CUQIpy 1.0.0.post0.dev352__py3-none-any.whl → 1.0.0.post0.dev371__py3-none-any.whl

{CUQIpy-1.0.0.post0.dev352.dist-info → CUQIpy-1.0.0.post0.dev371.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: CUQIpy
-Version: 1.0.0.post0.dev352
+Version: 1.0.0.post0.dev371
 Summary: Computational Uncertainty Quantification for Inverse problems in Python
 Maintainer-email: "Nicolai A. B. Riis" <nabr@dtu.dk>, "Jakob S. Jørgensen" <jakj@dtu.dk>, "Amal M. Alghamdi" <amaal@dtu.dk>, Chao Zhang <chaz@dtu.dk>
 License: Apache License

{CUQIpy-1.0.0.post0.dev352.dist-info → CUQIpy-1.0.0.post0.dev371.dist-info}/RECORD

@@ -1,6 +1,6 @@
 cuqi/__init__.py,sha256=LsGilhl-hBLEn6Glt8S_l0OJzAA1sKit_rui8h-D-p0,488
 cuqi/_messages.py,sha256=fzEBrZT2kbmfecBBPm7spVu7yHdxGARQB4QzXhJbCJ0,415
-cuqi/_version.py,sha256=g8tnztVUpVATX40RuxhlLPkPxb_ZLhy-dHUYqyHVXs8,510
+cuqi/_version.py,sha256=QVI79ROoiVftKzZNgtINBJapDUzlYy57knasEqfGVuQ,510
 cuqi/config.py,sha256=wcYvz19wkeKW2EKCGIKJiTpWt5kdaxyt4imyRkvtTRA,526
 cuqi/diagnostics.py,sha256=5OrbJeqpynqRXOe5MtOKKhe7EAVdOEpHIqHnlMW9G_c,3029
 cuqi/array/__init__.py,sha256=-EeiaiWGNsE3twRS4dD814BIlfxEsNkTCZUc5gjOXb0,30
@@ -33,24 +33,26 @@ cuqi/distribution/_normal.py,sha256=UeoTtGDT7YSf4ZNo2amlVF9K-YQpYbf8q76jcRJTVFw,
 cuqi/distribution/_posterior.py,sha256=zAfL0GECxekZ2lBt1W6_LN0U_xskMwK4VNce5xAF7ig,5018
 cuqi/distribution/_uniform.py,sha256=7xJmCZH_LPhuGkwEDGh-_CTtzcWKrXMOxtTJUFb7Ydo,1607
 cuqi/experimental/__init__.py,sha256=vhZvyMX6rl8Y0haqCzGLPz6PSUKyu75XMQbeDHqTTrw,83
-cuqi/experimental/mcmc/__init__.py,sha256=TyN_CASRnTcUBQYxoYUeSUBhorLzVwgPQaY72-6hXm8,537
+cuqi/experimental/mcmc/__init__.py,sha256=0Vk_MzfE_9tvqQRgR6_3nkjSe_D3vgFqVM9pFrXN2iQ,581
 cuqi/experimental/mcmc/_conjugate.py,sha256=qYrBvZ9wNK4oBz0c0RRUtQkbpPIHI3BvBYSLRw8ok5k,3757
 cuqi/experimental/mcmc/_conjugate_approx.py,sha256=JQe9gmnNespCxSP6vaZWfizFvUWUh8Jn-jRqsJYyNeM,2839
-cuqi/experimental/mcmc/_cwmh.py,sha256=dbvmy6Fyr_xszbO3YmYcRsDaRRtQfPimLo6rbp0II6M,6898
+cuqi/experimental/mcmc/_cwmh.py,sha256=-TM_S_UtD5ljEfXGEUpYImxNx3JXppIKTSpoWen7kP8,7142
 cuqi/experimental/mcmc/_direct.py,sha256=E3UevdJ_DLk2wL0lid1TTKkdmgnIMJ5Ihr7iM1jU8KI,738
 cuqi/experimental/mcmc/_gibbs.py,sha256=z6YOCiBM1YuZbQHfdmsArR-pT61dsS14F_O4kUxsNYM,10638
 cuqi/experimental/mcmc/_hmc.py,sha256=0sZMHtnNFGGtQdzpx-cgqA0xyfvGy7r4K62RH3AQNa4,19285
 cuqi/experimental/mcmc/_langevin_algorithm.py,sha256=n6WRQooKuUDjmqF-CtpcSNFDvaHCgLKhWxX-hi7h_ZA,8224
 cuqi/experimental/mcmc/_laplace_approximation.py,sha256=VVLOKQWZViT1CZg5RDiycG6trpKdQg94aQCKrAdSl2g,5707
-cuqi/experimental/mcmc/_mh.py,sha256=6yQjdpx3fMKvescRFL94Ik-ALTKi0BwBRXbTsIsck-I,2630
+cuqi/experimental/mcmc/_mh.py,sha256=r1RNQLuOaT_WlHvCwS2StsgNAOeTD36z2fOzUtbGhHk,2842
 cuqi/experimental/mcmc/_pcn.py,sha256=T4T32mfoii3k6Jfz0qxPQbwdh6wdVOxttiEP7NWaZzg,3386
 cuqi/experimental/mcmc/_rto.py,sha256=wzlqm8waT6mB-3RFtMz-PlSUa1Yy3dfUoyKKahTaey4,10086
 cuqi/experimental/mcmc/_sampler.py,sha256=4dh9XVALkD3Ro9vkLZkNoFNge7Xv8QRbjh4LB7NY0HI,20073
+cuqi/experimental/mcmc/_utilities.py,sha256=qrSq8hvK_G2rSxYYfR5psk4sbTe7098TS5QNu13THeE,528
 cuqi/geometry/__init__.py,sha256=Tz1WGzZBY-QGH3c0GiyKm9XHN8MGGcnU6TUHLZkzB3o,842
 cuqi/geometry/_geometry.py,sha256=WYFC-4_VBTW73b2ldsnfGYKvdSiCE8plr89xTSmkadg,46804
-cuqi/implicitprior/__init__.py,sha256=ZRZ9fgxgEl5n0A9F7WCl1_jid-GUiC8ZLkyTmGQmFlY,100
-cuqi/implicitprior/_regularizedGMRF.py,sha256=FHPA8ufqqg4ANafOi-Oq8Iv2Ikwytb2V023fXmmo_44,3092
-cuqi/implicitprior/_regularizedGaussian.py,sha256=eWF1E7YuJbNfczUIMrrwP2EtIoL0ZZTb8KY7l4oDrzU,9009
+cuqi/implicitprior/__init__.py,sha256=CaDQGYtmeFzN37vf3QUmKhcN9-H5lO66ZbK035k4qUw,246
+cuqi/implicitprior/_regularizedGMRF.py,sha256=IR9tKzNMoz-b0RKu6ahVgMx_lDNB3jZHVWFMQm6QqZk,6259
+cuqi/implicitprior/_regularizedGaussian.py,sha256=cQtrgzyJU2pwoK4ORGl1erKLE9VY5NqwZTiqiViDswA,12371
+cuqi/implicitprior/_regularizedUnboundedUniform.py,sha256=H2fTOSqYTlDiLxQ7Ya6wnpCUIkpO4qKrkTOsOPnBBeU,3483
 cuqi/likelihood/__init__.py,sha256=QXif382iwZ5bT3ZUqmMs_n70JVbbjxbqMrlQYbMn4Zo,1776
 cuqi/likelihood/_likelihood.py,sha256=z3AXAbIrv_DjOYh4jy3iDHemuIFUUJu6wdvJ5e2dgW0,6913
 cuqi/model/__init__.py,sha256=IcN4aZCnyp9o-8TNIoZ8vew99QQgi0EmZvnsIuR6qYI,49
@@ -82,8 +84,8 @@ cuqi/testproblem/_testproblem.py,sha256=x769LwwRdJdzIiZkcQUGb_5-vynNTNALXWKato7s
 cuqi/utilities/__init__.py,sha256=T4tLsC215MknBCsw_C0Qeeg_ox26aDUrCA5hbWvNQkU,387
 cuqi/utilities/_get_python_variable_name.py,sha256=QwlBVj2koJRA8s8pWd554p7-ElcI7HUwY32HknaR92E,1827
 cuqi/utilities/_utilities.py,sha256=MWAqV6L5btMpWwlUzrZYuV2VeSpfTbOaLRMRkuw2WIA,8509
-CUQIpy-1.0.0.post0.dev352.dist-info/LICENSE,sha256=kJWRPrtRoQoZGXyyvu50Uc91X6_0XRaVfT0YZssicys,10799
-CUQIpy-1.0.0.post0.dev352.dist-info/METADATA,sha256=NfPWIJpaMKeytArVU0GZCtQnlf87FNbAQkiOIdmA_ik,18393
-CUQIpy-1.0.0.post0.dev352.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
-CUQIpy-1.0.0.post0.dev352.dist-info/top_level.txt,sha256=AgmgMc6TKfPPqbjV0kvAoCBN334i_Lwwojc7HE3ZwD0,5
-CUQIpy-1.0.0.post0.dev352.dist-info/RECORD,,
+CUQIpy-1.0.0.post0.dev371.dist-info/LICENSE,sha256=kJWRPrtRoQoZGXyyvu50Uc91X6_0XRaVfT0YZssicys,10799
+CUQIpy-1.0.0.post0.dev371.dist-info/METADATA,sha256=yXm_fUldjf8brl4nsQdu_nKbDch7lVGioYPdKZ7TFMA,18393
+CUQIpy-1.0.0.post0.dev371.dist-info/WHEEL,sha256=y4mX-SOX4fYIkonsAGA5N0Oy-8_gI4FXw5HNI1xqvWg,91
+CUQIpy-1.0.0.post0.dev371.dist-info/top_level.txt,sha256=AgmgMc6TKfPPqbjV0kvAoCBN334i_Lwwojc7HE3ZwD0,5
+CUQIpy-1.0.0.post0.dev371.dist-info/RECORD,,

{CUQIpy-1.0.0.post0.dev352.dist-info → CUQIpy-1.0.0.post0.dev371.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: bdist_wheel (0.43.0)
+Generator: setuptools (70.2.0)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

cuqi/_version.py

@@ -8,11 +8,11 @@ import json
 
 version_json = '''
 {
- "date": "2024-06-19T09:05:37+0200",
+ "date": "2024-07-05T10:04:17+0300",
  "dirty": false,
  "error": null,
- "full-revisionid": "1e1deddbe7925206fdaef6a2d9bf8ce9e33ad73d",
- "version": "1.0.0.post0.dev352"
+ "full-revisionid": "62f642d707e561a7c9deb0006625b11866043b81",
+ "version": "1.0.0.post0.dev371"
 }
 '''  # END VERSION_JSON
 

cuqi/experimental/mcmc/__init__.py

@@ -12,3 +12,4 @@ from ._gibbs import HybridGibbsNew
 from ._conjugate import ConjugateNew
 from ._conjugate_approx import ConjugateApproxNew
 from ._direct import DirectNew
+from ._utilities import find_valid_samplers

cuqi/experimental/mcmc/_cwmh.py

@@ -100,6 +100,9 @@ class CWMHNew(ProposalBasedSamplerNew):
             raise ValueError(
                 "Target should be an instance of "+\
                 f"{cuqi.density.Density.__class__.__name__}")
+        # Fail when there is no log density, which is currently assumed to be the case in case NaN is returned.
+        if np.isnan(self.target.logd(self._default_initial_point)):
+            raise ValueError("Target does not have valid logd")
         
     def validate_proposal(self):
         if not isinstance(self.proposal, cuqi.distribution.Distribution):

cuqi/experimental/mcmc/_mh.py

@@ -32,7 +32,9 @@ class MHNew(ProposalBasedSamplerNew):
         self._scale_temp = self.scale
 
     def validate_target(self):
-        pass # All targets are valid
+        # Fail only when there is no log density, which is currently assumed to be the case in case NaN is returned.
+        if np.isnan(self.target.logd(self._default_initial_point)):
+            raise ValueError("Target does not have valid logd")
 
     def validate_proposal(self):
         if not isinstance(self.proposal, cuqi.distribution.Distribution):

cuqi/experimental/mcmc/_utilities.py

@@ -0,0 +1,17 @@
+import cuqi
+import inspect
+
+def find_valid_samplers(target):
+    """ Finds all samplers in the cuqi.experimental.mcmc module that accept the provided target. """
+
+    all_samplers = [(name, cls) for name, cls in inspect.getmembers(cuqi.experimental.mcmc, inspect.isclass) if issubclass(cls, cuqi.experimental.mcmc.SamplerNew)]
+    valid_samplers = []
+
+    for name, sampler in all_samplers:
+        try:
+            sampler(target)
+            valid_samplers += [name]
+        except:
+            pass
+
+    return valid_samplers

cuqi/implicitprior/__init__.py

@@ -1,2 +1,3 @@
-from ._regularizedGaussian import RegularizedGaussian
-from ._regularizedGMRF import RegularizedGMRF
+from ._regularizedGaussian import RegularizedGaussian, ConstrainedGaussian, NonnegativeGaussian
+from ._regularizedGMRF import RegularizedGMRF, ConstrainedGMRF, NonnegativeGMRF
+from ._regularizedUnboundedUniform import RegularizedUnboundedUniform

cuqi/implicitprior/_regularizedGMRF.py

@@ -68,3 +68,85 @@ class RegularizedGMRF(RegularizedGaussian):
             super(Distribution, self).__init__(**kwargs)
 
             self._parse_regularization_input_arguments(proximal, projector, constraint, regularization, args)
+
+
+
+class ConstrainedGMRF(RegularizedGMRF):
+    """ Implicit Constrained GMRF (Gaussian Markov Random Field). 
+
+    Defines a so-called implicit prior based on a GMRF distribution with implicit constraints.
+    The constraint can be defined as a preset or in the form of a projector. 
+
+    Precisely one of projector or constraint needs to be provided. Otherwise, an error is raised.
+
+    Can be used as a prior in a posterior which can be sampled with the RegularizedLinearRTO sampler.
+
+    Alias for :class:`~cuqi.implicitprior.RegularizedGMRF` with only constraints available.
+
+    For more details on implicit regularized Gaussian see the following paper:
+
+    [1] Everink, Jasper M., Yiqiu Dong, and Martin S. Andersen. "Sparse Bayesian inference with regularized
+    Gaussian distributions." Inverse Problems 39.11 (2023): 115004.
+
+    Parameters
+    ----------
+    mean
+        See :class:`~cuqi.distribution.GMRF` for details.
+        
+    prec
+        See :class:`~cuqi.distribution.GMRF` for details.
+
+    bc_type
+        See :class:`~cuqi.distribution.GMRF` for details.
+
+    order
+        See :class:`~cuqi.distribution.GMRF` for details.
+
+    projector : callable f(x) or None
+        Euclidean projection onto the constraint C, that is, a solver for the optimization problem
+        min_(z in C) 0.5||x-z||_2^2.
+
+    constraint : string or None
+        Preset constraints. Can be set to "nonnegativity" and "box". Required for use in Gibbs.
+        For "box", the following additional parameters can be passed:
+            lower_bound : array_like or None
+                Lower bound of box, defaults to zero
+            upper_bound : array_like
+                Upper bound of box, defaults to one
+
+    """
+    def __init__(self, mean=None, prec=None, bc_type='zero', order=1, projector=None, constraint=None, **kwargs):
+        super().__init__(mean=mean, prec=prec, bc_type=bc_type, order=order, projector=projector, constraint=constraint, **kwargs)
+
+        
+class NonnegativeGMRF(RegularizedGMRF):
+    """ Implicit Nonnegative GMRF (Gaussian Markov Random Field). 
+
+    Defines a so-called implicit prior based on a GMRF distribution with implicit nonnegativity constraints.
+
+    Can be used as a prior in a posterior which can be sampled with the RegularizedLinearRTO sampler.
+
+    Alias for :class:`~cuqi.implicitprior.RegularizedGMRF` with only nonnegativity constraints.
+
+    For more details on implicit regularized Gaussian see the following paper:
+
+    [1] Everink, Jasper M., Yiqiu Dong, and Martin S. Andersen. "Sparse Bayesian inference with regularized
+    Gaussian distributions." Inverse Problems 39.11 (2023): 115004.
+
+    Parameters
+    ----------
+    mean
+        See :class:`~cuqi.distribution.GMRF` for details.
+        
+    prec
+        See :class:`~cuqi.distribution.GMRF` for details.
+
+    bc_type
+        See :class:`~cuqi.distribution.GMRF` for details.
+
+    order
+        See :class:`~cuqi.distribution.GMRF` for details.
+
+    """
+    def __init__(self, mean=None, prec=None, bc_type='zero', order=1, **kwargs):
+        super().__init__(mean=mean, prec=prec, bc_type=bc_type, order=order, constraint="nonnegativity", **kwargs)

cuqi/implicitprior/_regularizedGaussian.py

@@ -234,3 +234,90 @@ class RegularizedGaussian(Distribution):
             new_density = new_density.to_likelihood(value)
 
         return new_density
+
+
+class ConstrainedGaussian(RegularizedGaussian):
+    """ Implicit Constrained Gaussian.
+
+    Defines a so-called implicit prior based on a Gaussian distribution with implicit constraints.
+    The constraint can be defined as a preset or in the form of a projector. 
+
+    Precisely one of projector or constraint needs to be provided. Otherwise, an error is raised.
+
+    Can be used as a prior in a posterior which can be sampled with the RegularizedLinearRTO sampler.
+
+    Alias for :class:`~cuqi.implicitprior.RegularizedGaussian` with only constraints available.
+
+    For more details on implicit regularized Gaussian see the following paper:
+
+    [1] Everink, Jasper M., Yiqiu Dong, and Martin S. Andersen. "Sparse Bayesian inference with regularized
+    Gaussian distributions." Inverse Problems 39.11 (2023): 115004.
+
+    Parameters
+    ----------
+    mean
+        See :class:`~cuqi.distribution.Gaussian` for details.
+
+    cov
+        See :class:`~cuqi.distribution.Gaussian` for details.
+
+    prec
+        See :class:`~cuqi.distribution.Gaussian` for details.
+
+    sqrtcov
+        See :class:`~cuqi.distribution.Gaussian` for details.
+
+    sqrtprec
+        See :class:`~cuqi.distribution.Gaussian` for details.
+
+    projector : callable f(x) or None
+        Euclidean projection onto the constraint C, that is, a solver for the optimization problem
+        min_(z in C) 0.5||x-z||_2^2.
+
+    constraint : string or None
+        Preset constraints. Can be set to "nonnegativity" and "box". Required for use in Gibbs.
+        For "box", the following additional parameters can be passed:
+            lower_bound : array_like or None
+                Lower bound of box, defaults to zero
+            upper_bound : array_like
+                Upper bound of box, defaults to one
+
+    """
+    def __init__(self, mean=None, cov=None, prec=None, sqrtcov=None,sqrtprec=None, projector=None, constraint=None, **kwargs):
+        super().__init__(mean=mean, cov=cov, prec=prec, sqrtcov=sqrtcov, sqrtprec=sqrtprec, projector=projector, constraint=constraint, **kwargs)
+
+        
+class NonnegativeGaussian(RegularizedGaussian):
+    """ Implicit Nonnegative Gaussian.
+
+    Defines a so-called implicit prior based on a Gaussian distribution with implicit nonnegativity constraints.
+
+    Can be used as a prior in a posterior which can be sampled with the RegularizedLinearRTO sampler.
+
+    Alias for :class:`~cuqi.implicitprior.RegularizedGaussian` with only nonnegativity constraints.
+
+    For more details on implicit regularized Gaussian see the following paper:
+
+    [1] Everink, Jasper M., Yiqiu Dong, and Martin S. Andersen. "Sparse Bayesian inference with regularized
+    Gaussian distributions." Inverse Problems 39.11 (2023): 115004.
+
+    Parameters
+    ----------
+    mean
+        See :class:`~cuqi.distribution.Gaussian` for details.
+
+    cov
+        See :class:`~cuqi.distribution.Gaussian` for details.
+
+    prec
+        See :class:`~cuqi.distribution.Gaussian` for details.
+
+    sqrtcov
+        See :class:`~cuqi.distribution.Gaussian` for details.
+
+    sqrtprec
+        See :class:`~cuqi.distribution.Gaussian` for details.
+
+    """
+    def __init__(self, mean=None, cov=None, prec=None, sqrtcov=None,sqrtprec=None, **kwargs):
+        super().__init__(mean=mean, cov=cov, prec=prec, sqrtcov=sqrtcov, sqrtprec=sqrtprec, constraint="nonnegativity", **kwargs)

cuqi/implicitprior/_regularizedUnboundedUniform.py

@@ -0,0 +1,66 @@
+from cuqi.implicitprior import RegularizedGaussian
+from cuqi.distribution import Distribution, Gaussian
+
+import numpy as np
+
+
+class RegularizedUnboundedUniform(RegularizedGaussian):
+        """ Implicit Regularized Unbounded Uniform. 
+
+        Defines a so-called implicit prior with implicit regularization on a Gaussian distribution with zero precision.
+        The regularization can be defined in the form of a proximal operator or a projector.
+        Alternatively, preset constraints and regularization can be used.
+
+        For regularization of the form f(x), provide a single proximal operator.
+
+        Can be used as a prior in a posterior which can be sampled with the RegularizedLinearRTO sampler.
+
+        Alias for :class:`~cuqi.implicitprior.RegularizedGaussian` with zero mean and zero sqrtprec.
+
+        For more details on implicit regularized Gaussian see the following paper:
+
+        [1] Everink, Jasper M., Yiqiu Dong, and Martin S. Andersen. "Sparse Bayesian inference with regularized
+        Gaussian distributions." Inverse Problems 39.11 (2023): 115004.
+
+        Parameters
+        ----------
+        geometry : :class:`~cuqi.geometry.Geometry` or integer
+                The geometry of the underlying variable. Defines the dimension of the distribution. 
+
+        proximal : callable f(x, scale) or None
+                Euclidean proximal operator f of the regularization function g, that is, a solver for the optimization problem
+                min_z 0.5||x-z||_2^2+scale*g(x).
+
+        projector : callable f(x) or None
+                Euclidean projection onto the constraint C, that is, a solver for the optimization problem
+                min_(z in C) 0.5||x-z||_2^2.
+
+        constraint : string or None
+                Preset constraints. Can be set to "nonnegativity" and "box". Required for use in Gibbs.
+                For "box", the following additional parameters can be passed:
+                lower_bound : array_like or None
+                        Lower bound of box, defaults to zero
+                upper_bound : array_like
+                        Upper bound of box, defaults to one
+
+        regularization : string or None
+                Preset regularization. Can be set to "l1". Required for use in Gibbs in future update.
+                For "l1", the following additional parameters can be passed:
+                strength : scalar
+                        Regularization parameter, i.e., strength*||x||_1 , defaults to one
+
+        """
+        def __init__(self, geometry, proximal = None, projector = None, constraint = None, regularization = None, **kwargs):
+                
+                args = {"lower_bound" : kwargs.pop("lower_bound", None),
+                        "upper_bound" : kwargs.pop("upper_bound", None),
+                        "strength" : kwargs.pop("strength", None)}
+
+                # Underlying explicit Gaussian
+                # This line throws a warning due trying to applying get_sqrtprec_from_sqrtprec to an all zero matrix  
+                self._gaussian = Gaussian(mean = np.zeros(geometry.par_dim), sqrtprec = np.zeros((geometry.par_dim,geometry.par_dim)), geometry = geometry, **kwargs) 
+
+                # Init from abstract distribution class
+                super(Distribution, self).__init__(**kwargs)
+
+                self._parse_regularization_input_arguments(proximal, projector, constraint, regularization, args)