Fix for issue #7563

pymc/distributions/continuous.py

@@ -246,7 +246,7 @@ def get_tau_sigma(
 
 class Uniform(BoundedContinuous):
     r"""
-    Continuous uniform log-likelihood.
+    Continuous uniform distribution.
 
     The pdf of this distribution is
 
@@ -360,7 +360,7 @@ def rng_fn(cls, rng, size):
 
 
 class Flat(Continuous):
-    """Uninformative log-likelihood that returns 0 regardless of the passed value."""
+    """Uninformative distribution that returns 0 regardless of the passed value."""
 
     rv_op = flat
 
@@ -417,7 +417,7 @@ def logcdf(value):
 
 class Normal(Continuous):
     r"""
-    Univariate normal log-likelihood.
+    Univariate normal distribution.
 
     The pdf of this distribution is
 
@@ -558,7 +558,7 @@ def rng_fn(
 
 class TruncatedNormal(BoundedContinuous):
     r"""
-    Univariate truncated normal log-likelihood.
+    Univariate truncated normal distribution.
 
     The pdf of this distribution is
 
@@ -745,7 +745,7 @@ def truncated_normal_default_transform(op, rv):
 
 class HalfNormal(PositiveContinuous):
     r"""
-    Half-normal log-likelihood.
+    Half-normal distribution.
 
     The pdf of this distribution is
 
@@ -875,7 +875,7 @@ def rng_fn(cls, rng, mu, lam, alpha, size) -> np.ndarray:
 
 class Wald(PositiveContinuous):
     r"""
-    Wald log-likelihood.
+    Wald distribution.
 
     The pdf of this distribution is
 
@@ -1055,7 +1055,7 @@ def rng_fn(cls, rng, alpha, beta, size) -> np.ndarray:
 
 class Beta(UnitContinuous):
     r"""
-    Beta log-likelihood.
+    Beta distribution.
 
     The pdf of this distribution is
 
@@ -1241,7 +1241,7 @@ def rv_op(cls, a, b, *, size=None, rng=None):
 
 class Kumaraswamy(UnitContinuous):
     r"""
-    Kumaraswamy log-likelihood.
+    Kumaraswamy distribution.
 
     The pdf of this distribution is
 
@@ -1331,7 +1331,7 @@ def logcdf(value, a, b):
 
 class Exponential(PositiveContinuous):
     r"""
-    Exponential log-likelihood.
+    Exponential distribution.
 
     The pdf of this distribution is
 
@@ -1426,7 +1426,7 @@ def icdf(value, mu):
 
 class Laplace(Continuous):
     r"""
-    Laplace log-likelihood.
+    Laplace distribution.
 
     The pdf of this distribution is
 
@@ -1548,7 +1548,7 @@ def rv_op(cls, b, kappa, mu, *, size=None, rng=None):
 
 class AsymmetricLaplace(Continuous):
     r"""
-    Asymmetric-Laplace log-likelihood.
+    Asymmetric-Laplace distribution.
 
     The pdf of this distribution is
 
@@ -1639,7 +1639,7 @@ def logp(value, b, kappa, mu):
 
 class LogNormal(PositiveContinuous):
     r"""
-    Log-normal log-likelihood.
+    Log-normal distribution.
 
     Distribution of any random variable whose logarithm is normally
     distributed. A variable might be modeled as log-normal if it can
@@ -1758,7 +1758,7 @@ def icdf(value, mu, sigma):
 
 class StudentT(Continuous):
     r"""
-    Student's T log-likelihood.
+    Student's T distribution.
 
     Describes a normal variable whose precision is gamma distributed.
     If only nu parameter is passed, this specifies a standard (central)
@@ -1904,7 +1904,7 @@ def rng_fn(cls, rng, a, b, mu, sigma, size=None) -> np.ndarray:
 
 class SkewStudentT(Continuous):
     r"""
-    Skewed Student's T distribution log-likelihood.
+    Skewed Student's T distribution distribution.
 
     This follows Jones and Faddy (2003)
 
@@ -2019,7 +2019,7 @@ def icdf(value, a, b, mu, sigma):
 
 class Pareto(BoundedContinuous):
     r"""
-    Pareto log-likelihood.
+    Pareto distribution.
 
     Often used to characterize wealth distribution, or other examples of the
     80/20 rule.
@@ -2128,7 +2128,7 @@ def pareto_default_transform(op, rv):
 
 class Cauchy(Continuous):
     r"""
-    Cauchy log-likelihood.
+    Cauchy distribution.
 
     Also known as the Lorentz or the Breit-Wigner distribution.
 
@@ -2216,7 +2216,7 @@ def icdf(value, alpha, beta):
 
 class HalfCauchy(PositiveContinuous):
     r"""
-    Half-Cauchy log-likelihood.
+    Half-Cauchy distribution.
 
     The pdf of this distribution is
 
@@ -2300,7 +2300,7 @@ def icdf(value, loc, beta):
 
 class Gamma(PositiveContinuous):
     r"""
-    Gamma log-likelihood.
+    Gamma distribution.
 
     Represents the sum of alpha exponentially distributed random variables,
     each of which has rate beta.
@@ -2429,7 +2429,7 @@ def icdf(value, alpha, scale):
 
 class InverseGamma(PositiveContinuous):
     r"""
-    Inverse gamma log-likelihood, the reciprocal of the gamma distribution.
+    Inverse gamma distribution, the reciprocal of the gamma distribution.
 
     The pdf of this distribution is
 
@@ -2545,7 +2545,7 @@ def logcdf(value, alpha, beta):
 
 class ChiSquared:
     r"""
-    :math:`\chi^2` log-likelihood.
+    :math:`\chi^2` distribution.
 
     This is the distribution from the sum of the squares of :math:`\nu` independent standard normal random variables or a special
     case of the gamma distribution with :math:`\alpha = \nu/2` and :math:`\beta = 1/2`.
@@ -2617,7 +2617,7 @@ def rng_fn(cls, rng, alpha, beta, size) -> np.ndarray:
 
 class Weibull(PositiveContinuous):
     r"""
-    Weibull log-likelihood.
+    Weibull distribution.
 
     The pdf of this distribution is
 
@@ -2738,7 +2738,7 @@ def rv_op(cls, nu, sigma, *, size=None, rng=None) -> np.ndarray:
 
 class HalfStudentT(PositiveContinuous):
     r"""
-    Half Student's T log-likelihood.
+    Half Student's T distribution.
 
     The pdf of this distribution is
 
@@ -2859,7 +2859,7 @@ def rv_op(cls, mu, sigma, nu, *, size=None, rng=None):
 
 class ExGaussian(Continuous):
     r"""
-    Exponentially modified Gaussian log-likelihood.
+    Exponentially modified Gaussian distribution.
 
     Results from the convolution of a normal distribution with an exponential
     distribution.
@@ -2982,7 +2982,7 @@ def logcdf(value, mu, sigma, nu):
 
 class VonMises(CircularContinuous):
     r"""
-    Univariate VonMises log-likelihood.
+    Univariate VonMises distribution.
 
     The pdf of this distribution is
 
@@ -3068,7 +3068,7 @@ def rng_fn(cls, rng, mu, sigma, alpha, size=None) -> np.ndarray:
 
 class SkewNormal(Continuous):
     r"""
-    Univariate skew-normal log-likelihood.
+    Univariate skew-normal distribution.
 
     The pdf of this distribution is
 
@@ -3163,7 +3163,7 @@ def logp(value, mu, sigma, alpha):
 
 class Triangular(BoundedContinuous):
     r"""
-    Continuous Triangular log-likelihood.
+    Continuous Triangular distribution.
 
     The pdf of this distribution is
 
@@ -3292,7 +3292,7 @@ def triangular_default_transform(op, rv):
 
 class Gumbel(Continuous):
     r"""
-    Univariate right-skewed Gumbel log-likelihood.
+    Univariate right-skewed Gumbel distribution.
 
     This distribution is typically used for modeling maximum (or extreme) values.
     Those looking to find the extreme minimum provided by the left-skewed Gumbel should
@@ -3519,7 +3519,7 @@ def logp(value, b, sigma):
 
 class Logistic(Continuous):
     r"""
-    Logistic log-likelihood.
+    Logistic distribution.
 
     The pdf of this distribution is
 
@@ -3627,7 +3627,7 @@ def rv_op(cls, mu, sigma, *, size=None, rng=None):
 
 class LogitNormal(UnitContinuous):
     r"""
-    Logit-Normal log-likelihood.
+    Logit-Normal distribution.
 
     The pdf of this distribution is
 
@@ -3872,7 +3872,7 @@ def rng_fn(cls, rng, mu, sigma, size=None) -> np.ndarray:
 
 class Moyal(Continuous):
     r"""
-    Moyal log-likelihood.
+    Moyal distribution.
 
     The pdf of this distribution is
 

pymc/distributions/discrete.py

@@ -71,7 +71,7 @@
 
 class Binomial(Discrete):
     R"""
-    Binomial log-likelihood.
+    Binomial distribution.
 
     The discrete probability distribution of the number of successes
     in a sequence of n independent yes/no experiments, each of which
@@ -176,7 +176,7 @@ def logcdf(value, n, p):
 
 class BetaBinomial(Discrete):
     R"""
-    Beta-binomial log-likelihood.
+    Beta-binomial distribution.
 
     Equivalent to binomial random variable with success probability
     drawn from a beta distribution.
@@ -293,7 +293,7 @@ def logcdf(value, n, alpha, beta):
 
 
 class Bernoulli(Discrete):
-    R"""Bernoulli log-likelihood.
+    R"""Bernoulli distribution.
 
     The Bernoulli distribution describes the probability of successes
     (x=1) and failures (x=0).
@@ -413,7 +413,7 @@ def rv_op(cls, q, beta, *, size=None, rng=None):
 
 
 class DiscreteWeibull(Discrete):
-    R"""Discrete Weibull log-likelihood.
+    R"""Discrete Weibull distribution.
 
     The discrete Weibull distribution is a flexible model of count data that
     can handle both over- and under-dispersion.
@@ -506,7 +506,7 @@ def logcdf(value, q, beta):
 
 class Poisson(Discrete):
     R"""
-    Poisson log-likelihood.
+    Poisson distribution.
 
     Often used to model the number of events occurring in a fixed period
     of time when the times at which events occur are independent.
@@ -602,7 +602,7 @@ def logcdf(value, mu):
 
 class NegativeBinomial(Discrete):
     R"""
-    Negative binomial log-likelihood.
+    Negative binomial distribution.
 
     The negative binomial distribution describes a Poisson random variable
     whose rate parameter is gamma distributed.
@@ -750,7 +750,7 @@ def logcdf(value, n, p):
 
 class Geometric(Discrete):
     R"""
-    Geometric log-likelihood.
+    Geometric distribution.
 
     The probability that the first success in a sequence of Bernoulli
     trials occurs on the x'th trial.
@@ -1084,7 +1084,7 @@ def icdf(value, lower, upper):
 
 class Categorical(Discrete):
     R"""
-    Categorical log-likelihood.
+    Categorical distribution.
 
     The most general discrete distribution. The pmf of this distribution is
 

pymc/distributions/distribution.py

@@ -668,7 +668,7 @@ def rv_op(cls, c, *, size=None, rng=None):
 
 class DiracDelta(Discrete):
     r"""
-    DiracDelta log-likelihood.
+    DiracDelta distribution.
 
     Parameters
     ----------