inference-tools 0.14.1__py3-none-any.whl → 0.14.2__py3-none-any.whl

inference/_version.py

@@ -17,5 +17,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '0.14.1'
-__version_tuple__ = version_tuple = (0, 14, 1)
+__version__ = version = '0.14.2'
+__version_tuple__ = version_tuple = (0, 14, 2)

inference/approx/__init__.py

@@ -1,3 +1,7 @@
-from inference.approx.conditional import conditional_sample, get_conditionals
+from inference.approx.conditional import (
+    conditional_sample,
+    get_conditionals,
+    conditional_moments,
+)
 
-__all__ = ["conditional_sample", "get_conditionals"]
+__all__ = ["conditional_sample", "get_conditionals", "conditional_moments"]

inference/approx/conditional.py

@@ -272,3 +272,42 @@ def conditional_sample(
     for i in range(n_params):
         samples[:, i] = piecewise_linear_sample(axes[:, i], probs[:, i], n_samples)
     return samples
+
+
+def conditional_moments(
+    posterior: callable, bounds: list, conditioning_point: ndarray
+) -> tuple[ndarray, ndarray]:
+    """
+    Calculate the mean and variance of the 1D conditional distributions of the posterior
+    around a given point in the parameter space.
+
+    :param posterior: \
+        A function which returns the posterior log-probability when given a
+        numpy ``ndarray`` of the model parameters.
+
+    :param bounds: \
+        A list of length-2 tuples specifying the lower and upper bounds on
+        each parameter, in the form ``(lower, upper)``.
+
+    :param conditioning_point: \
+        The point in the parameter space around which the conditional distributions are
+        evaluated.
+
+    :return means, variances: \
+        The means and variances of the conditional distributions as a pair of
+        1D numpy ``ndarray``.
+    """
+    axes, probs = get_conditionals(
+        posterior=posterior, bounds=bounds, conditioning_point=conditioning_point
+    )
+
+    grid_size, n_params = probs.shape
+    means = zeros(n_params)
+    variances = zeros(n_params)
+    # integrate to calculate the means and variances
+    for i in range(n_params):
+        means[i] = simpson(y=axes[:, i] * probs[:, i], x=axes[:, i])
+        variances[i] = simpson(
+            y=(axes[:, i] - means[i]) ** 2 * probs[:, i], x=axes[:, i]
+        )
+    return means, variances

inference/mcmc/base.py

@@ -1,7 +1,7 @@
 from abc import ABC, abstractmethod
 from copy import copy
 from time import time
-from numpy import ndarray
+from numpy import ndarray, isfinite
 from numpy.random import permutation
 
 from inference.pdf.base import DensityEstimator
@@ -262,3 +262,35 @@ class MarkovChain(ABC):
             \r>> 'burn' and 'thin' keyword arguments.
             """
         )
+
+    def _validate_posterior(self, posterior: callable, start: ndarray):
+        if not callable(posterior):
+            raise ValueError(
+                f"""\n
+                \r[ {self.__class__.__name__} error ]
+                \r>> The given 'posterior' is not a callable object.
+                """
+            )
+
+        prob = posterior(start)
+
+        if not isinstance(prob, float):
+            raise ValueError(
+                f"""\n
+                \r[ {self.__class__.__name__} error ]
+                \r>> The given 'posterior' must return a float or a type which
+                \r>> derives from float (e.g. numpy.float64), however the returned
+                \r>> value has type:
+                \r>> {type(prob)}
+                """
+            )
+
+        if not isfinite(prob):
+            raise ValueError(
+                f"""\n
+                \r[ {self.__class__.__name__} error ]
+                \r>> The given 'posterior' must return a finite value for the given
+                \r>> 'start' parameter values, but instead returns a value of:
+                \r>> {prob}
+                """
+            )

inference/mcmc/gibbs.py

@@ -253,7 +253,7 @@ class MetropolisChain(MarkovChain):
 
         if posterior is not None:
             self.posterior = posterior
-
+            self._validate_posterior(posterior=posterior, start=start)
             # if widths are not specified, take 5% of the starting values (unless they're zero)
             if widths is None:
                 widths = [v * 0.05 if v != 0 else 1.0 for v in start]

inference/mcmc/hmc/__init__.py

@@ -87,7 +87,7 @@ class HamiltonianChain(MarkovChain):
             start = start if isinstance(start, ndarray) else array(start)
             start = start if start.dtype is float64 else start.astype(float64)
             assert start.ndim == 1
-
+            self._validate_posterior(posterior=posterior, start=start)
             self.theta = [start]
             self.probs = [self.posterior(start) * self.inv_temp]
             self.leapfrog_steps = [0]

inference/mcmc/hmc/mass.py

@@ -3,7 +3,7 @@ from typing import Union
 from numpy import ndarray, sqrt, eye, isscalar
 from numpy.random import Generator
 from numpy.linalg import cholesky
-from scipy.linalg import solve_triangular
+from scipy.linalg import solve_triangular, issymmetric
 
 
 class ParticleMass(ABC):
@@ -37,12 +37,49 @@ class VectorMass(ScalarMass):
         assert inv_mass.ndim == 1
         assert inv_mass.size == n_parameters
 
+        valid_variances = (
+            inv_mass.ndim == 1
+            and inv_mass.size == n_parameters
+            and (inv_mass > 0.0).all()
+        )
+
+        if not valid_variances:
+            raise ValueError(
+                f"""\n
+                \r[ VectorMass error ]
+                \r>> The inverse-mass vector must be a 1D array and have size
+                \r>> equal to the given number of model parameters ({n_parameters})
+                \r>> and contain only positive values.
+                """
+            )
+
 
 class MatrixMass(ParticleMass):
     def __init__(self, inv_mass: ndarray, n_parameters: int):
-        assert inv_mass.ndim == 2
-        assert inv_mass.shape[0] == inv_mass.shape[1] == n_parameters
-        assert (inv_mass == inv_mass.T).all()
+
+        valid_covariance = (
+            inv_mass.ndim == 2
+            and inv_mass.shape[0] == inv_mass.shape[1]
+            and issymmetric(inv_mass)
+        )
+
+        if not valid_covariance:
+            raise ValueError(
+                """\n
+                \r[ MatrixMass error ]
+                \r>> The given inverse-mass matrix must be a valid covariance matrix,
+                \r>> i.e. 2 dimensional, square and symmetric.
+                """
+            )
+
+        if inv_mass.shape[0] != n_parameters:
+            raise ValueError(
+                f"""\n
+                \r[ MatrixMass error ]
+                \r>> The dimensions of the given inverse-mass matrix {inv_mass.shape}
+                \r>> do not match the given number of model parameters ({n_parameters}).
+                """
+            )
 
         self.inv_mass = inv_mass
         self.n_parameters = n_parameters

{inference_tools-0.14.1.dist-info → inference_tools-0.14.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: inference-tools
-Version: 0.14.1
+Version: 0.14.2
 Summary: A collection of python tools for Bayesian data analysis
 Author-email: Chris Bowman <chris.bowman.physics@gmail.com>
 License: MIT License

{inference_tools-0.14.1.dist-info → inference_tools-0.14.2.dist-info}/RECORD

@@ -1,11 +1,11 @@
 inference/__init__.py,sha256=Wheq9bSUF5Y_jAc_w_Avi4WW2kphDK0qHGM6FsIKSxY,275
-inference/_version.py,sha256=9-B5HerO_wiKUcm3zqJZazE8kjqwU6_WcIM1m-vWIoQ,513
+inference/_version.py,sha256=9gfM7I3EzKUUvEDxnQgfyPI3Ie4vtLtm20hLu-bUsls,513
 inference/likelihoods.py,sha256=0mRn9S7CaX6hNv1fKVeaAFYk50bALvVbyX7E2aH3Bn8,10021
 inference/plotting.py,sha256=vMpRGiZMMlVgAcVaKC2wtvjzVlBmOkC2BM90A3wSwJ8,19194
 inference/posterior.py,sha256=ptPZgzT--ehbpu57nW9GmFuyovFOSmw56HWfuC-8GGA,3584
 inference/priors.py,sha256=zDuIgJTZrqEqkp8rE-aBRlAuqBacR9aC_QNm8jNIYl8,19368
-inference/approx/__init__.py,sha256=b8xCdshVeGHyao6-P0038QB71WOMLrcYXCOYiYjK7Tk,132
-inference/approx/conditional.py,sha256=IeUismbo25qa1BUIqsZ2noum9_mLXNaORsg57abxBec,9515
+inference/approx/__init__.py,sha256=ghGGQNpOp4BBE7Ani-ProAN9z3BlIX62ZR6cbQcivS8,193
+inference/approx/conditional.py,sha256=mGM_djkpvlHfTDUoN84mQmIA2f9FUDhp-hdLiwACAzk,10896
 inference/gp/__init__.py,sha256=R4iPgf8TdunkOv_VLwue7Fz3AjGWDTBop58nCmbmMQ0,801
 inference/gp/acquisition.py,sha256=Yr1dshTYwkMIrKYPSwDZDusXXNsOpobrxaympJc5q3g,8158
 inference/gp/covariance.py,sha256=DVN8lAtDjCWXYSsQwhQZxV6RJ8KZeo72unOCjHhTGg0,25919
@@ -14,22 +14,22 @@ inference/gp/mean.py,sha256=6EJ_OxBi98netl9Rp2Ij7eXdWndGVS-X_g5VWnWMVkk,4084
 inference/gp/optimisation.py,sha256=sPhakklWIgg1yEUhUzA-m5vl0kVPvHdcgnQ0OAGT8qs,11763
 inference/gp/regression.py,sha256=10TzqVeUzUkuw8-Cbe4LbxevByTi5iE5QDdRClN7Nhk,25677
 inference/mcmc/__init__.py,sha256=IsEhVSIpZCDNIqgSq_21M6DH6x8F1jJbYWM0e3S3QG4,445
-inference/mcmc/base.py,sha256=cEh1LPmKd6JMop8EcuH3dvAeJYei88pcPTw1xe7tGKY,10496
+inference/mcmc/base.py,sha256=ay8P8ypF8_Dj3hIkjmjniiDxc40xVdmRSqCjVAqnMMc,11637
 inference/mcmc/ensemble.py,sha256=JRXu7SBYXN4Y9RzgA6kGUHpZNw4q4A9wf0KOAQdlz0E,15585
-inference/mcmc/gibbs.py,sha256=f-eccDBILfaZercZii3vuJ29V505VUsCHoxhD9gZ7xA,24288
+inference/mcmc/gibbs.py,sha256=roXjTdO63fQTtFN6vYZa0yHvWYInFU0qX2hREH0PTgo,24358
 inference/mcmc/parallel.py,sha256=SKLzMP4aqIj1xsxKuByA1lr1GdgIu5pPzVw7hlfXZEQ,14053
 inference/mcmc/pca.py,sha256=NxC81NghGlBQslFVOk2HzpsnCjlEdDnv_w8es4Qe7PU,10695
 inference/mcmc/utilities.py,sha256=YjpK3FvV0Q98jLusrZrvGck-bjm6uZZ1U7HHH3aly8g,6048
-inference/mcmc/hmc/__init__.py,sha256=R2ZjKca1CjWwzAHRKetZOAbiJKo2YZVmX4jrz2EAyL4,17661
+inference/mcmc/hmc/__init__.py,sha256=QgERQDsEqeMBK2xPaLaaCG95zp0jfRaixDERQlwzejs,17731
 inference/mcmc/hmc/epsilon.py,sha256=t2kNi10MSVFXjmAx5zRUARDuPu_yWbwoK2McMuaaAUs,2467
-inference/mcmc/hmc/mass.py,sha256=qnxsbkogZFeqGbssZ2w4tsaUGytEXL-I0Gqs4UZzcAg,2545
+inference/mcmc/hmc/mass.py,sha256=vYuH67H1BnUm3z0OSQ4gVvL060PGTcG9TwB59nTJHCE,3759
 inference/pdf/__init__.py,sha256=gVmQ1HLTab6_oWMQN26A1r7PkqbApaJmBK-c7TIFxjY,270
 inference/pdf/base.py,sha256=Zj5mfFmDqTe5cFz0biBxcvEaxdOUC-SsOUjebUEX7HM,5442
 inference/pdf/hdi.py,sha256=soFw3fKQdzxbGNhU9BvFHdt0uGKfhus3E3vM6L47yhY,4638
 inference/pdf/kde.py,sha256=KSl8y---602MlxoSVH8VknNQYZ2KAOTky50QU3jRw28,12999
 inference/pdf/unimodal.py,sha256=9S05c0hq_rF-MLoDJgUmaJKRdcP8F9_Idj7Ncb6m9q0,6218
-inference_tools-0.14.1.dist-info/licenses/LICENSE,sha256=Y0-EfO5pdxf6d0J6Er13ZSWiPZ2o6kHvM37eRgnJdww,1069
-inference_tools-0.14.1.dist-info/METADATA,sha256=flIdPaL3VFTzogPS-k2CwjIu_kbww--4libVTB9zegY,5400
-inference_tools-0.14.1.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
-inference_tools-0.14.1.dist-info/top_level.txt,sha256=I7bsb71rLtH3yvVH_HSLXUosY2AwCxEG3vctNsEhbEM,10
-inference_tools-0.14.1.dist-info/RECORD,,
+inference_tools-0.14.2.dist-info/licenses/LICENSE,sha256=Y0-EfO5pdxf6d0J6Er13ZSWiPZ2o6kHvM37eRgnJdww,1069
+inference_tools-0.14.2.dist-info/METADATA,sha256=yKkLGfLX7yADQX43ASxGXJsutGTrIVuHllHl5rlO2hg,5400
+inference_tools-0.14.2.dist-info/WHEEL,sha256=zaaOINJESkSfm_4HQVc5ssNzHCPXhJm0kEUakpsEHaU,91
+inference_tools-0.14.2.dist-info/top_level.txt,sha256=I7bsb71rLtH3yvVH_HSLXUosY2AwCxEG3vctNsEhbEM,10
+inference_tools-0.14.2.dist-info/RECORD,,

{inference_tools-0.14.1.dist-info → inference_tools-0.14.2.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (78.1.0)
+Generator: setuptools (80.8.0)
 Root-Is-Purelib: true
 Tag: py3-none-any