feat: more hash, sizeof and eq implementations

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

@@ -1,9 +1,11 @@
 from __future__ import annotations
 
+import sys
 import warnings
 from typing import Any
 
 import pandas as pd
+import xxhash
 from sklearn.impute import SimpleImputer as sk_SimpleImputer
 
 from safeds.data.tabular.containers import Table
@@ -47,9 +49,29 @@ class Constant(ImputerStrategy):
                 The given value to impute missing values.
             """
 
+            def __eq__(self, other: object) -> bool:
+                if not isinstance(other, Imputer.Strategy.Constant):
+                    return NotImplemented
+                if self is other:
+                    return True
+                return self._value == other._value
+
+            def __hash__(self) -> int:
+                return xxhash.xxh3_64(self.__class__.__qualname__.encode("utf-8")).intdigest()
+
             def __init__(self, value: Any):
                 self._value = value
 
+            def __sizeof__(self) -> int:
+                """
+                Return the complete size of this object.
+
+                Returns
+                -------
+                Size of this object in bytes.
+                """
+                return sys.getsizeof(self._value)
+
             def __str__(self) -> str:
                 return f"Constant({self._value})"
 
@@ -60,6 +82,14 @@ def _augment_imputer(self, imputer: sk_SimpleImputer) -> None:
         class Mean(ImputerStrategy):
             """An imputation strategy for imputing missing data with mean values."""
 
+            def __eq__(self, other: object) -> bool:
+                if not isinstance(other, Imputer.Strategy.Mean):
+                    return NotImplemented
+                return True
+
+            def __hash__(self) -> int:
+                return xxhash.xxh3_64(self.__class__.__qualname__.encode("utf-8")).intdigest()
+
             def __str__(self) -> str:
                 return "Mean"
 
@@ -69,6 +99,14 @@ def _augment_imputer(self, imputer: sk_SimpleImputer) -> None:
         class Median(ImputerStrategy):
             """An imputation strategy for imputing missing data with median values."""
 
+            def __eq__(self, other: object) -> bool:
+                if not isinstance(other, Imputer.Strategy.Median):
+                    return NotImplemented
+                return True
+
+            def __hash__(self) -> int:
+                return xxhash.xxh3_64(self.__class__.__qualname__.encode("utf-8")).intdigest()
+
             def __str__(self) -> str:
                 return "Median"
 
@@ -78,6 +116,14 @@ def _augment_imputer(self, imputer: sk_SimpleImputer) -> None:
         class Mode(ImputerStrategy):
             """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 __eq__(self, other: object) -> bool:
+                if not isinstance(other, Imputer.Strategy.Mode):
+                    return NotImplemented
+                return True
+
+            def __hash__(self) -> int:
+                return xxhash.xxh3_64(self.__class__.__qualname__.encode("utf-8")).intdigest()
+
             def __str__(self) -> str:
                 return "Mode"
 

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

@@ -1,5 +1,7 @@
 from __future__ import annotations
 
+import functools
+import operator
 from abc import ABC, abstractmethod
 from typing import TYPE_CHECKING
 
@@ -21,7 +23,16 @@ def __hash__(self) -> int:
         hash : int
             The hash value.
         """
-        return xxhash.xxh3_64(self.__class__.__qualname__.encode("utf-8") + (1 if self.is_fitted() else 0).to_bytes(1)).intdigest()
+        added = self.get_names_of_added_columns() if self.is_fitted() else []
+        changed = self.get_names_of_changed_columns() if self.is_fitted() else []
+        removed = self.get_names_of_removed_columns() if self.is_fitted() else []
+        return xxhash.xxh3_64(
+            self.__class__.__qualname__.encode("utf-8")
+            + (1 if self.is_fitted() else 0).to_bytes(1)
+            + functools.reduce(operator.add, [feature.encode("utf-8") for feature in added], b"A")
+            + functools.reduce(operator.add, [feature.encode("utf-8") for feature in changed], b"C")
+            + functools.reduce(operator.add, [feature.encode("utf-8") for feature in removed], b"R"),
+        ).intdigest()
 
     @abstractmethod
     def fit(self, table: Table, column_names: list[str] | None) -> TableTransformer:

src/safeds/data/tabular/typing/_imputer_strategy.py

@@ -20,3 +20,30 @@ def _augment_imputer(self, imputer: sk_SimpleImputer) -> None:
         imputer: SimpleImputer
             The imputer to augment.
         """
+
+    @abstractmethod
+    def __eq__(self, other: object) -> bool:
+        """
+        Compare two imputer strategies.
+
+        Parameters
+        ----------
+        other:
+            other object to compare to
+
+        Returns
+        -------
+        equals:
+            Whether the two imputer strategies are equal
+        """
+
+    @abstractmethod
+    def __hash__(self) -> int:
+        """
+        Return a deterministic hash value for this imputer strategy.
+
+        Returns
+        -------
+        hash : int
+            The hash value.
+        """

src/safeds/ml/classical/classification/_ada_boost.py

@@ -1,7 +1,11 @@
 from __future__ import annotations
 
+import functools
+import operator
+import struct
 from typing import TYPE_CHECKING
 
+import xxhash
 from sklearn.ensemble import AdaBoostClassifier as sk_AdaBoostClassifier
 
 from safeds.exceptions import ClosedBound, OpenBound, OutOfBoundsError
@@ -36,6 +40,19 @@ class AdaBoostClassifier(Classifier):
         If `maximum_number_of_learners` or `learning_rate` are less than or equal to 0.
     """
 
+    def __hash__(self) -> int:
+        return xxhash.xxh3_64(
+            Classifier.__hash__(self).to_bytes(8)
+            + (self._target_name.encode("utf-8") if self._target_name is not None else b"\0")
+            + (
+                functools.reduce(operator.add, [feature.encode("utf-8") for feature in self._feature_names], b"")
+                if self._feature_names is not None
+                else b"\0"
+            )
+            + struct.pack("d", self._learning_rate)
+            + self._maximum_number_of_learners.to_bytes(8),
+        ).intdigest()
+
     def __init__(
         self,
         *,

src/safeds/ml/classical/classification/_decision_tree.py

@@ -1,7 +1,10 @@
 from __future__ import annotations
 
+import functools
+import operator
 from typing import TYPE_CHECKING
 
+import xxhash
 from sklearn.tree import DecisionTreeClassifier as sk_DecisionTreeClassifier
 
 from safeds.ml.classical._util_sklearn import fit, predict
@@ -17,6 +20,17 @@
 class DecisionTreeClassifier(Classifier):
     """Decision tree classification."""
 
+    def __hash__(self) -> int:
+        return xxhash.xxh3_64(
+            Classifier.__hash__(self).to_bytes(8)
+            + (self._target_name.encode("utf-8") if self._target_name is not None else b"\0")
+            + (
+                functools.reduce(operator.add, [feature.encode("utf-8") for feature in self._feature_names], b"")
+                if self._feature_names is not None
+                else b"\0"
+            ),
+        ).intdigest()
+
     def __init__(self) -> None:
         # Internal state
         self._wrapped_classifier: sk_DecisionTreeClassifier | None = None

src/safeds/ml/classical/classification/_gradient_boosting.py

@@ -1,7 +1,11 @@
 from __future__ import annotations
 
+import functools
+import operator
+import struct
 from typing import TYPE_CHECKING
 
+import xxhash
 from sklearn.ensemble import GradientBoostingClassifier as sk_GradientBoostingClassifier
 
 from safeds.exceptions import ClosedBound, OpenBound, OutOfBoundsError
@@ -34,6 +38,19 @@ class GradientBoostingClassifier(Classifier):
         If `number_of_trees` or `learning_rate` is less than or equal to 0.
     """
 
+    def __hash__(self) -> int:
+        return xxhash.xxh3_64(
+            Classifier.__hash__(self).to_bytes(8)
+            + (self._target_name.encode("utf-8") if self._target_name is not None else b"\0")
+            + (
+                functools.reduce(operator.add, [feature.encode("utf-8") for feature in self._feature_names], b"")
+                if self._feature_names is not None
+                else b"\0"
+            )
+            + struct.pack("d", self._learning_rate)
+            + self._number_of_trees.to_bytes(8),
+        ).intdigest()
+
     def __init__(self, *, number_of_trees: int = 100, learning_rate: float = 0.1) -> None:
         # Validation
         if number_of_trees < 1:

src/safeds/ml/classical/classification/_k_nearest_neighbors.py

@@ -1,7 +1,10 @@
 from __future__ import annotations
 
+import functools
+import operator
 from typing import TYPE_CHECKING
 
+import xxhash
 from sklearn.neighbors import KNeighborsClassifier as sk_KNeighborsClassifier
 
 from safeds.exceptions import ClosedBound, DatasetMissesDataError, OutOfBoundsError
@@ -31,6 +34,18 @@ class KNearestNeighborsClassifier(Classifier):
         If `number_of_neighbors` is less than 1.
     """
 
+    def __hash__(self) -> int:
+        return xxhash.xxh3_64(
+            Classifier.__hash__(self).to_bytes(8)
+            + (self._target_name.encode("utf-8") if self._target_name is not None else b"\0")
+            + (
+                functools.reduce(operator.add, [feature.encode("utf-8") for feature in self._feature_names], b"")
+                if self._feature_names is not None
+                else b"\0"
+            )
+            + self._number_of_neighbors.to_bytes(8),
+        ).intdigest()
+
     def __init__(self, number_of_neighbors: int) -> None:
         # Validation
         if number_of_neighbors < 1:

src/safeds/ml/classical/classification/_logistic_regression.py

@@ -1,7 +1,10 @@
 from __future__ import annotations
 
+import functools
+import operator
 from typing import TYPE_CHECKING
 
+import xxhash
 from sklearn.linear_model import LogisticRegression as sk_LogisticRegression
 
 from safeds.ml.classical._util_sklearn import fit, predict
@@ -17,6 +20,17 @@
 class LogisticRegressionClassifier(Classifier):
     """Regularized logistic regression."""
 
+    def __hash__(self) -> int:
+        return xxhash.xxh3_64(
+            Classifier.__hash__(self).to_bytes(8)
+            + (self._target_name.encode("utf-8") if self._target_name is not None else b"\0")
+            + (
+                functools.reduce(operator.add, [feature.encode("utf-8") for feature in self._feature_names], b"")
+                if self._feature_names is not None
+                else b"\0"
+            ),
+        ).intdigest()
+
     def __init__(self) -> None:
         # Internal state
         self._wrapped_classifier: sk_LogisticRegression | None = None

src/safeds/ml/classical/classification/_random_forest.py

@@ -1,7 +1,10 @@
 from __future__ import annotations
 
+import functools
+import operator
 from typing import TYPE_CHECKING
 
+import xxhash
 from sklearn.ensemble import RandomForestClassifier as sk_RandomForestClassifier
 
 from safeds.exceptions import ClosedBound, OutOfBoundsError
@@ -29,6 +32,18 @@ class RandomForestClassifier(Classifier):
         If `number_of_trees` is less than 1.
     """
 
+    def __hash__(self) -> int:
+        return xxhash.xxh3_64(
+            Classifier.__hash__(self).to_bytes(8)
+            + (self._target_name.encode("utf-8") if self._target_name is not None else b"\0")
+            + (
+                functools.reduce(operator.add, [feature.encode("utf-8") for feature in self._feature_names], b"")
+                if self._feature_names is not None
+                else b"\0"
+            )
+            + self._number_of_trees.to_bytes(8),
+        ).intdigest()
+
     def __init__(self, *, number_of_trees: int = 100) -> None:
         # Validation
         if number_of_trees < 1: