Skip to content

Increase unittest check_logcdf coverage and fix issues with some distribution methods #4393

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 10 commits into from
Jan 2, 2021
Merged

Increase unittest check_logcdf coverage and fix issues with some distribution methods #4393

Show file tree
Hide file tree
Changes from 5 commits
Commits
Show all changes
10 commits
Select commit Hold shift + click to select a range
9289599
Change `check_logcdf` to test that values below or above domain are p…
ricardoV94 Dec 29, 2020
07f09ad
Add multiple value test for logcdf.
ricardoV94 Dec 31, 2020
b91d1c1
Update release note
ricardoV94 Jan 2, 2021
d0316b5
Update docstrings with valid value types
ricardoV94 Jan 2, 2021
335b7eb
Update RELEASE-NOTES.md
ricardoV94 Jan 2, 2021
4fa834a
Add more informative comments and remove TODO
ricardoV94 Jan 2, 2021
5cc8fdc
Merge remote-tracking branch 'origin/increase_logcdf_coverage' into i…
ricardoV94 Jan 2, 2021
7c3fb12
TypeError: format -> f-strings
ricardoV94 Jan 2, 2021
8c51062
Ignore finite upper limit in Nat domains.
ricardoV94 Jan 2, 2021
4929b64
Use `tt.switch` in `DiscreteUniform` for hard boundary (addresses pre…
ricardoV94 Jan 2, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions RELEASE-NOTES.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,6 +29,7 @@ It also brings some dreadfully awaited fixes, so be sure to go through the chang
- Fixed mathematical formulation in `MvStudentT` random method. (see [#4359](https://github.com/pymc-devs/pymc3/pull/4359))
- Fix issue in `logp` method of `HyperGeometric`. It now returns `-inf` for invalid parameters (see [4367](https://github.com/pymc-devs/pymc3/pull/4367))
- Fixed `MatrixNormal` random method to work with parameters as random variables. (see [#4368](https://github.com/pymc-devs/pymc3/pull/4368))
- Update the `logcdf` method of several continuous distributions to return -inf for invalid parameters and values, and raise an informative error when multiple values cannot be evaluated in a single call. (see [4393](https://github.com/pymc-devs/pymc3/pull/4393))

## PyMC3 3.10.0 (7 December 2020)

Expand Down
130 changes: 87 additions & 43 deletions pymc3/distributions/continuous.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -278,21 +278,24 @@ def logcdf(self, value):

Parameters
----------
value: numeric
value: numeric or np.ndarray or theano.tensor
Value(s) for which log CDF is calculated. If the log CDF for multiple
values are desired the values must be provided in a numpy array or theano tensor.

Returns
-------
TensorVariable
"""
lower = self.lower
upper = self.upper

return tt.switch(
tt.or_(tt.lt(value, self.lower), tt.gt(value, self.upper)),
tt.lt(value, lower) | tt.lt(upper, lower),
-np.inf,
tt.switch(
tt.eq(value, self.upper),
tt.lt(value, upper),
tt.log(value - lower) - tt.log(upper - lower),
0,
tt.log(value - self.lower) - tt.log(self.upper - self.lower),
),
)

Expand Down Expand Up @@ -344,7 +347,7 @@ def logcdf(self, value):

Parameters
----------
value: numeric
value: numeric or np.ndarray or theano.tensor
Value(s) for which log CDF is calculated. If the log CDF for multiple
values are desired the values must be provided in a numpy array or theano tensor.

Expand Down Expand Up @@ -401,7 +404,7 @@ def logcdf(self, value):

Parameters
----------
value: numeric
value: numeric or np.ndarray or theano.tensor
Value(s) for which log CDF is calculated. If the log CDF for multiple
values are desired the values must be provided in a numpy array or theano tensor.

Expand Down Expand Up @@ -542,7 +545,7 @@ def logcdf(self, value):

Parameters
----------
value: numeric
value: numeric or np.ndarray or theano.tensor
Value(s) for which log CDF is calculated. If the log CDF for multiple
values are desired the values must be provided in a numpy array or theano tensor.

Expand Down Expand Up @@ -900,7 +903,7 @@ def logcdf(self, value):

Parameters
----------
value: numeric
value: numeric or np.ndarray or theano.tensor
Value(s) for which log CDF is calculated. If the log CDF for multiple
values are desired the values must be provided in a numpy array or theano tensor.

Expand All @@ -910,10 +913,10 @@ def logcdf(self, value):
"""
sigma = self.sigma
z = zvalue(value, mu=0, sigma=sigma)
return tt.switch(
tt.lt(z, -1.0),
tt.log(tt.erfcx(-z / tt.sqrt(2.0))) - tt.sqr(z),
return bound(
tt.log1p(-tt.erfc(z / tt.sqrt(2.0))),
0 <= value,
0 < sigma,
)


Expand Down Expand Up @@ -1106,7 +1109,7 @@ def logcdf(self, value):

Parameters
----------
value: numeric
value: numeric or np.ndarray or theano.tensor
Value(s) for which log CDF is calculated. If the log CDF for multiple
values are desired the values must be provided in a numpy array or theano tensor.

Expand Down Expand Up @@ -1297,20 +1300,32 @@ def logcdf(self, value):
Parameters
----------
value: numeric
Value(s) for which log CDF is calculated. If the log CDF for multiple
values are desired the values must be provided in a numpy array or theano tensor.
Value(s) for which log CDF is calculated.

Returns
-------
TensorVariable
"""
value = floatX(tt.as_tensor(value))
a = floatX(tt.as_tensor(self.alpha))
b = floatX(tt.as_tensor(self.beta))
return tt.switch(
tt.le(value, 0),
-np.inf,
tt.switch(tt.ge(value, 1), 0, tt.log(incomplete_beta(a, b, value))),
# incomplete_beta function can only handle scalar values (see #4342)
if np.ndim(value):
raise TypeError(
"Beta.logcdf expects a scalar value but received a {}-dimensional object.".format(
np.ndim(value)
)
)

a = self.alpha
b = self.beta

return bound(
tt.switch(
tt.lt(value, 1),
tt.log(incomplete_beta(a, b, value)),
0,
),
0 <= value,
0 < a,
0 < b,
)

def _distr_parameters_for_repr(self):
Expand Down Expand Up @@ -1521,7 +1536,7 @@ def logcdf(self, value):

Parameters
----------
value: numeric
value: numeric or np.ndarray or theano.tensor
Value(s) for which log CDF is calculated. If the log CDF for multiple
values are desired the values must be provided in a numpy array or theano tensor.

Expand Down Expand Up @@ -1636,7 +1651,7 @@ def logcdf(self, value):

Parameters
----------
value: numeric
value: numeric or np.ndarray or theano.tensor
Value(s) for which log CDF is calculated. If the log CDF for multiple
values are desired the values must be provided in a numpy array or theano tensor.

Expand Down Expand Up @@ -1792,7 +1807,7 @@ def logcdf(self, value):

Parameters
----------
value: numeric
value: numeric or np.ndarray or theano.tensor
Value(s) for which log CDF is calculated. If the log CDF for multiple
values are desired the values must be provided in a numpy array or theano tensor.

Expand Down Expand Up @@ -1955,20 +1970,34 @@ def logcdf(self, value):
Parameters
----------
value: numeric
Value(s) for which log CDF is calculated. If the log CDF for multiple
values are desired the values must be provided in a numpy array or theano tensor.
Value(s) for which log CDF is calculated.

Returns
-------
TensorVariable
"""
# incomplete_beta function can only handle scalar values (see #4342)
if np.ndim(value):
raise TypeError(
"StudentT.logcdf expects a scalar value but received a {}-dimensional object.".format(
np.ndim(value)
)
)

nu = self.nu
mu = self.mu
sigma = self.sigma
lam = self.lam
t = (value - mu) / sigma
sqrt_t2_nu = tt.sqrt(t ** 2 + nu)
x = (t + sqrt_t2_nu) / (2.0 * sqrt_t2_nu)
return tt.log(incomplete_beta(nu / 2.0, nu / 2.0, x))

return bound(
tt.log(incomplete_beta(nu / 2.0, nu / 2.0, x)),
0 < nu,
0 < sigma,
0 < lam,
)


class Pareto(Continuous):
Expand Down Expand Up @@ -2090,7 +2119,7 @@ def logcdf(self, value):

Parameters
----------
value: numeric
value: numeric or np.ndarray or theano.tensor
Value(s) for which log CDF is calculated. If the log CDF for multiple
values are desired the values must be provided in a numpy array or theano tensor.

Expand Down Expand Up @@ -2209,7 +2238,7 @@ def logcdf(self, value):

Parameters
----------
value: numeric
value: numeric or np.ndarray or theano.tensor
Value(s) for which log CDF is calculated. If the log CDF for multiple
values are desired the values must be provided in a numpy array or theano tensor.

Expand Down Expand Up @@ -2317,7 +2346,7 @@ def logcdf(self, value):

Parameters
----------
value: numeric
value: numeric or np.ndarray or theano.tensor
Value(s) for which log CDF is calculated. If the log CDF for multiple
values are desired the values must be provided in a numpy array or theano tensor.

Expand Down Expand Up @@ -2468,7 +2497,7 @@ def logcdf(self, value):

Parameters
----------
value: numeric
value: numeric or np.ndarray or theano.tensor
Value(s) for which log CDF is calculated. If the log CDF for multiple
values are desired the values must be provided in a numpy array or theano tensor.

Expand All @@ -2478,7 +2507,17 @@ def logcdf(self, value):
"""
alpha = self.alpha
beta = self.beta
return bound(tt.log(tt.gammainc(alpha, beta * value)), value >= 0, alpha > 0, beta > 0)
# To avoid gammainc C-assertion when given invalid values (#4340)
safe_alpha = tt.switch(tt.lt(alpha, 0), 0, alpha)
safe_beta = tt.switch(tt.lt(beta, 0), 0, beta)
safe_value = tt.switch(tt.lt(value, 0), 0, value)

return bound(
tt.log(tt.gammainc(safe_alpha, safe_beta * safe_value)),
0 <= value,
0 < alpha,
0 < beta,
)

def _distr_parameters_for_repr(self):
return ["alpha", "beta"]
Expand Down Expand Up @@ -2632,7 +2671,7 @@ def logcdf(self, value):

Parameters
----------
value: numeric
value: numeric or np.ndarray or theano.tensor
Value(s) for which log CDF is calculated. If the log CDF for multiple
values are desired the values must be provided in a numpy array or theano tensor.

Expand All @@ -2642,11 +2681,16 @@ def logcdf(self, value):
"""
alpha = self.alpha
beta = self.beta
# To avoid gammaincc C-assertion when given invalid values (#4340)
safe_alpha = tt.switch(tt.lt(alpha, 0), 0, alpha)
safe_beta = tt.switch(tt.lt(beta, 0), 0, beta)
safe_value = tt.switch(tt.lt(value, 0), 0, value)

return bound(
tt.log(tt.gammaincc(alpha, beta / value)),
value >= 0,
alpha > 0,
beta > 0,
tt.log(tt.gammaincc(safe_alpha, safe_beta / safe_value)),
0 <= value,
0 < alpha,
0 < beta,
)


Expand Down Expand Up @@ -2814,7 +2858,7 @@ def logcdf(self, value):

Parameters
----------
value: numeric
value: numeric or np.ndarray or theano.tensor
Value(s) for which log CDF is calculated. If the log CDF for multiple
values are desired the values must be provided in a numpy array or theano tensor.

Expand Down Expand Up @@ -3114,7 +3158,7 @@ def logcdf(self, value):

Parameters
----------
value: numeric
value: numeric or np.ndarray or theano.tensor
Value(s) for which log CDF is calculated. If the log CDF for multiple
values are desired the values must be provided in a numpy array or theano tensor.

Expand Down Expand Up @@ -3503,7 +3547,7 @@ def logcdf(self, value):

Parameters
----------
value: numeric
value: numeric or np.ndarray or theano.tensor
Value(s) for which log CDF is calculated. If the log CDF for multiple
values are desired the values must be provided in a numpy array or theano tensor.

Expand Down Expand Up @@ -3632,7 +3676,7 @@ def logcdf(self, value):

Parameters
----------
value: numeric
value: numeric or np.ndarray or theano.tensor
Value(s) for which log CDF is calculated. If the log CDF for multiple
values are desired the values must be provided in a numpy array or theano tensor.

Expand Down Expand Up @@ -3914,7 +3958,7 @@ def logcdf(self, value):

Parameters
----------
value: numeric
value: numeric or np.ndarray or theano.tensor
Value(s) for which log CDF is calculated. If the log CDF for multiple
values are desired the values must be provided in a numpy array or theano tensor.

Expand Down Expand Up @@ -4256,7 +4300,7 @@ def logcdf(self, value):

Parameters
----------
value: numeric
value: numeric or np.ndarray or theano.tensor
Value(s) for which log CDF is calculated. If the log CDF for multiple
values are desired the values must be provided in a numpy array or theano tensor.

Expand Down
12 changes: 6 additions & 6 deletions pymc3/distributions/discrete.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -463,7 +463,7 @@ def logcdf(self, value):

Parameters
----------
value: numeric
value: numeric or np.ndarray or theano.tensor
Value(s) for which log CDF is calculated. If the log CDF for multiple
values are desired the values must be provided in a numpy array or theano tensor.

Expand Down Expand Up @@ -602,7 +602,7 @@ def logcdf(self, value):

Parameters
----------
value: numeric
value: numeric or np.ndarray or theano.tensor
Value(s) for which log CDF is calculated. If the log CDF for multiple
values are desired the values must be provided in a numpy array or theano tensor.

Expand Down Expand Up @@ -717,7 +717,7 @@ def logcdf(self, value):

Parameters
----------
value: numeric
value: numeric or np.ndarray or theano.tensor
Value(s) for which log CDF is calculated. If the log CDF for multiple
values are desired the values must be provided in a numpy array or theano tensor.

Expand Down Expand Up @@ -1017,7 +1017,7 @@ def logcdf(self, value):

Parameters
----------
value: numeric
value: numeric or np.ndarray or theano.tensor
Value(s) for which log CDF is calculated. If the log CDF for multiple
values are desired the values must be provided in a numpy array or theano tensor.

Expand Down Expand Up @@ -1288,7 +1288,7 @@ def logcdf(self, value):

Parameters
----------
value: numeric
value: numeric or np.ndarray or theano.tensor
Value(s) for which log CDF is calculated. If the log CDF for multiple
values are desired the values must be provided in a numpy array or theano tensor.

Expand Down Expand Up @@ -1601,7 +1601,7 @@ def logcdf(self, value):

Parameters
----------
value: numeric
value: numeric or np.ndarray or theano.tensor
Value(s) for which log CDF is calculated. If the log CDF for multiple
values are desired the values must be provided in a numpy array or theano tensor.

Expand Down
Loading