Revise documents

Author: yuta-nakahara

bayesml/metatree/__init__.py

@@ -4,20 +4,19 @@
 r"""
 The stochastic data generative model is as follows:
 
-* :math:`\mathcal{X}` : a space of an explanatory variable (a finite set)
-* :math:`\boldsymbol{x}=[x_1, \ldots, x_d] \in \mathcal{X}^d` : an explanatory variable
+* :math:`\boldsymbol{x}=[x_1, \ldots, x_p, x_{p+1}, \ldots , x_{p+q}]` : an explanatory variable. The first :math:`p` variables are continuous. The other :math:`q` variables are categorical. 
 * :math:`\mathcal{Y}` : a space of an objective variable
 * :math:`y \in \mathcal{Y}` : an objective variable
 * :math:`D_\mathrm{max} \in \mathbb{N}` : the maximum depth of trees
-* :math:`T` : :math:`|\mathcal{X}|`-ary regular tree whose depth is smaller than or equal to :math:`D_\mathrm{max}`, where "regular" means that all inner nodes have :math:`k` child nodes.
+* :math:`T` : a tree whose depth is smaller than or equal to :math:`D_\mathrm{max}`
 * :math:`\mathcal{T}` : a set of :math:`T`
 * :math:`s` : a node of a tree
 * :math:`\mathcal{S}` : a set of :math:`s`
 * :math:`\mathcal{I}(T)` : a set of inner nodes of :math:`T`
 * :math:`\mathcal{L}(T)` : a set of leaf nodes of :math:`T`
-* :math:`\boldsymbol{k}=(k_s)_{s \in \mathcal{S}}` : feature assign vector where :math:`k_s \in \{1,2,\ldots,d\}`
+* :math:`\boldsymbol{k}=(k_s)_{s \in \mathcal{S}}` : feature assignmet vector where :math:`k_s \in \{1, 2,\ldots,p+q\}`. If :math:`k_s \leq p`, the node :math:`s` has a threshold.
 * :math:`\boldsymbol{\theta}=(\theta_s)_{s \in \mathcal{S}}` : a set of parameter
-* :math:`s(\boldsymbol{x}) \in \mathcal{L}(T)` : a leaf node of :math:`T` corresponding to :math:`\boldsymbol{x}`
+* :math:`s(\boldsymbol{x}) \in \mathcal{L}(T)` : a leaf node of :math:`T` corresponding to :math:`\boldsymbol{x}`, which is determined according to :math:`\boldsymbol{k}` and the thresholds.
 
 .. math::
     p(y | \boldsymbol{x}, \boldsymbol{\theta}, T, \boldsymbol{k})=p(y | \theta_{s(\boldsymbol{x})})

bayesml/metatree/_metatree.py

@@ -90,7 +90,7 @@ class GenModel(base.Generative):
         ``c_dim_continuous+c_dim_categorical``, by default [2,2,...,2].
         The first ``c_dim_continuous`` elements represent 
         the numbers of children of continuous features at 
-        inner nodes. The rest ``c_dim_categorial`` elements 
+        inner nodes. The other ``c_dim_categorial`` elements 
         represent those of categorical features.
         If a single integer is input, it will be broadcasted.
     c_max_depth : int, optional
@@ -100,7 +100,7 @@ class GenModel(base.Generative):
         ``c_dim_continuous+c_dim_categorical``. 
         The first ``c_dim_continuous`` elements represent 
         the maximum assignment numbers of continuous features 
-        on a path. The rest ``c_dim_categorial`` elements 
+        on a path. The other ``c_dim_categorial`` elements 
         represent those of categorical features.
         By default [c_max_depth,...,c_max_depth,1,...,1].
     c_ranges : numpy.ndarray, optional
@@ -928,6 +928,8 @@ def _plot_2d_threshold_recursion_categorical(self,ax,node:_Node,categorical_inde
     def visualize_model(self,filename=None,format=None,sample_size=100,x_continuous=None,x_categorical=None):
         """Visualize the stochastic data generative model and generated samples.
 
+        Note that values of categorical features will be shown with jitters.
+
         Parameters
         ----------
         filename : str, optional
@@ -1047,7 +1049,7 @@ class LearnModel(base.Posterior,base.PredictiveMixin):
         ``c_dim_continuous+c_dim_categorical``, by default [2,2,...,2].
         The first ``c_dim_continuous`` elements represent 
         the numbers of children of continuous features at 
-        inner nodes. The rest ``c_dim_categorial`` elements 
+        inner nodes. The other ``c_dim_categorial`` elements 
         represent those of categorical features.
         If a single integer is input, it will be broadcasted.
     c_max_depth : int, optional
@@ -1057,7 +1059,7 @@ class LearnModel(base.Posterior,base.PredictiveMixin):
         ``c_dim_continuous+c_dim_categorical``. 
         The first ``c_dim_continuous`` elements represent 
         the maximum assignment numbers of continuous features 
-        on a path. The rest ``c_dim_categorial`` elements 
+        on a path. The other ``c_dim_categorial`` elements 
         represent those of categorical features.
         By default [c_max_depth,...,c_max_depth,1,...,1].
     c_ranges : numpy.ndarray, optional
@@ -2014,6 +2016,10 @@ def _copy_map_tree_recursion(self,copied_node:_Node,original_node:_Node):
     def estimate_params(self,loss="0-1",visualize=True,filename=None,format=None):
         """Estimate the parameter under the given criterion.
 
+        The approximate MAP meta-tree 
+        :math:`M_{T,\boldsymbol{k}_b} = \mathrm{argmax} p(M_{T,\boldsymbol{k}_{b'}} | \boldsymbol{x}^n, y^n)` 
+        will be returned.
+
         Parameters
         ----------
         loss : str, optional