[Modify] delete y_scale

zjuwss · Dec 27, 2023 · 0de6bec · 0de6bec
1 parent ef14f3a
commit 0de6bec
Show file tree

Hide file tree

Showing 2 changed files with 3 additions and 33 deletions.
diff --git a/src/gnnwr/datasets.py b/src/gnnwr/datasets.py
@@ -126,15 +126,13 @@ def scale(self, scale_fn=None, scale_params=None):
             self.x_scale_info = {"min": x_scale_params.data_min_, "max": x_scale_params.data_max_}
             self.x_data = x_scale_params.transform(pd.DataFrame(self.x_data, columns=self.x))
             self.y_scale_info = {"min": y_scale_params.data_min_, "max": y_scale_params.data_max_}
-            self.y_data = y_scale_params.transform(pd.DataFrame(self.y_data, columns=self.y))
         elif scale_fn == "standard_scale":
             self.scale_fn = "standard_scale"
             x_scale_params = scale_params[0]
             y_scale_params = scale_params[1]
             self.x_scale_info = {"mean": x_scale_params.mean_, "var": x_scale_params.var_}
             self.x_data = x_scale_params.transform(pd.DataFrame(self.x_data, columns=self.x))
             self.y_scale_info = {"mean": y_scale_params.mean_, "var": y_scale_params.var_}
-            self.y_data = y_scale_params.transform(pd.DataFrame(self.y_data, columns=self.y))
 
         self.getScaledDataframe()
 
@@ -160,16 +158,12 @@ def scale2(self, scale_fn, scale_params):
             self.scale_fn = "minmax_scale"
             x_scale_params = scale_params[0]
             y_scale_params = scale_params[1]
-            # self.x_data = self.x_data * (x_scale_params["max"] - x_scale_params["min"]) + x_scale_params["min"]
             self.x_data = (self.x_data - x_scale_params["min"]) / (x_scale_params["max"] - x_scale_params["min"])
-            self.y_data = (self.y_data - y_scale_params["min"]) / (y_scale_params["max"] - y_scale_params["min"])
         elif scale_fn == "standard_scale":
             self.scale_fn = "standard_scale"
             x_scale_params = scale_params[0]
             y_scale_params = scale_params[1]
-            # self.x_data = self.x_data * np.sqrt(x_scale_params["var"]) + x_scale_params["mean"]
             self.x_data = (self.x_data - x_scale_params['mean']) / np.sqrt(x_scale_params["var"])
-            self.y_data = (self.y_data - y_scale_params['mean']) / np.sqrt(y_scale_params["var"])
 
         self.getScaledDataframe()
 
@@ -184,7 +178,7 @@ def getScaledDataframe(self):
         scaledData = np.concatenate((self.x_data, self.y_data), axis=1)
         self.scaledDataframe = pd.DataFrame(scaledData, columns=columns)
 
-    def rescale(self, x, y):
+    def rescale(self, x):
         """
         rescale the data with the scale function and scale parameters
 
@@ -204,35 +198,12 @@ def rescale(self, x, y):
         """
         if self.scale_fn == "minmax_scale":
             x = np.multiply(x, self.x_scale_info["max"] - self.x_scale_info["min"]) + self.x_scale_info["min"]
-            y = np.multiply(y, self.y_scale_info["max"] - self.y_scale_info["min"]) + self.y_scale_info["min"]
         elif self.scale_fn == "standard_scale":
             x = np.multiply(x, np.sqrt(self.x_scale_info["var"])) + self.x_scale_info["mean"]
-            y = np.multiply(y, np.sqrt(self.y_scale_info["var"])) + self.y_scale_info["mean"]
         else:
             raise ValueError("invalid process_fn")
-        return x, y
-
-    def rescale_y(self, y):
-        """
-        rescale the dependent variable data
-
-        Parameters
-        ----------
-        y: numpy.ndarray
-            dependent variable data
+        return x
 
-        Returns
-        -------
-        y: numpy.ndarray
-            rescaled dependent variable data
-        """
-        if self.scale_fn == "minmax_scale":
-            y = np.multiply(y, self.y_scale_info["max"] - self.y_scale_info["min"]) + self.y_scale_info["min"]
-        elif self.scale_fn == "standard_scale":
-            y = np.multiply(y, np.sqrt(self.y_scale_info["var"])) + self.y_scale_info["mean"]
-        else:
-            raise ValueError("invalid process_fn")
-        return y
 
     def save(self, dirname):
         """

diff --git a/src/gnnwr/models.py b/src/gnnwr/models.py
@@ -519,7 +519,6 @@ def predict(self, dataset):
                 output = self._out(self._model(data).mul(coef.to(torch.float32)))
                 output = output.view(-1).cpu().detach().numpy()
                 result = np.append(result, output)
-        result = self._train_dataset.rescale_y(result)
         dataset.dataframe['pred_result'] = result
         dataset.pred_result = result
         return dataset.dataframe
@@ -769,7 +768,7 @@ def reg_result(self, filename=None, model_path=None, use_dict=False, only_return
         columns = columns + ["Pred_" + self._train_dataset.y[0]] + self._train_dataset.id
         result = pd.DataFrame(result, columns=columns)
         result[self._train_dataset.id] = result[self._train_dataset.id].astype(np.int32)
-        result["Pred_" + self._train_dataset.y[0]] = self._train_dataset.rescale_y(result["Pred_" + self._train_dataset.y[0]]).astype(np.float32)
+        result["Pred_" + self._train_dataset.y[0]] = result["Pred_" + self._train_dataset.y[0]].astype(np.float32)
         if only_return:
             return result
         if filename is not None: