feat: Added and improved errors and warnings in the table transformers

src/safeds/data/tabular/containers/_table.py

@@ -627,10 +627,8 @@ def add_column(self, column: Column) -> Table:
         ------
         DuplicateColumnNameError
             If the new column already exists.
-
         ColumnSizeError
             If the size of the column does not match the amount of rows.
-
         """
         if self.has_column(column.name):
             raise DuplicateColumnNameError(column.name)

src/safeds/data/tabular/transformation/_imputer.py

@@ -1,5 +1,6 @@
 from __future__ import annotations
 
+import warnings
 from typing import Any
 
 import pandas as pd
@@ -8,7 +9,7 @@
 from safeds.data.tabular.containers import Table
 from safeds.data.tabular.transformation._table_transformer import TableTransformer
 from safeds.data.tabular.typing import ImputerStrategy
-from safeds.exceptions import TransformerNotFittedError, UnknownColumnNameError
+from safeds.exceptions import NonNumericColumnError, TransformerNotFittedError, UnknownColumnNameError
 
 
 class Imputer(TableTransformer):
@@ -75,7 +76,7 @@ def _augment_imputer(self, imputer: sk_SimpleImputer) -> None:
                 imputer.strategy = "median"
 
         class Mode(ImputerStrategy):
-            """An imputation strategy for imputing missing data with mode values."""
+            """An imputation strategy for imputing missing data with mode values. The lowest value will be used if there are multiple values with the same highest count."""
 
             def __str__(self) -> str:
                 return "Mode"
@@ -107,18 +108,59 @@ def fit(self, table: Table, column_names: list[str] | None) -> Imputer:
         -------
         fitted_transformer : TableTransformer
             The fitted transformer.
+
+        Raises
+        ------
+        UnknownColumnNameError
+            If column_names contain a column name that is missing in the table
+        ValueError
+            If the table contains 0 rows
+        NonNumericColumnError
+            If the strategy is set to either Mean or Median and the specified columns of the table contain non-numerical data
         """
         if column_names is None:
             column_names = table.column_names
         else:
-            missing_columns = set(column_names) - set(table.column_names)
+            missing_columns = sorted(set(column_names) - set(table.column_names))
             if len(missing_columns) > 0:
-                raise UnknownColumnNameError(list(missing_columns))
+                raise UnknownColumnNameError(missing_columns)
+
+        if table.number_of_rows == 0:
+            raise ValueError("The Imputer cannot be fitted because the table contains 0 rows")
+
+        if (isinstance(self._strategy, Imputer.Strategy.Mean | Imputer.Strategy.Median)) and table.keep_only_columns(
+            column_names,
+        ).remove_columns_with_non_numerical_values().number_of_columns < len(
+            column_names,
+        ):
+            raise NonNumericColumnError(
+                str(
+                    sorted(
+                        set(table.keep_only_columns(column_names).column_names)
+                        - set(
+                            table.keep_only_columns(column_names)
+                            .remove_columns_with_non_numerical_values()
+                            .column_names,
+                        ),
+                    ),
+                ),
+            )
 
         if isinstance(self._strategy, Imputer.Strategy.Mode):
+            multiple_most_frequent = {}
             for name in column_names:
                 if len(table.get_column(name).mode()) > 1:
-                    raise IndexError("There are multiple most frequent values in a column given for the Imputer")
+                    multiple_most_frequent[name] = table.get_column(name).mode()
+            if len(multiple_most_frequent) > 0:
+                warnings.warn(
+                    (
+                        "There are multiple most frequent values in a column given to the Imputer.\nThe lowest values"
+                        " are being chosen in this cases. The following columns have multiple most frequent"
+                        f" values:\n{multiple_most_frequent}"
+                    ),
+                    UserWarning,
+                    stacklevel=2,
+                )
 
         wrapped_transformer = sk_SimpleImputer()
         self._strategy._augment_imputer(wrapped_transformer)
@@ -151,15 +193,33 @@ def transform(self, table: Table) -> Table:
         ------
         TransformerNotFittedError
             If the transformer has not been fitted yet.
+        UnknownColumnNameError
+            If the input table does not contain all columns used to fit the transformer
+        ValueError
+            If the table contains 0 rows
         """
         # Transformer has not been fitted yet
         if self._wrapped_transformer is None or self._column_names is None:
             raise TransformerNotFittedError
 
         # Input table does not contain all columns used to fit the transformer
-        missing_columns = set(self._column_names) - set(table.column_names)
+        missing_columns = sorted(set(self._column_names) - set(table.column_names))
         if len(missing_columns) > 0:
-            raise UnknownColumnNameError(list(missing_columns))
+            raise UnknownColumnNameError(missing_columns)
+
+        if table.number_of_rows == 0:
+            raise ValueError("The Imputer cannot transform the table because it contains 0 rows")
+
+        if table.keep_only_columns(self._column_names).remove_columns_with_missing_values().number_of_columns > 0:
+            warnings.warn(
+                (
+                    "The columns"
+                    f" {table.keep_only_columns(self._column_names).remove_columns_with_missing_values().column_names} have"
+                    " no missing values, so the Imputer did not change these columns"
+                ),
+                UserWarning,
+                stacklevel=2,
+            )
 
         data = table._data.copy()
         data[self._column_names] = pd.DataFrame(

src/safeds/data/tabular/transformation/_label_encoder.py

@@ -1,12 +1,14 @@
 from __future__ import annotations
 
+import warnings
+
 from sklearn.preprocessing import OrdinalEncoder as sk_OrdinalEncoder
 
 from safeds.data.tabular.containers import Table
 from safeds.data.tabular.transformation._table_transformer import (
     InvertibleTableTransformer,
 )
-from safeds.exceptions import TransformerNotFittedError, UnknownColumnNameError
+from safeds.exceptions import NonNumericColumnError, TransformerNotFittedError, UnknownColumnNameError
 
 
 # noinspection PyProtectedMember
@@ -34,13 +36,35 @@ def fit(self, table: Table, column_names: list[str] | None) -> LabelEncoder:
         -------
         fitted_transformer : TableTransformer
             The fitted transformer.
+
+        Raises
+        ------
+        UnknownColumnNameError
+            If column_names contain a column name that is missing in the table
+        ValueError
+            If the table contains 0 rows
         """
         if column_names is None:
             column_names = table.column_names
         else:
-            missing_columns = set(column_names) - set(table.column_names)
+            missing_columns = sorted(set(column_names) - set(table.column_names))
             if len(missing_columns) > 0:
-                raise UnknownColumnNameError(list(missing_columns))
+                raise UnknownColumnNameError(missing_columns)
+
+        if table.number_of_rows == 0:
+            raise ValueError("The LabelEncoder cannot transform the table because it contains 0 rows")
+
+        if table.keep_only_columns(column_names).remove_columns_with_non_numerical_values().number_of_columns > 0:
+            warnings.warn(
+                (
+                    "The columns"
+                    f" {table.keep_only_columns(column_names).remove_columns_with_non_numerical_values().column_names} contain"
+                    " numerical data. The LabelEncoder is designed to encode non-numerical values into numerical"
+                    " values"
+                ),
+                UserWarning,
+                stacklevel=2,
+            )
 
         wrapped_transformer = sk_OrdinalEncoder()
         wrapped_transformer.fit(table._data[column_names])
@@ -71,15 +95,22 @@ def transform(self, table: Table) -> Table:
         ------
         TransformerNotFittedError
             If the transformer has not been fitted yet.
+        UnknownColumnNameError
+            If the input table does not contain all columns used to fit the transformer
+        ValueError
+            If the table contains 0 rows
         """
         # Transformer has not been fitted yet
         if self._wrapped_transformer is None or self._column_names is None:
             raise TransformerNotFittedError
 
         # Input table does not contain all columns used to fit the transformer
-        missing_columns = set(self._column_names) - set(table.column_names)
+        missing_columns = sorted(set(self._column_names) - set(table.column_names))
         if len(missing_columns) > 0:
-            raise UnknownColumnNameError(list(missing_columns))
+            raise UnknownColumnNameError(missing_columns)
+
+        if table.number_of_rows == 0:
+            raise ValueError("The LabelEncoder cannot transform the table because it contains 0 rows")
 
         data = table._data.copy()
         data.columns = table.column_names
@@ -106,11 +137,40 @@ def inverse_transform(self, transformed_table: Table) -> Table:
         ------
         TransformerNotFittedError
             If the transformer has not been fitted yet.
+        UnknownColumnNameError
+            If the input table does not contain all columns used to fit the transformer
+        NonNumericColumnError
+            If the specified columns of the input table contain non-numerical data
+        ValueError
+            If the table contains 0 rows
         """
         # Transformer has not been fitted yet
         if self._wrapped_transformer is None or self._column_names is None:
             raise TransformerNotFittedError
 
+        missing_columns = sorted(set(self._column_names) - set(transformed_table.column_names))
+        if len(missing_columns) > 0:
+            raise UnknownColumnNameError(missing_columns)
+
+        if transformed_table.keep_only_columns(
+            self._column_names,
+        ).remove_columns_with_non_numerical_values().number_of_columns < len(self._column_names):
+            raise NonNumericColumnError(
+                str(
+                    sorted(
+                        set(self._column_names)
+                        - set(
+                            transformed_table.keep_only_columns(self._column_names)
+                            .remove_columns_with_non_numerical_values()
+                            .column_names,
+                        ),
+                    ),
+                ),
+            )
+
+        if transformed_table.number_of_rows == 0:
+            raise ValueError("The LabelEncoder cannot inverse transform the table because it contains 0 rows")
+
         data = transformed_table._data.copy()
         data.columns = transformed_table.column_names
         data[self._column_names] = self._wrapped_transformer.inverse_transform(data[self._column_names])