Changes in test for random kwarg in DensityDist (#2840)

* Added test

* Test scipy distribution compatibility with DensityDist

* Updated RELEASE-NOTES.md

* Changes in test for random method in DensityDist

* Added docstring for DensityDist

* Update tests for random method with DensityDist

Author: Vaibhavdixit02

RELEASE-NOTES.md

@@ -4,6 +4,7 @@
 
 ### New features
 
+<<<<<<< refs/remotes/pymc-devs/master
 - Add `logit_p` keyword to `pm.Bernoulli`, so that users can specify the logit of the success probability. This is faster and more stable than using `p=tt.nnet.sigmoid(logit_p)`.
 - Add `random` keyword to `pm.DensityDist` thus enabling users to pass custom random method which in turn makes sampling from a `DensityDist` possible.
 - Effective sample size computation is updated. The estimation uses Geyer's initial positive sequence, which no longer truncates the autocorrelation series inaccurately. `pm.diagnostics.effective_n` now can reports N_eff>N.
@@ -19,6 +20,18 @@
 - The bandwidth for KDE plots is computed using a modified version of Scott's rule. The new version uses entropy instead of standard
 deviation. This works better for multimodal distributions. Functions using KDE plots has a new argument `bw` controlling the bandwidth.
 
+=======
+- Add `logit_p` keyword to `pm.Bernoulli`, so that users can specify the logit
+  of the success probability. This is faster and more stable than using
+  `p=tt.nnet.sigmoid(logit_p)`.
+- Add `random` keyword to `pm.DensityDist` thus enabling users to pass custom random method
+  which in turn makes sampling from a `DensityDist` possible. 
+
+### Fixes
+
+- `VonMises` does not overflow for large values of kappa. i0 and i1 have been removed and we now use
+   log_i0 to compute the logp.
+>>>>>>> Changes in test for random method in DensityDist
 
 ### Deprecations
 

pymc3/distributions/distribution.py

@@ -176,7 +176,22 @@ def __init__(self, shape=(), dtype=None, defaults=('median', 'mean', 'mode'),
 
 
 class DensityDist(Distribution):
-    """Distribution based on a given log density function."""
+    """Distribution based on a given log density function.
+        
+        A distribution with the passed log density function is created. 
+        Requires a custom random function passed as kwarg `random` to
+        enable sampling.
+
+        Example:
+        --------
+        .. code-block:: python
+            with pm.Model():
+                mu = pm.Normal('mu',0,1)
+                normal_dist = pm.Normal.dist(mu, 1)
+                pm.DensityDist('density_dist', normal_dist.logp, observed=np.random.randn(100), random=normal_dist.random)
+                trace = pm.sample(100)
+
+    """
 
     def __init__(self, logp, shape=(), dtype=None, testval=0, random=None, *args, **kwargs):
         if dtype is None:

pymc3/tests/test_distributions_random.py

@@ -741,46 +741,25 @@ def ref_rand(size, w, mu, sd):
                      size=1000,
                      ref_rand=ref_rand)
 
-    def test_density_dist(self):
-        def ref_rand(size, mu, sd):
-            return st.norm.rvs(size=size, loc=mu, scale=sd)
-        
-        class TestDensityDist(pm.DensityDist):
-
-            def __init__(self, **kwargs):
-                norm_dist = pm.Normal.dist()
-                super(TestDensityDist, self).__init__(logp=norm_dist.logp, random=norm_dist.random)
-
-        pymc3_random(TestDensityDist, {},ref_rand=ref_rand)
-
-        def check_model_samplability(self):
-            model = pm.Model()
-            with model:
-                normal_dist = pm.Normal.dist()
-                density_dist = pm.DensityDist('density_dist', normal_dist.logp, random=normal_dist.random)
-                step = pm.Metropolis()
-                trace = pm.sample(100, step, tuning=0)
-
-            try:
-                ppc = pm.sample_ppc(trace, samples=500, model=model, size=100)
-                if len(ppc) == 0:
-                    npt.assert_true(len(ppc) == 0, 'length of ppc sample is zero')
-            except:
-                assert False
-
-        def check_scipy_distributions(self):
-            model = pm.Model()
-            with model:
-                norm_dist_logp = st.norm.logpdf
-                norm_dist_random = np.random.normal
-                density_dist = pm.DensityDist('density_dist', normal_dist_logp, random=normal_dist_random)
-                step = pm.Metropolis()
-                trace = pm.sample(100, step, tuning=0)
-
-            try:
-                ppc = pm.sample_ppc(trace, samples=500, model=model, size=100)
-                if len(ppc) == 0:
-                    npt.assert_true(len(ppc) == 0, 'length of ppc sample is zero')
-            except:
-                assert False
-            
+def test_density_dist_with_random_sampleable():
+    with pm.Model() as model:
+        mu = pm.Normal('mu',0,1)
+        normal_dist = pm.Normal.dist(mu, 1)
+        pm.DensityDist('density_dist', normal_dist.logp, observed=np.random.randn(100), random=normal_dist.random)
+        trace = pm.sample(100)
+
+    samples = 500
+    ppc = pm.sample_ppc(trace, samples=samples, model=model, size=100)
+    assert len(ppc['density_dist']) == samples
+
+
+def test_density_dist_without_random_not_sampleable():
+    with pm.Model() as model:
+        mu = pm.Normal('mu',0,1)
+        normal_dist = pm.Normal.dist(mu, 1)
+        pm.DensityDist('density_dist', normal_dist.logp, observed=np.random.randn(100))
+        trace = pm.sample(100)
+
+    samples = 500
+    with pytest.raises(ValueError):
+        pm.sample_ppc(trace, samples=samples, model=model, size=100)