Doc updates

Author: WardBrian

cmdstanpy/stanfit/vb.py

@@ -121,6 +121,15 @@ def stan_variable(self, var: str) -> np.ndarray:
         a leading axis added for the number of draws from the variational
         approximation.
 
+        * If the variable is a scalar variable, the return array has shape
+          ( draws, ).
+        * If the variable is a vector, the return array has shape
+          ( draws, len(vector))
+        * If the variable is a matrix, the return array has shape
+          ( draws, size(dim 1), size(dim 2) )
+        * If the variable is an array with N dimensions, the return array
+          has shape ( draws, size(dim 1), ..., size(dim N))
+
         This functionaltiy is also available via a shortcut using ``.`` -
         writing ``fit.a`` is a synonym for ``fit.stan_variable("a")``
 

docsrc/api.rst

@@ -62,6 +62,11 @@ CmdStanVB
 .. autoclass:: cmdstanpy.CmdStanVB
    :members:
 
+CmdStanLaplace
+==============
+
+.. autoclass:: cmdstanpy.CmdStanLaplace
+   :members:
 
 *********
 Functions

docsrc/users-guide/examples/VI as Sampler Inits.ipynb

@@ -64,7 +64,8 @@
     "The ADVI algorithm provides estimates of all model parameters.\n",
     "\n",
     "The `variational` method returns a `CmdStanVB` object, with method `stan_variables`, which\n",
-    "returns the approximate estimates of all model parameters as a Python dictionary."
+    "returns the approximat posterior samples of all model parameters as a Python dictionary. \n",
+    "Here, we report the approximate posterior mean."
    ]
   },
   {
@@ -73,7 +74,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "print(vb_fit.stan_variables())"
+    "vb_mean = {var: samples.mean(axis=0) for var, samples in vb_fit.stan_variables().items()}\n",
+    "print(vb_mean)"
    ]
   },
   {
@@ -93,9 +95,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "vb_vars = vb_fit.stan_variables()\n",
     "mcmc_vb_inits_fit = model.sample(\n",
-    "    data=data_file, inits=vb_vars, iter_warmup=75, seed=12345\n",
+    "    data=data_file, inits=vb_mean, iter_warmup=75, seed=12345\n",
     ")"
    ]
   },