Support categorical and linearregression

Author: yuta-nakahara

bayesml/bernoulli/_bernoulli.py

@@ -290,6 +290,9 @@ def get_hn_params(self):
         """
         return {"hn_alpha":self.hn_alpha, "hn_beta":self.hn_beta}
 
+    def _check_sample(self,x):
+        return _check.ints_of_01(x,'x',DataFormatError)
+
     def update_posterior(self,x):
         """Update the hyperparameters of the posterior distribution using traning data.
 
@@ -298,7 +301,7 @@ def update_posterior(self,x):
         x : numpy.ndarray
             All the elements must be 0 or 1.
         """
-        _check.ints_of_01(x,'x',DataFormatError)
+        x = self._check_sample(x)
         self.hn_alpha += np.count_nonzero(x==1)
         self.hn_beta += np.count_nonzero(x==0)
         return self

bayesml/categorical/_categorical.py

@@ -321,6 +321,22 @@ def get_hn_params(self):
         """
         return {"hn_alpha_vec": self.hn_alpha_vec}
 
+    # default onehot option is False because it is used in metatree
+    def _check_sample(self,x,onehot=False):
+        if onehot:
+            _check.onehot_vecs(x,'x',DataFormatError)
+            if x.shape[-1] != self.c_degree:
+                raise(DataFormatError(f"x.shape[-1] must be c_degree:{self.c_degree}"))
+            return x.reshape(-1,self.c_degree)
+        else:
+            _check.nonneg_ints(x,'x',DataFormatError)
+            if np.max(x) >= self.c_degree:
+                raise(DataFormatError(
+                    'np.max(x) must be smaller than self.c_degree: '
+                    +f'np.max(x) = {np.max(x)}, self.c_degree = {self.c_degree}'
+                ))
+            return x
+
     def update_posterior(self,x,onehot=True):
         """Update the hyperparameters of the posterior distribution using traning data.
 
@@ -336,22 +352,12 @@ def update_posterior(self,x,onehot=True):
             If True, the input sample must be one-hot encoded, 
             by default True.
         """
+        x = self._check_sample(x,onehot)
         if onehot:
-            _check.onehot_vecs(x,'x',DataFormatError)
-            if x.shape[-1] != self.c_degree:
-                raise(DataFormatError(f"x.shape[-1] must be c_degree:{self.c_degree}"))
-            x = x.reshape(-1,self.c_degree)
             self.hn_alpha_vec[:] += x.sum(axis=0)
         else:
-            _check.nonneg_ints(x,'x',DataFormatError)
-            if np.max(x) >= self.c_degree:
-                raise(DataFormatError(
-                    'np.max(x) must be smaller than self.c_degree: '
-                    +f'np.max(x) = {np.max(x)}, self.c_degree = {self.c_degree}'
-                ))
             for k in range(self.c_degree):
                 self.hn_alpha_vec[k] += np.count_nonzero(x==k)
-
         return self
 
     def _update_posterior(self,x):
@@ -396,7 +402,10 @@ def estimate_params(self, loss="squared",dict_out=False):
                     return (self.hn_alpha_vec - 1) / (np.sum(self.hn_alpha_vec) - self.c_degree)
             else:
                 warnings.warn("MAP estimate of lambda_mat doesn't exist for the current hn_alpha_vec.",ResultWarning)
-                return None
+                if dict_out:
+                    return {'theta_vec':None}
+                else:
+                    return None
         elif loss == "KL":
             return ss_dirichlet(alpha=self.hn_alpha_vec)
         else:
@@ -476,6 +485,9 @@ def calc_pred_dist(self):
         """Calculate the parameters of the predictive distribution."""
         self.p_theta_vec[:] = self.hn_alpha_vec / self.hn_alpha_vec.sum()
         return self
+    
+    def _calc_pred_density(self,x):
+        return self.p_theta_vec[x]
 
     def make_prediction(self,loss="squared",onehot=True):
         """Predict a new data point under the given criterion.

bayesml/exponential/_exponential.py

@@ -292,6 +292,9 @@ def get_hn_params(self):
         """
         return {"hn_alpha":self.hn_alpha, "hn_beta":self.hn_beta}
 
+    def _check_sample(self,x):
+        return _check.pos_floats(x, 'x', DataFormatError)
+
     def update_posterior(self,x):
         """Update the hyperparameters of the posterior distribution using traning data.
 
@@ -300,7 +303,7 @@ def update_posterior(self,x):
         x : numpy.ndarray
             All the elements must be positive real numbers.
         """
-        _check.pos_floats(x, 'x', DataFormatError)
+        x = self._check_sample(x)
         try:
             self.hn_alpha += x.size
         except:

bayesml/linearregression/_linearregression.py

@@ -501,6 +501,24 @@ def get_hn_params(self):
         """
         return {"hn_mu_vec":self.hn_mu_vec, "hn_lambda_mat":self.hn_lambda_mat, "hn_alpha":self.hn_alpha, "hn_beta":self.hn_beta}
 
+    def _check_sample_x(self,x):
+        _check.float_vecs(x,'x',DataFormatError)
+        if x.shape[-1] != self.c_degree:
+            raise(DataFormatError(f"x.shape[-1] must be c_degree:{self.c_degree}"))
+
+    def _check_sample_y(self,y):
+        _check.floats(y,'y',DataFormatError)
+
+    def _check_sample(self,x,y):
+        self._check_sample_x(x)
+        self._check_sample_y(y)
+        if type(y) is np.ndarray:
+            if x.shape[:-1] != y.shape: 
+                raise(DataFormatError(f"x.shape[:-1] and y.shape must be same."))
+        elif x.shape[:-1] != ():
+            raise(DataFormatError(f"If y is a scaler, x.shape[:-1] must be the empty tuple ()."))
+        return x.reshape(-1,self.c_degree), np.ravel(y)
+
     def update_posterior(self, x, y):
         """Update the hyperparameters of the posterior distribution using traning data.
 
@@ -512,18 +530,7 @@ def update_posterior(self, x, y):
         y : numpy ndarray
             float array.
         """
-        _check.float_vecs(x,'x',DataFormatError)
-        if x.shape[-1] != self.c_degree:
-            raise(DataFormatError(f"x.shape[-1] must be c_degree:{self.c_degree}"))
-        _check.floats(y,'y',DataFormatError)
-        if type(y) is np.ndarray:
-            if x.shape[:-1] != y.shape: 
-                raise(DataFormatError(f"x.shape[:-1] and y.shape must be same."))
-        elif x.shape[:-1] != ():
-            raise(DataFormatError(f"If y is a scaler, x.shape[:-1] must be the empty tuple ()."))
-            
-        x = x.reshape(-1,self.c_degree)
-        y = np.ravel(y)
+        x,y = self._check_sample(x,y)            
 
         hn1_Lambda = np.array(self.hn_lambda_mat)
         hn1_mu = np.array(self.hn_mu_vec)
@@ -536,6 +543,8 @@ def update_posterior(self, x, y):
 
     def _update_posterior(self, x, y):
         """Update opsterior without input check."""
+        x = x.reshape(-1,self.c_degree)
+        y = np.ravel(y)
         hn1_Lambda = np.array(self.hn_lambda_mat)
         hn1_mu = np.array(self.hn_mu_vec)
         self.hn_lambda_mat +=  x.T @ x
@@ -703,6 +712,16 @@ def calc_pred_dist(self, x):
         self.p_nu = 2.0 * self.hn_alpha
         return self
 
+    def _calc_pred_dist(self, x):
+        """Calculate predictive distribution without check."""
+        self.p_m = x @ self.hn_mu_vec
+        self.p_lambda = self.hn_alpha / self.hn_beta / (1.0 + x @ np.linalg.solve(self.hn_lambda_mat,x))
+        self.p_nu = 2.0 * self.hn_alpha
+        return self
+
+    def _calc_pred_density(self,y):
+        return ss_t.pdf(y,loc=self.p_m, scale=1.0/np.sqrt(self.p_lambda), df=self.p_nu)
+    
     def make_prediction(self,loss="squared"):
         """Predict a new data point under the given criterion.