delete old files

src/preprocessing.py

@@ -160,38 +160,29 @@ def custom_loss(
                 preprocess.scaler_type, scaler_type))
 
     if scaler_type == "minmax":
-        scale_X = tf.convert_to_tensor(
-            preprocess.scaler_X.data_range_, dtype=tf.float32
+        data_range = tf.convert_to_tensor(
+            preprocess.scaler_output.data_range_, dtype=tf.float32
         )
-        min_X = tf.convert_to_tensor(
-            preprocess.scaler_X.data_min_, dtype=tf.float32
-        )
-        scale_y = tf.convert_to_tensor(
-            preprocess.scaler_y.data_range_, dtype=tf.float32
-        )
-        min_y = tf.convert_to_tensor(
-            preprocess.scaler_y.data_min_, dtype=tf.float32
+        min_values = tf.convert_to_tensor(
+            preprocess.scaler_output.data_min_, dtype=tf.float32
         )
+  
     elif scaler_type == "standard":
-        scale_X = tf.convert_to_tensor(
-            preprocess.scaler_X.scale_, dtype=tf.float32)
-        mean_X = tf.convert_to_tensor(
-            preprocess.scaler_X.mean_, dtype=tf.float32)
-        scale_y = tf.convert_to_tensor(
-            preprocess.scaler_y.scale_, dtype=tf.float32)
-        mean_y = tf.convert_to_tensor(
-            preprocess.scaler_y.mean_, dtype=tf.float32)
+        scale_output = tf.convert_to_tensor(
+            preprocess.scaler_output.scale_, dtype=tf.float32)
+        mean_output = tf.convert_to_tensor(
+            preprocess.scaler_output.mean_, dtype=tf.float32)
 
     def loss(results, predicted):
         # inverse min/max scaling
         if scaler_type == "minmax":
-            predicted_inverse = predicted * scale_y + min_y
-            results_inverse = results * scale_X + min_X
+            predicted_inverse = predicted * data_range + min_values
+            results_inverse = results * data_range + min_values
 
         # inverse standard scaling
         elif scaler_type == "standard":
-            predicted_inverse = predicted * scale_y + mean_y
-            results_inverse = results * scale_X + mean_X
+            predicted_inverse = predicted * scale_output + mean_output
+            results_inverse = results * scale_output + mean_output
 
         elif scaler_type == "none":
             predicted_inverse = predicted
@@ -204,6 +195,8 @@ def custom_loss(
 
         # mass balance
         # in total no Barium and Strontium should be lost in one simulation step
+        
+        # TODO: encapsulate the mass balance terms in a function
         dBa = tf.keras.backend.abs(
             (
                 predicted_inverse[:, column_dict["Ba"]]
@@ -224,6 +217,19 @@ def custom_loss(
                 + results_inverse[:, column_dict["Celestite"]]
             )
         )
+        
+        dS = tf.keras.backend.abs(
+            (
+                predicted_inverse[:, column_dict["S"]]
+                + predicted_inverse[:, column_dict["Celestite"]]
+                + predicted_inverse[:, column_dict["Barite"]]
+            )
+            - (
+                results_inverse[:, column_dict["S"]]
+                + results_inverse[:, column_dict["Celestite"]]
+                + results_inverse[:, column_dict["Barite"]]
+            )
+        )
 
         # huber loss
         huber_loss = tf.keras.losses.Huber(delta)(results, predicted)
@@ -233,6 +239,8 @@ def custom_loss(
             total_loss = huber_loss
         elif loss_variant == "huber_mass_balance":
             total_loss = h1 * huber_loss + h2 * dBa + h3 * dSr
+        elif "huber_mass_balance_extended":
+            total_loss = h1 * huber_loss + h2 * dBa + h3 * dSr + h3 * dS
         else:
             raise Exception(
                 "No valid loss variant found. Choose between 'huber' and 'huber_mass_balance'."
@@ -243,7 +251,7 @@ def custom_loss(
     return loss
 
 
-def mass_balance_metric(preprocess, column_dict, scaler_type="minmax"):
+def mass_balance_metric(preprocess, column_dict, scaler_type="minmax", loss_variant="huber_mass_balance"):
     """Auxilary function to calculate the mass balance during training.
 
     Args:
@@ -256,36 +264,29 @@ def mass_balance_metric(preprocess, column_dict, scaler_type="minmax"):
     """
 
     if scaler_type == "minmax":
-        scale_X = tf.convert_to_tensor(
-            preprocess.scaler_X.data_range_, dtype=tf.float32
+        data_range = tf.convert_to_tensor(
+            preprocess.scaler_output.data_range_, dtype=tf.float32
         )
-        min_X = tf.convert_to_tensor(
-            preprocess.scaler_X.data_min_, dtype=tf.float32)
-        scale_y = tf.convert_to_tensor(
-            preprocess.scaler_y.data_range_, dtype=tf.float32
+        min_values = tf.convert_to_tensor(
+            preprocess.scaler_output.data_min_, dtype=tf.float32
         )
-        min_y = tf.convert_to_tensor(
-            preprocess.scaler_y.data_min_, dtype=tf.float32)
-
+  
     elif scaler_type == "standard":
-        scale_X = tf.convert_to_tensor(
-            preprocess.scaler_X.scale_, dtype=tf.float32)
-        mean_X = tf.convert_to_tensor(
-            preprocess.scaler_X.mean_, dtype=tf.float32)
-        scale_y = tf.convert_to_tensor(
-            preprocess.scaler_y.scale_, dtype=tf.float32)
-        mean_y = tf.convert_to_tensor(
-            preprocess.scaler_y.mean_, dtype=tf.float32)
+        scale_output = tf.convert_to_tensor(
+            preprocess.scaler_output.scale_, dtype=tf.float32)
+        mean_output = tf.convert_to_tensor(
+            preprocess.scaler_output.mean_, dtype=tf.float32)
 
     def mass_balance(results, predicted):
         # inverse min/max scaling
         if scaler_type == "minmax":
-            predicted_inverse = predicted * scale_y + min_y
-            results_inverse = results * scale_X + min_X
+            predicted_inverse = predicted * data_range + min_values
+            results_inverse = results * data_range + min_values
 
+        # inverse standard scaling
         elif scaler_type == "standard":
-            predicted_inverse = predicted * scale_y + mean_y
-            results_inverse = results * scale_X + mean_X
+            predicted_inverse = predicted * scale_output + mean_output
+            results_inverse = results * scale_output + mean_output
 
         elif scaler_type == "none":
             predicted_inverse = predicted
@@ -306,6 +307,7 @@ def mass_balance_metric(preprocess, column_dict, scaler_type="minmax"):
                 + results_inverse[:, column_dict["Barite"]]
             )
         )
+                
         dSr = tf.keras.backend.abs(
             (
                 predicted_inverse[:, column_dict["Sr"]]
@@ -316,11 +318,74 @@ def mass_balance_metric(preprocess, column_dict, scaler_type="minmax"):
                 + results_inverse[:, column_dict["Celestite"]]
             )
         )
-        return tf.reduce_mean(dBa + dSr)
+        
+        dS = tf.keras.backend.abs(
+            (
+                predicted_inverse[:, column_dict["S"]]
+                + predicted_inverse[:, column_dict["Celestite"]]
+                + predicted_inverse[:, column_dict["Barite"]]
+            )
+            - (
+                results_inverse[:, column_dict["S"]]
+                + results_inverse[:, column_dict["Celestite"]]
+                + results_inverse[:, column_dict["Barite"]]
+            )
+        )
+        
+        if loss_variant == "huber_mass_balance":
+            return tf.reduce_mean(dBa + dSr)
+        elif loss_variant == "huber_mass_balance_extended":
+            return tf.reduce_mean(dBa + dSr + dS)
 
     return mass_balance
 
 
+# def mass_balance_barium(predicted_inverse, results_inverse, column_dict):
+#     dBa = tf.keras.backend.abs(
+#             (
+#                 predicted_inverse[:, column_dict["Ba"]]
+#                 + predicted_inverse[:, column_dict["Barite"]]
+#             )
+#             - (
+#                 results_inverse[:, column_dict["Ba"]]
+#                 + results_inverse[:, column_dict["Barite"]]
+#             )
+#         )
+    
+#     return dBa
+    
+    
+# def mass_balance_strontium(predicted_inverse, results_inverse, column_dict):
+#     dSr = tf.keras.backend.abs(
+#             (
+#                 predicted_inverse[:, column_dict["Sr"]]
+#                 + predicted_inverse[:, column_dict["Celestite"]]
+#             )
+#             - (
+#                 results_inverse[:, column_dict["Sr"]]
+#                 + results_inverse[:, column_dict["Celestite"]]
+#             )
+#         )
+    
+#     return dSr
+
+# def mass_balance_sulfur(predicted_inverse, results_inverse, column_dict):
+#     dS = tf.keras.backend.abs(
+#             (
+#                 predicted_inverse[:, column_dict["S"]]
+#                 + predicted_inverse[:, column_dict["Celestite"]]
+#                 + predicted_inverse[:, column_dict["Barite"]]
+#             )
+#             - (
+#                 results_inverse[:, column_dict["S"]]
+#                 + results_inverse[:, column_dict["Celestite"]]
+#                 + results_inverse[:, column_dict["Barite"]]
+#             )
+#         )
+    
+#     return dS
+
+
 def huber_metric(delta=1.0):
     """Auxilary function to calculate the Huber loss during training.
 
@@ -337,8 +402,9 @@ def huber_metric(delta=1.0):
     return huber
 
 
-def mass_balance_evaluation(model, X, y, preprocess):
-    """Calculates the mass balance difference for each cell.
+def mass_balance_evaluation(model, X, preprocess):
+    """Calculates the mass balance difference for each cell 
+    between the predicted values and the design dataset.
 
     Args:
         model: trained model
@@ -353,18 +419,12 @@ def mass_balance_evaluation(model, X, y, preprocess):
     columns = X.iloc[:, X.columns != "Class"].columns
     classes = X["Class"]
     classes.reset_index(drop=True, inplace=True)
-    prediction = pd.DataFrame(model.predict(X[columns]), columns=y.columns)
+    prediction = pd.DataFrame(model.predict(X[columns]), columns=preprocess.scaler_output.feature_names_in_)
+    
     # backtransform min/max or standard scaler
-
-    if preprocess.scaler_X is not None:
-        X = pd.DataFrame(
-            preprocess.scaler_X.inverse_transform(
-                X.iloc[:, X.columns != "Class"]),
-            columns=columns,
-        )
-        prediction = pd.DataFrame(
-            preprocess.scaler_y.inverse_transform(prediction), columns=columns
-        )
+    if preprocess.scaler_input is not None:
+        X = preprocess.scale_inverse(X)[0]
+        prediction = preprocess.scale_inverse(prediction)[0]
 
     # apply backtransformation if log transformation was applied
     if preprocess.func_dict_out is not None:
@@ -378,9 +438,12 @@ def mass_balance_evaluation(model, X, y, preprocess):
         (prediction["Sr"] + prediction["Celestite"]) -
         (X["Sr"] + X["Celestite"])
     )
+    dS = np.abs(
+        (prediction["S"] + prediction["Celestite"] + prediction["Barite"]) -
+        (X["S"] + X["Celestite"] + X["Barite"]))
 
     mass_balance_result = pd.DataFrame(
-        {"dBa": dBa, "dSr": dSr, "mass_balance": dBa + dSr, "Class": classes}
+        {"dBa": dBa, "dSr": dSr, "dS": dS, "mass_balance": dBa + dSr, "mass_balance_extended": dBa+dSr+dS, "Class": classes}
     )
 
     return mass_balance_result
@@ -421,8 +484,8 @@ class preprocessing:
             random_state (int, optional): Seed for reproducability. Defaults to 42.
         """
         self.random_state = random_state
-        self.scaler_X = None
-        self.scaler_y = None
+        self.scaler_input = None
+        self.scaler_output = None
         self.func_dict_in = func_dict_in if func_dict_in is not None else None
         self.func_dict_out = func_dict_out if func_dict_out is not None else None
         self.state = {"cluster": False, "log": False,
@@ -500,8 +563,10 @@ class preprocessing:
         
         label = np.zeros(len(X))
         label[X[species] > threshold] = 1
-        X["Class"] = label
-        y["Class"] = label
+        X = X.copy()
+        y = y.copy()
+        X.loc[:, "Class"] = label
+        y.loc[:, "Class"] = label
         
         return X, y
         
@@ -584,52 +649,47 @@ class preprocessing:
         self.state["balance"] = True
         return design_resampled, target_resampled
 
-    def scale_fit(self, X, y, scaling, type="standard"):
+    def scale_fit(self, X, y, type="standard"):
         self.scaler_type = type
-        self.scaler_scope = scaling
         """Fit a scaler for data preprocessing.
 
         Args:
             X: design dataset
             y: target dataset
-            scaling: learn individual scaler for X and y when "individual" is selected or one global scaler on all data in X and y if "global" is selected (scaler_X and scaler_y are equal)
+            scaling: fit a scaler on all data in X and y. If X and y have different dimensions
+                     input and output scaler are trained for the specific columns.
             type (str, optional): Using MinMax Scaling or Standarization. Defaults to "Standard".
         """
 
         if type == "minmax":
-            self.scaler_X = MinMaxScaler()
-            self.scaler_y = MinMaxScaler()
+            self.scaler_input = MinMaxScaler()
+            self.scaler_output = MinMaxScaler()
         elif type == "standard":
-            self.scaler_X = StandardScaler()
-            self.scaler_y = StandardScaler()
+            self.scaler_input = StandardScaler()
+            self.scaler_output = StandardScaler()
 
         else:
             raise Exception("No valid scaler type found")
 
-        if scaling == "individual":
-            self.scaler_X.fit(X.iloc[:, X.columns != "Class"])
-            self.scaler_y.fit(y.iloc[:, y.columns != "Class"])
 
-        elif scaling == "global":
-            self.scaler_X.fit(
-                pd.concat(
-                    [X.iloc[:, X.columns != "Class"],
-                        y.iloc[:, y.columns != "Class"]],
-                    axis=0,
-                )
-            )
-            self.scaler_y = self.scaler_X
+        all_data = pd.concat([X, y],axis=0)
+        
+        if len(X.columns) == len(y.columns):
+            self.scaler_input.fit(all_data.loc[:, X.columns != "Class"])
+            self.scaler_output = self.scaler_input
+            
+        else:
+            self.scaler_input.fit(all_data[X.columns[X.columns != "Class"]])
+            self.scaler_output.fit(all_data[y.columns[y.columns != "Class"]])
+            
 
         self.state["scale"] = True
         
         
-        return pd.concat(
-                    [X.iloc[:, X.columns != "Class"],
-                        y.iloc[:, y.columns != "Class"]],
-                    axis=0,
-                )
+        
+    
 
-    def scale_transform(self, X_train, X_test, y_train, y_test):
+    def scale_transform(self, *args):
         """Apply learned scaler on datasets.
 
         Args:
@@ -641,82 +701,31 @@ class preprocessing:
         Returns:
             transformed dataframes
         """
-
-        if self.scaler_scope == "global":
-            if len(X_train.columns) > len(y_train.columns):
-                y_train_modified = X_train.copy()
-                y_test_modified = X_test.copy()
-
-                for i in y_train_modified.columns:
-                    if i in y_train.columns:
-                        y_train_modified[i] = y_train[i]
-                        y_test_modified[i] = y_test[i]
-                    else:
-                        y_train_modified[i] = np.nan
-                        y_test_modified[i] = np.nan
-
-                y_train = y_train_modified
-                y_test = y_test_modified
-
-
+        
+        results = []
+        for i in args:
+            # check which scaler should be used depending on the columns
+            if len(i.columns[i.columns != "Class"]) == len(self.scaler_input.feature_names_in_):
+                scaler = self.scaler_input
             else:
-                X_train_modified = y_train.copy()
-                X_test_modified = y_test.copy()
-
-                for i in X_train_modified.columns:
-                    if i in X_train.columns:
-                        X_train_modified[i] = X_train[i]
-                        X_test_modified[i] = X_test[i]
-                    else:
-                        X_train_modified[i] = np.nan
-                        X_test_modified[i] = np.nan
-
-                X_train = X_train_modified
-                X_test = X_test_modified
-
-
-        X_train = pd.concat(
-            [
-                self.scaler_X.transform(
-                    X_train.loc[:, X_train.columns != "Class"]),
-                X_train.loc[:, "Class"],
-            ],
-            axis=1,
-        )
-
-        X_test = pd.concat(
-            [
-                self.scaler_X.transform(
-                    X_test.loc[:, X_test.columns != "Class"]),
-                X_test.loc[:, "Class"],
-            ],
-            axis=1,
-        )
-
-        y_train = pd.concat(
-            [
-                self.scaler_y.transform(
-                    y_train.loc[:, y_train.columns != "Class"]),
-                y_train.loc[:, "Class"],
-            ],
-            axis=1,
-        )
-
-        y_test = pd.concat(
-            [
-                self.scaler_y.transform(
-                    y_test.loc[:, y_test.columns != "Class"]),
-                y_test.loc[:, "Class"],
-            ],
-            axis=1,
-        )
-        
-        X_train.dropna(axis=1, inplace=True)
-        X_test.dropna(axis=1, inplace=True) 
-        y_train.dropna(axis=1, inplace=True)    
-        y_test.dropna(axis=1, inplace=True) 
-        
-        return X_train, X_test, y_train, y_test
+                scaler = self.scaler_output
+            
+            if "Class" in i.columns:
+                i = pd.concat(
+                    [
+                        scaler.transform(i.loc[:, i.columns != "Class"]),
+                        i.loc[:, "Class"],
+                    ],
+                    axis=1,
+                )
+            else:
+                i = scaler.transform(i)
+                
+            results.append(i)
+            
+            
+        return results
+       
 
     def scale_inverse(self, *args):
         """Backtransform the dataset
@@ -725,65 +734,28 @@ class preprocessing:
             Backtransformed data frames
         """
 
-        
-        
         result = []
-        
-        
-        if self.scaler_scope == "individual":
-            for i in args:
-                if(len(i.columns) == len(self.scaler_X.feature_names_in_)):
-                    scaler = self.scaler_X
-                else:
-                    scaler = self.scaler_y
-                if "Class" in i.columns:
-                    inversed = pd.DataFrame(
-                        scaler.inverse_transform(
-                            i.loc[:, i.columns != "Class"]),
-                        columns=i.columns[:-1],
-                    )
-                    class_column = i.loc[:, "Class"].reset_index(drop=True)
-                    i = pd.concat([inversed, class_column], axis=1)
-                else:
+
+            
+        for i in args:
+            # check which scaler should be used depending on the columns
+            if len(i.columns[i.columns != "Class"]) == len(self.scaler_input.feature_names_in_):
+                scaler = self.scaler_input
+            else:
+                scaler = self.scaler_output
+            
+            if "Class" in i.columns:
+                inversed = pd.DataFrame(
+                    scaler.inverse_transform(
+                        i.loc[:, i.columns != "Class"]),
+                    columns=i.columns[:-1],
+                )
+                class_column = i.loc[:, "Class"].reset_index(drop=True)
+                i = pd.concat([inversed, class_column], axis=1)
+            else:
                     i = pd.DataFrame(
                         scaler.inverse_transform(i), columns=i.columns)
-                result.append(i)
-                
-        elif self.scaler_scope == "global":
-            
-            for i in args:
-                if (len(i.columns) == len(self.preprocess.scaler_X.feature_names_in_)):
-                    if "Class" in i.columns:
-                        inversed = pd.DataFrame(
-                            self.scaler_X.inverse_transform(
-                                i.loc[:, i.columns != "Class"]),
-                            columns=i.columns[:-1],
-                        )
-                        class_column = i.loc[:, "Class"].reset_index(drop=True)
-                        i = pd.concat([inversed, class_column], axis=1)
-                    else:
-                        i = pd.DataFrame(
-                            self.scaler_X.inverse_transform(i), columns=i.columns)
-                    result.append(i)
-                    
-                else:
-                    df = pd.DataFrame()
-                    for j in self.scaler_X.feature_names_in_:
-                        if j in i.columns:
-                            df[j] = i[j]
-                        else:
-                            df[j] = np.nan
-                    if "Class" in i.columns:
-                        inversed = pd.DataFrame(
-                            self.scaler_X.inverse_transform(
-                                df.loc[:, df.columns != "Class"]),
-                            columns=df.columns[:-1],
-                        )
-                    else:
-                        i = pd.DataFrame(
-                            self.scaler_X.inverse_transform(df), columns=df.columns)
-                    result.append(i)
-                
+            result.append(i)
         
         return result
 

tests/test_scaler.py

@@ -0,0 +1,14 @@
+# import unittest
+# import os
+
+# os.chdir("../src/")
+# print(os.getcwd())  
+
+# from preprocessing import *
+
+# class TestScaler(unittest.TestCase):
+#     def sample_test(self):
+#         self.assertEqual(1, 1)
+        
+# if __name__ == '__main__':
+#     unittest.main()