revise hparams of bernoulli

Author: yuta-nakahara

bayesml/base.py

@@ -17,7 +17,7 @@ def get_h_params(self):
     def save_h_params(self,filename):
         """Save the hyperparameters using python ``pickle`` module.
 
-        They are saved as a python dictionary obtained by ``get_h_params()``.
+        They are saved as a python dictionary obtained by ``GenModel.get_h_params()``.
 
         Parameters
         ----------
@@ -43,8 +43,8 @@ def load_h_params(self,filename):
         filename : str
             The filename (including a extention like .pkl) to be loaded.
             It must be a pickled python dictionary obtained by
-            ``save_h_params()`` of GenModel, ``save_h0_params()`` of LearnModel 
-            or ``save_hn_params()`` of LearnModel.
+            ``GenModel.save_h_params()``, ``LearnModel.save_h0_params()`` 
+            or ``LearnModel.save_hn_params()``.
 
         Warnings
         --------
@@ -57,13 +57,13 @@ def load_h_params(self,filename):
         with open(filename, 'rb') as f:
             tmp_h_params = pickle.load(f)
         if type(tmp_h_params) is dict:
-            self.set_h_params(**tmp_h_params)
+            self.set_h_params(*tmp_h_params.values())
             return
 
         raise(ParameterFormatError(
-            filename+" must be a pickled python dictionary with "
-            +str(self.get_h_params().keys())
-            +", where `h_`, `h0_`, and `hn_` can be replaced to each other.")
+            filename+" must be a pickled python dictionary obtained by "
+            +"``GenModel.save_h_params()``, ``LearnModel.save_h0_params()`` "
+            +'or ``LearnModel.save_hn_params()``.')
             )
 
     @abstractmethod
@@ -81,7 +81,7 @@ def get_params(self):
     def save_params(self,filename):
         """Save the parameters using python ``pickle`` module.
 
-        They are saved as a pickled python dictionary obtained by ``get_params()``.
+        They are saved as a pickled python dictionary obtained by ``GenModel.get_params()``.
 
         Parameters
         ----------
@@ -106,7 +106,7 @@ def load_params(self,filename):
         ----------
         filename : str
             The filename (including a extention like .pkl) to be loaded.
-            It must be a pickled python dictionary with keys obtained by ``get_params().keys()``.
+            It must be a pickled python dictionary obtained by ``GenModel.save_params()``.
 
         Warnings
         --------
@@ -119,11 +119,10 @@ def load_params(self,filename):
         with open(filename, 'rb') as f:
             params = pickle.load(f)
         if type(params) is dict:
-            if params.keys() == self.get_params().keys():
-                self.set_params(**params)
-                return
+            self.set_params(*params.values())
+            return
 
-        raise(ParameterFormatError(filename+" must be a pickled python dictionary with "+str(self.get_params().keys())))
+        raise(ParameterFormatError(filename+" must be a pickled python dictionary obtained by ``GenModel.save_params()``"))
 
     @abstractmethod
     def gen_sample(self):
@@ -149,7 +148,7 @@ def get_h0_params(self):
     def save_h0_params(self,filename):
         """Save the hyperparameters using python ``pickle`` module.
 
-        They are saved as a pickled python dictionary obtained by ``get_h0_params()``.
+        They are saved as a pickled python dictionary obtained by ``LearnModel.get_h0_params()``.
 
         Parameters
         ----------
@@ -175,8 +174,8 @@ def load_h0_params(self,filename):
         filename : str
             The filename (including a extention like .pkl) to be loaded.
             It must be a pickled python dictionary obtained by
-            ``save_h_params()`` of GenModel, ``save_h0_params()`` of LearnModel 
-            or ``save_hn_params()`` of LearnModel.
+            ``GenModel.save_h_params()``, ``LearnModel.save_h0_params()`` 
+            or ``LearnModel.save_hn_params()``.
 
         Warnings
         --------
@@ -189,13 +188,13 @@ def load_h0_params(self,filename):
         with open(filename, 'rb') as f:
             tmp_h_params = pickle.load(f)
         if type(tmp_h_params) is dict:
-            self.set_h0_params(**tmp_h_params)
+            self.set_h0_params(*tmp_h_params.values())
             return
 
         raise(ParameterFormatError(
-            filename+" must be a pickled python dictionary with "
-            +str(self.get_h0_params().keys())
-            +", where `h_`, `h0_`, and `hn_` can be replaced to each other.")
+            filename+" must be a pickled python dictionary obtained by "
+            +"``GenModel.save_h_params()``, ``LearnModel.save_h0_params()`` "
+            +'or ``LearnModel.save_hn_params()``.')
             )
 
     @abstractmethod
@@ -209,7 +208,7 @@ def get_hn_params(self):
     def save_hn_params(self,filename):
         """Save the hyperparameters using python ``pickle`` module.
 
-        They are saved as a pickled python dictionary obtained by ``get_hn_params()``.
+        They are saved as a pickled python dictionary obtained by ``LearnModel.get_hn_params()``.
 
         Parameters
         ----------
@@ -235,8 +234,8 @@ def load_hn_params(self,filename):
         filename : str
             The filename (including a extention like .pkl) to be loaded.
             It must be a pickled python dictionary obtained by
-            ``save_h_params()`` of GenModel, ``save_h0_params()`` of LearnModel 
-            or ``save_hn_params()`` of LearnModel.
+            ``GenModel.save_h_params()``, ``LearnModel.save_h0_params()`` 
+            or ``LearnModel.save_hn_params()``.
 
         Warnings
         --------
@@ -249,13 +248,13 @@ def load_hn_params(self,filename):
         with open(filename, 'rb') as f:
             tmp_h_params = pickle.load(f)
         if type(tmp_h_params) is dict:
-            self.set_hn_params(**tmp_h_params)
+            self.set_hn_params(*tmp_h_params.values())
             return
 
         raise(ParameterFormatError(
-            filename+" must be a pickled python dictionary with "
-            +str(self.get_hn_params().keys())
-            +", where `h_`, `h0_`, and `hn_` can be replaced to each other.")
+            filename+" must be a pickled python dictionary obtained by "
+            +"``GenModel.save_h_params()``, ``LearnModel.save_h0_params()`` "
+            +'or ``LearnModel.save_hn_params()``.')
             )
 
     @abstractmethod

bayesml/bernoulli/_bernoulli.py

@@ -32,37 +32,19 @@ def __init__(self,*,theta=0.5,h_alpha=0.5,h_beta=0.5,seed=None):
         self.h_alpha = _check.pos_float(h_alpha,'h_alpha',ParameterFormatError)
         self.h_beta = _check.pos_float(h_beta,'h_beta',ParameterFormatError)
         self.rng = np.random.default_rng(seed)
-        self._H_PARAM_KEYS = {'h_alpha','h_beta'}
-        self._H0_PARAM_KEYS = {'h0_alpha','h0_beta'}
-        self._HN_PARAM_KEYS = {'hn_alpha','hn_beta'}
 
-    def set_h_params(self,**kwargs):
+    def set_h_params(self,h_alpha,h_beta):
         """Set the hyperparameters of the prior distribution.
         
         Parameters
         ----------
-        **kwargs
-            a python dictionary {'h_alpha':float, 'h_beta':float} or
-            {'h0_alpha':float, 'h0_beta':float} or {'hn_alpha':float, 'hn_beta':float}
-            They are obtained by ``get_h_params()`` of GenModel,
-            ``get_h0_params`` of LearnModel or ``get_hn_params`` of LearnModel.
+        h_alpha : float
+            a positive real number
+        h_beta : float, optional
+            a positibe real number
         """
-        if kwargs.keys() == self._H_PARAM_KEYS:
-            self.h_alpha = _check.pos_float(kwargs['h_alpha'],'h_alpha',ParameterFormatError)
-            self.h_beta = _check.pos_float(kwargs['h_beta'],'h_beta',ParameterFormatError)
-        elif kwargs.keys() == self._H0_PARAM_KEYS:
-            self.h_alpha = _check.pos_float(kwargs['h0_alpha'],'h_alpha',ParameterFormatError)
-            self.h_beta = _check.pos_float(kwargs['h0_beta'],'h_beta',ParameterFormatError)
-        elif kwargs.keys() == self._HN_PARAM_KEYS:
-            self.h_alpha = _check.pos_float(kwargs['hn_alpha'],'h_alpha',ParameterFormatError)
-            self.h_beta = _check.pos_float(kwargs['hn_beta'],'h_beta',ParameterFormatError)
-        else:
-            raise(ParameterFormatError(
-                "The input of this function must be a python dictionary with keys:"
-                +str(self._H_PARAM_KEYS)+" or "
-                +str(self._H0_PARAM_KEYS)+" or "
-                +str(self._HN_PARAM_KEYS)+".")
-                )
+        self.h_alpha = _check.pos_float(h_alpha,'h_alpha',ParameterFormatError)
+        self.h_beta = _check.pos_float(h_beta,'h_beta',ParameterFormatError)
 
     def get_h_params(self):
         """Get the hyperparameters of the prior distribution.
@@ -207,37 +189,19 @@ def __init__(self,h0_alpha=0.5,h0_beta=0.5):
         self.hn_alpha = self.h0_alpha
         self.hn_beta = self.h0_beta
         self.p_theta = self.hn_alpha / (self.hn_alpha + self.hn_beta)
-        self._H_PARAM_KEYS = {'h_alpha','h_beta'}
-        self._H0_PARAM_KEYS = {'h0_alpha','h0_beta'}
-        self._HN_PARAM_KEYS = {'hn_alpha','hn_beta'}
 
-    def set_h0_params(self,**kwargs):
+    def set_h0_params(self,h0_alpha,h0_beta):
         """Set initial values of the hyperparameter of the posterior distribution.
         
         Parameters
         ----------
-        **kwargs
-            a python dictionary {'h_alpha':float, 'h_beta':float} or
-            {'h0_alpha':float, 'h0_beta':float} or {'hn_alpha':float, 'hn_beta':float}
-            They are obtained by ``get_h_params()`` of GenModel,
-            ``get_h0_params`` of LearnModel or ``get_hn_params`` of LearnModel.
+        h0_alpha : float
+            a positive real number
+        h0_beta : float
+            a positibe real number
         """
-        if kwargs.keys() == self._H_PARAM_KEYS:
-            self.h0_alpha = _check.pos_float(kwargs['h_alpha'],'h0_alpha',ParameterFormatError)
-            self.h0_beta = _check.pos_float(kwargs['h_beta'],'h0_beta',ParameterFormatError)
-        elif kwargs.keys() == self._H0_PARAM_KEYS:
-            self.h0_alpha = _check.pos_float(kwargs['h0_alpha'],'h0_alpha',ParameterFormatError)
-            self.h0_beta = _check.pos_float(kwargs['h0_beta'],'h0_beta',ParameterFormatError)
-        elif kwargs.keys() == self._HN_PARAM_KEYS:
-            self.h0_alpha = _check.pos_float(kwargs['hn_alpha'],'h0_alpha',ParameterFormatError)
-            self.h0_beta = _check.pos_float(kwargs['hn_beta'],'h0_beta',ParameterFormatError)
-        else:
-            raise(ParameterFormatError(
-                "The input of this function must be a python dictionary with keys:"
-                +str(self._H_PARAM_KEYS)+" or "
-                +str(self._H0_PARAM_KEYS)+" or "
-                +str(self._HN_PARAM_KEYS)+".")
-                )
+        self.h0_alpha = _check.pos_float(h0_alpha,'h0_alpha',ParameterFormatError)
+        self.h0_beta = _check.pos_float(h0_beta,'h0_beta',ParameterFormatError)
         self.reset_hn_params()
 
     def get_h0_params(self):
@@ -251,33 +215,18 @@ def get_h0_params(self):
         """
         return {"h0_alpha":self.h0_alpha, "h0_beta":self.h0_beta}
 
-    def set_hn_params(self,**kwargs):
+    def set_hn_params(self,hn_alpha,hn_beta):
         """Set updated values of the hyperparameter of the posterior distribution.
         
         Parameters
         ----------
-        **kwargs
-            a python dictionary {'h_alpha':float, 'h_beta':float} or
-            {'h0_alpha':float, 'h0_beta':float} or {'hn_alpha':float, 'hn_beta':float}
-            They are obtained by ``get_h_params()`` of GenModel,
-            ``get_h0_params`` of LearnModel or ``get_hn_params`` of LearnModel.
+        h0_alpha : float
+            a positive real number
+        h0_beta : float
+            a positibe real number
         """
-        if kwargs.keys() == self._H_PARAM_KEYS:
-            self.hn_alpha = _check.pos_float(kwargs['h_alpha'],'hn_alpha',ParameterFormatError)
-            self.hn_beta = _check.pos_float(kwargs['h_beta'],'hn_beta',ParameterFormatError)
-        elif kwargs.keys() == self._H0_PARAM_KEYS:
-            self.hn_alpha = _check.pos_float(kwargs['h0_alpha'],'hn_alpha',ParameterFormatError)
-            self.hn_beta = _check.pos_float(kwargs['h0_beta'],'hn_beta',ParameterFormatError)
-        elif kwargs.keys() == self._HN_PARAM_KEYS:
-            self.hn_alpha = _check.pos_float(kwargs['hn_alpha'],'hn_alpha',ParameterFormatError)
-            self.hn_beta = _check.pos_float(kwargs['hn_beta'],'hn_beta',ParameterFormatError)
-        else:
-            raise(ParameterFormatError(
-                "The input of this function must be a python dictionary with keys:"
-                +str(self._H_PARAM_KEYS)+" or "
-                +str(self._H0_PARAM_KEYS)+" or "
-                +str(self._HN_PARAM_KEYS)+".")
-                )
+        self.hn_alpha = _check.pos_float(hn_alpha,'hn_alpha',ParameterFormatError)
+        self.hn_beta = _check.pos_float(hn_beta,'hn_beta',ParameterFormatError)
         self.calc_pred_dist()
 
     def get_hn_params(self):

doc/devdoc/examples/h_params_test.py

@@ -0,0 +1,14 @@
+from bayesml import bernoulli
+
+model = bernoulli.GenModel(h_alpha=0.5,h_beta=0.3)
+params = model.get_params()
+model.save_params('tmp.pkl')
+print(params)
+
+model_2 = bernoulli.GenModel(theta=0.9,h_alpha=1.0,h_beta=1.0)
+print(model_2.get_params())
+# model_2.set_h_params(*h_params.values())
+# print(model_2.get_h_params())
+
+model_2.load_params('tmp.pkl')
+print(model_2.get_params())