spatial_coords, kfold=sub, co_clustering=co_clust)
    if verbose:
        print 'number of components: ', migmm.k

    return like, 1 - pproba
Пример #4
0
def dpmm(gfc,
         alpha,
         g0,
         g1,
         dof,
         prior_precision,
         gf1,
         sub,
         burnin,
         spatial_coords=None,
         nis=1000,
         co_clust=False,
         verbose=False):
    """Apply the dpmm analysis to compute clusters from regions coordinates
    """
    from nipy.algorithms.clustering.imm import MixedIMM

    dim = gfc.shape[1]
    migmm = MixedIMM(alpha, dim)
    migmm.set_priors(gfc)
    migmm.set_constant_densities(null_dens=g0, prior_dens=g1)
    migmm._prior_dof = dof
    migmm._prior_scale = np.diag(prior_precision[0] / dof)
    migmm._inv_prior_scale_ = [np.diag(dof * 1. / (prior_precision[0]))]
    migmm.sample(gfc,
                 null_class_proba=1 - gf1,
                 niter=burnin,
                 init=False,
                 kfold=sub)
    if verbose:
        print 'number of components: ', migmm.k

    # sampling
    if co_clust:
        like, pproba, co_clust = migmm.sample(gfc,
                                              null_class_proba=1 - gf1,
                                              niter=nis,
                                              sampling_points=spatial_coords,
                                              kfold=sub,
                                              co_clustering=co_clust)
        if verbose:
            print 'number of components: ', migmm.k

        return like, 1 - pproba, co_clust
    else:
        like, pproba = migmm.sample(gfc,
                                    null_class_proba=1 - gf1,
                                    niter=nis,
                                    sampling_points=spatial_coords,
                                    kfold=sub,
                                    co_clustering=co_clust)
    if verbose:
        print 'number of components: ', migmm.k

    return like, 1 - pproba