Remove size parameter from sample_posterior_predictive

Author: ricardoV94

pymc/sampling.py

@@ -58,7 +58,7 @@
 
 import pymc as pm
 
-from pymc.aesaraf import change_rv_size, compile_pymc
+from pymc.aesaraf import compile_pymc
 from pymc.backends.arviz import _DefaultTrace
 from pymc.backends.base import BaseTrace, MultiTrace
 from pymc.backends.ndarray import NDArray
@@ -1688,7 +1688,6 @@ def sample_posterior_predictive(
     samples: Optional[int] = None,
     model: Optional[Model] = None,
     var_names: Optional[List[str]] = None,
-    size: Optional[int] = None,
     keep_size: Optional[bool] = None,
     random_seed=None,
     progressbar: bool = True,
@@ -1721,13 +1720,9 @@ def sample_posterior_predictive(
         generally be the model used to generate the ``trace``, but it doesn't need to be.
     var_names : Iterable[str]
         Names of variables for which to compute the posterior predictive samples.
-    size : int
-        The number of random draws from the distribution specified by the parameters in each
-        sample of the trace. Not recommended unless more than ndraws times nchains posterior
-        predictive samples are needed.
     keep_size : bool, default True
         Force posterior predictive sample to have the same shape as posterior and sample stats
-        data: ``(nchains, ndraws, ...)``. Overrides samples and size parameters.
+        data: ``(nchains, ndraws, ...)``. Overrides samples parameter.
     random_seed : int
         Seed for the random number generator.
     progressbar : bool
@@ -1806,8 +1801,6 @@ def sample_posterior_predictive(
             "Should not specify both keep_size and samples arguments. "
             "See the docstring of the samples argument for more details."
         )
-    if keep_size and size is not None:
-        raise IncorrectArgumentsError("Should not specify both keep_size and size arguments")
 
     if samples is None:
         if isinstance(_trace, MultiTrace):
@@ -1867,8 +1860,6 @@ def sample_posterior_predictive(
             return trace
         return {}
 
-    if size is not None:
-        vars_to_sample = [change_rv_size(v, size, expand=True) for v in vars_to_sample]
     vars_in_trace = get_vars_in_point_list(_trace, model)
 
     if compile_kwargs is None:

pymc/tests/test_sampling.py

@@ -536,13 +536,6 @@ def test_normal_scalar(self):
             _, pval = stats.kstest(ppc["a"] - trace["mu"], stats.norm(loc=0, scale=1).cdf)
             assert pval > 0.001
 
-        # size argument not introduced to fast version [2019/08/20:rpg]
-        with model:
-            ppc = pm.sample_posterior_predictive(
-                trace, size=5, var_names=["a"], return_inferencedata=False
-            )
-            assert ppc["a"].shape == (nchains * ndraws, 5)
-
     def test_normal_scalar_idata(self):
         nchains = 2
         ndraws = 500
@@ -599,13 +592,6 @@ def test_normal_vector(self, caplog):
             assert "a" in ppc
             assert ppc["a"].shape == (12, 2)
 
-            # size unsupported by fast_ version  argument. [2019/08/19:rpg]
-            ppc = pm.sample_posterior_predictive(
-                trace, return_inferencedata=False, samples=10, var_names=["a"], size=4
-            )
-            assert "a" in ppc
-            assert ppc["a"].shape == (10, 4, 2)
-
     def test_normal_vector_idata(self, caplog):
         with pm.Model() as model:
             mu = pm.Normal("mu", 0.0, 1.0)
@@ -632,9 +618,6 @@ def test_exceptions(self, caplog):
             with pytest.raises(IncorrectArgumentsError):
                 ppc = pm.sample_posterior_predictive(idata, samples=10, keep_size=True)
 
-            with pytest.raises(IncorrectArgumentsError):
-                ppc = pm.sample_posterior_predictive(idata, size=4, keep_size=True)
-
             # test wrong type argument
             bad_trace = {"mu": stats.norm.rvs(size=1000)}
             with pytest.raises(TypeError, match="type for `trace`"):
@@ -658,12 +641,6 @@ def test_vector_observed(self):
             assert "a" in ppc
             assert ppc["a"].shape == (12, 2)
 
-            ppc = pm.sample_posterior_predictive(
-                idata, return_inferencedata=False, samples=10, var_names=["a"], size=4
-            )
-            assert "a" in ppc
-            assert ppc["a"].shape == (10, 4, 2)
-
     def test_sum_normal(self):
         with pm.Model() as model:
             a = pm.Normal("a", sigma=0.2)