CUQIpy 1.4.0.post0.dev13__py3-none-any.whl → 1.4.0.post0.dev41__py3-none-any.whl

cuqi/legacy/sampler/_rto.py

@@ -0,0 +1,284 @@
+import scipy as sp
+from scipy.linalg.interpolative import estimate_spectral_norm
+from scipy.sparse.linalg import LinearOperator as scipyLinearOperator
+import numpy as np
+import cuqi
+from cuqi.solver import CGLS, FISTA
+from cuqi.legacy.sampler import Sampler
+
+
+class LinearRTO(Sampler):
+    """
+    Linear RTO (Randomize-Then-Optimize) sampler.
+
+    Samples posterior related to the inverse problem with Gaussian likelihood and prior, and where the forward model is linear or more generally affine.
+
+    Parameters
+    ------------
+    target : `cuqi.distribution.Posterior`, `cuqi.distribution.MultipleLikelihoodPosterior` or 5-dimensional tuple.
+        If target is of type cuqi.distribution.Posterior or cuqi.distribution.MultipleLikelihoodPosterior, it represents the posterior distribution.
+        If target is a 5-dimensional tuple, it assumes the following structure:
+        (data, model, L_sqrtprec, P_mean, P_sqrtrec)
+        
+        Here:
+        data: is a m-dimensional numpy array containing the measured data.
+        model: is a m by n dimensional matrix, AffineModel or LinearModel representing the forward model.
+        L_sqrtprec: is the squareroot of the precision matrix of the Gaussian likelihood.
+        P_mean: is the prior mean.
+        P_sqrtprec: is the squareroot of the precision matrix of the Gaussian mean.
+
+    x0 : `np.ndarray` 
+        Initial point for the sampler. *Optional*.
+
+    maxit : int
+        Maximum number of iterations of the inner CGLS solver. *Optional*.
+
+    tol : float
+        Tolerance of the inner CGLS solver. *Optional*.
+
+    callback : callable, *Optional*
+        If set this function will be called after every sample.
+        The signature of the callback function is `callback(sample, sample_index)`,
+        where `sample` is the current sample and `sample_index` is the index of the sample.
+        An example is shown in demos/demo31_callback.py.
+        
+    """
+    def __init__(self, target, x0=None, maxit=10, tol=1e-6, shift=0, **kwargs):
+        
+        # Accept tuple of inputs and construct posterior
+        if isinstance(target, tuple) and len(target) == 5:
+            # Structure (data, model, L_sqrtprec, P_mean, P_sqrtprec)
+            data = target[0]
+            model = target[1]
+            L_sqrtprec = target[2]
+            P_mean = target[3]
+            P_sqrtprec = target[4]
+
+            # If numpy matrix convert to CUQI model
+            if isinstance(model, np.ndarray) and len(model.shape) == 2:
+                model = cuqi.model.LinearModel(model)
+
+            # Check model input
+            if not isinstance(model, cuqi.model.AffineModel):
+                raise TypeError("Model needs to be cuqi.model.AffineModel or matrix")
+
+            # Likelihood
+            L = cuqi.distribution.Gaussian(model, sqrtprec=L_sqrtprec).to_likelihood(data)
+
+            # Prior TODO: allow multiple priors stacked
+            #if isinstance(P_mean, list) and isinstance(P_sqrtprec, list):
+            #    P = cuqi.distribution.JointGaussianSqrtPrec(P_mean, P_sqrtprec)
+            #else:
+            P = cuqi.distribution.Gaussian(P_mean, sqrtprec=P_sqrtprec)
+
+            # Construct posterior
+            target = cuqi.distribution.Posterior(L, P)
+
+        super().__init__(target, x0=x0, **kwargs)
+
+        self._check_posterior()
+
+        # Modify initial guess        
+        if x0 is not None:
+            self.x0 = x0
+        else:
+            self.x0 = np.zeros(self.prior.dim)
+
+        # Other parameters
+        self.maxit = maxit
+        self.tol = tol        
+        self.shift = 0
+                
+        L1 = [likelihood.distribution.sqrtprec for likelihood in self.likelihoods]
+        L2 = self.prior.sqrtprec
+        L2mu = self.prior.sqrtprecTimesMean
+
+        # pre-computations
+        self.n = len(self.x0)
+        self.b_tild = np.hstack([L@(likelihood.data - model._shift) for (L, likelihood, model) in zip(L1, self.likelihoods, self.models)]+ [L2mu])
+
+        callability = [callable(likelihood.model) for likelihood in self.likelihoods]
+        notcallability = [not c for c in callability]
+        if all(notcallability):
+            self.M = sp.sparse.vstack([L@likelihood.model for (L, likelihood) in zip(L1, self.likelihoods)] + [L2])
+        elif all(callability):
+            # in this case, model is a function doing forward and backward operations
+            def M(x, flag):
+                if flag == 1:
+                    out1 = [L @ likelihood.model._forward_func_no_shift(x) for (L, likelihood) in zip(L1, self.likelihoods)] # Use forward function which excludes shift
+                    out2 = L2 @ x
+                    out  = np.hstack(out1 + [out2])
+                elif flag == 2:
+                    idx_start = 0
+                    idx_end = 0
+                    out1 = np.zeros(self.n)
+                    for likelihood in self.likelihoods:
+                        idx_end += len(likelihood.data)
+                        out1 += likelihood.model._adjoint_func_no_shift(likelihood.distribution.sqrtprec.T@x[idx_start:idx_end]) # Use adjoint function which excludes shift
+                        idx_start = idx_end
+                    out2 = L2.T @ x[idx_end:]
+                    out  = out1 + out2                
+                return out   
+            self.M = M  
+        else:
+            raise TypeError("All likelihoods need to be callable or none need to be callable.") 
+
+    @property
+    def prior(self):
+        return self.target.prior
+
+    @property
+    def likelihood(self):
+        return self.target.likelihood
+    
+    @property
+    def likelihoods(self):
+        if isinstance(self.target, cuqi.distribution.Posterior):
+            return [self.target.likelihood]
+        elif isinstance(self.target, cuqi.distribution.MultipleLikelihoodPosterior):
+            return self.target.likelihoods
+
+    @property
+    def model(self):
+        return self.target.model     
+    
+    @property
+    def models(self):
+        if isinstance(self.target, cuqi.distribution.Posterior):
+            return [self.target.model]
+        elif isinstance(self.target, cuqi.distribution.MultipleLikelihoodPosterior):
+            return self.target.models    
+
+    def _sample(self, N, Nb):   
+        Ns = N+Nb   # number of simulations        
+        samples = np.empty((self.n, Ns))
+                     
+        # initial state   
+        samples[:, 0] = self.x0
+        for s in range(Ns-1):
+            y = self.b_tild + np.random.randn(len(self.b_tild))
+            sim = CGLS(self.M, y, samples[:, s], self.maxit, self.tol, self.shift)            
+            samples[:, s+1], _ = sim.solve()
+
+            self._print_progress(s+2,Ns) #s+2 is the sample number, s+1 is index assuming x0 is the first sample
+            self._call_callback(samples[:, s+1], s+1)
+
+        # remove burn-in
+        samples = samples[:, Nb:]
+        
+        return samples, None, None
+
+    def _sample_adapt(self, N, Nb):
+        return self._sample(N,Nb)
+    
+    def _check_posterior(self):
+        # Check target type
+        if not isinstance(self.target, (cuqi.distribution.Posterior, cuqi.distribution.MultipleLikelihoodPosterior)):
+            raise ValueError(f"To initialize an object of type {self.__class__}, 'target' need to be of type 'cuqi.distribution.Posterior' or 'cuqi.distribution.MultipleLikelihoodPosterior'.")       
+
+        # Check Linear model and Gaussian likelihood(s)
+        if isinstance(self.target, cuqi.distribution.Posterior):
+            if not isinstance(self.model, cuqi.model.AffineModel):
+                raise TypeError("Model needs to be linear or affine")
+
+            if not hasattr(self.likelihood.distribution, "sqrtprec"):
+                raise TypeError("Distribution in Likelihood must contain a sqrtprec attribute")
+            
+        elif isinstance(self.target, cuqi.distribution.MultipleLikelihoodPosterior): # Elif used for further alternatives, e.g., stacked posterior
+            for likelihood in self.likelihoods:
+                if not isinstance(likelihood.model, cuqi.model.LinearModel):
+                    raise TypeError("Model needs to be linear")
+
+                if not hasattr(likelihood.distribution, "sqrtprec"):
+                    raise TypeError("Distribution in Likelihood must contain a sqrtprec attribute")
+        
+        # Check Gaussian prior
+        if not hasattr(self.prior, "sqrtprec"):
+            raise TypeError("prior must contain a sqrtprec attribute")
+
+        if not hasattr(self.prior, "sqrtprecTimesMean"):
+            raise TypeError("Prior must contain a sqrtprecTimesMean attribute")
+
+
+class RegularizedLinearRTO(LinearRTO):
+    """
+    Regularized Linear RTO (Randomize-Then-Optimize) sampler.
+
+    Samples posterior related to the inverse problem with Gaussian likelihood and implicit Gaussian prior, and where the forward model is Linear.
+
+    Parameters
+    ------------
+    target : `cuqi.distribution.Posterior`
+        See `cuqi.legacy.sampler.LinearRTO`
+
+    x0 : `np.ndarray` 
+        Initial point for the sampler. *Optional*.
+
+    maxit : int
+        Maximum number of iterations of the inner FISTA solver. *Optional*.
+        
+    stepsize : string or float
+        If stepsize is a string and equals either "automatic", then the stepsize is automatically estimated based on the spectral norm.
+        If stepsize is a float, then this stepsize is used.
+
+    abstol : float
+        Absolute tolerance of the inner FISTA solver. *Optional*.
+
+    callback : callable, *Optional*
+        If set this function will be called after every sample.
+        The signature of the callback function is `callback(sample, sample_index)`,
+        where `sample` is the current sample and `sample_index` is the index of the sample.
+        An example is shown in demos/demo31_callback.py.
+        
+    """
+    def __init__(self, target, x0=None, maxit=100, stepsize = "automatic", abstol=1e-10, adaptive = True, **kwargs):
+
+        if not callable(target.prior.proximal):
+            raise TypeError("Projector needs to be callable")
+        
+        super().__init__(target, x0=x0, maxit=100, **kwargs)
+
+        # Other parameters
+        self.stepsize = stepsize
+        self.abstol = abstol   
+        self.adaptive = adaptive
+        self.proximal = target.prior.proximal
+
+    @property
+    def prior(self):
+        return self.target.prior.gaussian
+
+    def _sample(self, N, Nb):   
+        Ns = N+Nb   # number of simulations        
+        samples = np.empty((self.n, Ns))
+                   
+        if isinstance(self.stepsize, str):
+            if self.stepsize in ["automatic"]:
+                if not callable(self.M):
+                    M_op = scipyLinearOperator(self.M.shape, matvec = lambda v: self.M@v, rmatvec = lambda w: self.M.T@w)
+                else:
+                    M_op = scipyLinearOperator((len(self.b_tild), self.n), matvec = lambda v: self.M(v,1), rmatvec = lambda w: self.M(w,2))
+                    
+                _stepsize = 0.99/(estimate_spectral_norm(M_op)**2)
+                # print(f"Estimated stepsize for regularized Linear RTO: {_stepsize}")
+            else:
+                raise ValueError("Stepsize choice not supported")
+        else:
+            _stepsize = self.stepsize
+            
+        # initial state   
+        samples[:, 0] = self.x0
+        for s in range(Ns-1):
+            y = self.b_tild + np.random.randn(len(self.b_tild))
+            sim = FISTA(self.M, y, self.proximal,
+                        samples[:, s], maxit = self.maxit, stepsize = _stepsize, abstol = self.abstol, adaptive = self.adaptive)         
+            samples[:, s+1], _ = sim.solve()
+            
+            self._print_progress(s+2,Ns) #s+2 is the sample number, s+1 is index assuming x0 is the first sample
+            self._call_callback(samples[:, s+1], s+1)
+        # remove burn-in
+        samples = samples[:, Nb:]
+        
+        return samples, None, None
+
+

cuqi/legacy/sampler/_sampler.py

@@ -0,0 +1,182 @@
+from abc import ABC, abstractmethod
+import sys
+import numpy as np
+import cuqi
+from cuqi.samples import Samples
+import warnings
+
+class Sampler(ABC):
+
+    def __init__(self, target, x0=None, dim=None, callback=None):
+
+        warnings.warn(f"\nYou are using the legacy sampler '{self.__class__.__name__}'.\n"
+                      f"This will be removed in a future release of CUQIpy.\n"
+                      f"Please consider using the new samplers in the 'cuqi.sampler' module.\n", UserWarning, stacklevel=2)
+
+        self._dim = dim
+        if hasattr(target,'dim'): 
+            if self._dim is None:
+                self._dim = target.dim 
+            elif self._dim != target.dim:
+                raise ValueError("'dim' need to be None or equal to 'target.dim'") 
+        elif x0 is not None:
+            self._dim = len(x0)
+
+        self.target = target
+
+        if x0 is None:
+            x0 = np.ones(self.dim)
+        self.x0 = x0
+
+        self.callback = callback
+
+    def step(self, x):
+        """
+        Perform a single MCMC step
+        """
+        # Currently a hack to get step method for any sampler
+        self.x0 = x
+        return self.sample(2).samples[:,-1]
+
+    def step_tune(self, x, *args, **kwargs):
+        """
+        Perform a single MCMC step and tune the sampler. This is used during burn-in.
+        """
+        # Currently a hack to get step method for any sampler
+        out = self.step(x)
+        self.tune(*args, *kwargs)
+        return out
+
+    def tune(self):
+        """
+        Tune the sampler parameters.
+        """
+        pass
+
+
+    @property
+    def geometry(self):
+        if hasattr(self, 'target') and hasattr(self.target, 'geometry'):
+            geom =  self.target.geometry
+        else:
+            geom = cuqi.geometry._DefaultGeometry1D(self.dim)
+        return geom
+
+    @property 
+    def target(self):
+        return self._target 
+
+    @target.setter 
+    def target(self, value):
+        if  not isinstance(value, cuqi.distribution.Distribution) and callable(value):
+            # obtain self.dim
+            if self.dim is not None:
+                dim = self.dim
+            else:
+                raise ValueError(f"If 'target' is a lambda function, the parameter 'dim' need to be specified when initializing {self.__class__}.")
+
+            # set target
+            self._target = cuqi.distribution.UserDefinedDistribution(logpdf_func=value, dim = dim)
+
+        elif isinstance(value, cuqi.distribution.Distribution):
+            self._target = value
+        else:
+            raise ValueError("'target' need to be either a lambda function or of type 'cuqi.distribution.Distribution'")
+
+
+    @property
+    def dim(self):
+        if hasattr(self,'target') and hasattr(self.target,'dim'):
+            self._dim = self.target.dim 
+        return self._dim
+    
+
+    def sample(self,N,Nb=0):
+        # Get samples from the samplers sample method
+        result = self._sample(N,Nb)
+        return self._create_Sample_object(result,N+Nb)
+
+    def sample_adapt(self,N,Nb=0):
+        # Get samples from the samplers sample method
+        result = self._sample_adapt(N,Nb)
+        return self._create_Sample_object(result,N+Nb)
+
+    def _create_Sample_object(self,result,N):
+        loglike_eval = None
+        acc_rate = None
+        if isinstance(result,tuple):
+            #Unpack samples+loglike+acc_rate
+            s = result[0]
+            if len(result)>1: loglike_eval = result[1]
+            if len(result)>2: acc_rate = result[2]
+            if len(result)>3: raise TypeError("Expected tuple of at most 3 elements from sampling method.")
+        else:
+            s = result
+                
+        #Store samples in cuqi samples object if more than 1 sample
+        if N==1:
+            if len(s) == 1 and isinstance(s,np.ndarray): #Extract single value from numpy array
+                s = s.ravel()[0]
+            else:
+                s = s.flatten()
+        else:
+            s = Samples(s, self.geometry)#, geometry = self.geometry)
+            s.loglike_eval = loglike_eval
+            s.acc_rate = acc_rate
+        return s
+
+    @abstractmethod
+    def _sample(self,N,Nb):
+        pass
+
+    @abstractmethod
+    def _sample_adapt(self,N,Nb):
+        pass
+
+    def _print_progress(self,s,Ns):
+        """Prints sampling progress"""
+        if Ns > 2:
+            if (s % (max(Ns//100,1))) == 0:
+                msg = f'Sample {s} / {Ns}'
+                sys.stdout.write('\r'+msg)
+            if s==Ns:
+                msg = f'Sample {s} / {Ns}'
+                sys.stdout.write('\r'+msg+'\n')
+
+    def _call_callback(self, sample, sample_index):
+        """ Calls the callback function. Assumes input is sample and sample index"""
+        if self.callback is not None:
+            self.callback(sample, sample_index)
+
+class ProposalBasedSampler(Sampler,ABC):
+    def __init__(self, target,  proposal=None, scale=1, x0=None, dim=None, **kwargs):
+        #TODO: after fixing None dim
+        #if dim is None and hasattr(proposal,'dim'):
+        #    dim = proposal.dim
+        super().__init__(target, x0=x0, dim=dim, **kwargs)
+
+        self.proposal =proposal
+        self.scale = scale
+
+
+    @property 
+    def proposal(self):
+        return self._proposal 
+
+    @proposal.setter 
+    def proposal(self, value):
+        self._proposal = value
+
+    @property
+    def geometry(self):
+        geom1, geom2 = None, None
+        if hasattr(self, 'proposal') and hasattr(self.proposal, 'geometry') and self.proposal.geometry.par_dim is not None:
+            geom1=  self.proposal.geometry
+        if hasattr(self, 'target') and hasattr(self.target, 'geometry') and self.target.geometry.par_dim is not None:
+            geom2 = self.target.geometry
+        if not isinstance(geom1,cuqi.geometry._DefaultGeometry) and geom1 is not None:
+            return geom1
+        elif not isinstance(geom2,cuqi.geometry._DefaultGeometry) and geom2 is not None: 
+            return geom2
+        else:
+            return cuqi.geometry._DefaultGeometry1D(self.dim)