hyperactive.experiment.integrations.sklearn_cv.SklearnCvExperiment.__init__() - Code Metrics - Inspection of "V5 API rework - experimental" - SimonBlanke/Hyperactive - Measure and Improve Code Quality continuously with Scrutinizer

Passed

Pull Request — master (#110)

unknown

created 2025-05-05 11:48 UTC

SklearnCvExperiment.init() A

↳ Parent: hyperactive.experiment.integrations.sklearn_cv

Complexity

Conditions

Size

Total Lines	21
Code Lines	15

Duplication

Lines	0
Ratio	0 %

Importance

Changes

Metric	Value
eloc	15
dl	0
loc	21
rs	9.65
c	0
b	0
f	0
cc	3
nop	6

"""Experiment adapter for sklearn cross-validation experiments."""

from sklearn import clone
from sklearn.metrics import check_scoring
from sklearn.model_selection import cross_validate
from sklearn.utils.validation import _num_samples

from hyperactive.base import BaseExperiment

class SklearnCvExperiment(BaseExperiment):
    """Experiment adapter for sklearn cross-validation experiments.

    This class is used to perform cross-validation experiments using a given
    sklearn estimator. It allows for hyperparameter tuning and evaluation of
    the model's performance using cross-validation.

    The score returned is the mean of the cross-validation scores,
    of applying cross-validation to ``estimator`` with the parameters given in
    ``score`` ``params``.

    The cross-validation performed is specified by the ``cv`` parameter,
    and the scoring metric is specified by the ``scoring`` parameter.
    The ``X`` and ``y`` parameters are the input data and target values,
    which are used in fit/predict cross-validation.

    Parameters
    ----------
    estimator : sklearn estimator
        The estimator to be used for the experiment.
    X : array-like, shape (n_samples, n_features)
            The input data for the model.
    y : array-like, shape (n_samples,) or (n_samples, n_outputs)
        The target values for the model.
    cv : int or cross-validation generator, default = KFold(n_splits=3, shuffle=True)
        The number of folds or cross-validation strategy to be used.
        If int, the cross-validation used is KFold(n_splits=cv, shuffle=True).
    scoring : callable or str, default = accuracy_score or mean_squared_error
        sklearn scoring function or metric to evaluate the model's performance.
        Default is determined by the type of estimator:
        ``accuracy_score`` for classifiers, and
        ``mean_squared_error`` for regressors, as per sklearn convention
        through the default ``score`` method of the estimator.

    Example
    -------
    >>> from hyperactive.experiment.integrations import SklearnCvExperiment
    >>> from sklearn.datasets import load_iris
    >>> from sklearn.svm import SVC
    >>> from sklearn.metrics import accuracy_score
    >>> from sklearn.model_selection import KFold
    >>>
    >>> X, y = load_iris(return_X_y=True)
    >>>
    >>> sklearn_exp = SklearnCvExperiment(
    ...    estimator=SVC(),
    ...     scoring=accuracy_score,
    ...     cv=KFold(n_splits=3, shuffle=True),
    ...     X=X,
    ...     y=y,
    ... )
    >>> params = {"C": 1.0, "kernel": "linear"}
    >>> score, add_info = sklearn_exp.score(params)

    For default choices of ``scoring`` and ``cv``:
    >>> sklearn_exp = SklearnCvExperiment(
    ...    estimator=SVC(),
    ...     X=X,
    ...     y=y,
    ... )
    >>> params = {"C": 1.0, "kernel": "linear"}
    >>> score, add_info = sklearn_exp.score(params)

    Quick call without metadata return or dictionary:
    >>> score = sklearn_exp(C=1.0, kernel="linear")
    """

    def __init__(self, estimator, X, y, scoring, cv):
        self.estimator = estimator
        self.X = X
        self.y = y
        self.scoring = scoring
        self.cv = cv

        super().__init__()

        if cv is None:
            from sklearn.model_selection import KFold

            self._cv = KFold(n_splits=3, shuffle=True)
        elif isinstance(cv, int):
            from sklearn.model_selection import KFold

            self._cv = KFold(n_splits=cv, shuffle=True)
        else:
            self._cv = cv

        self._scoring = check_scoring(estimator=estimator, scoring=scoring)

    def _paramnames(self):
        """Return the parameter names of the search.

        Returns
        -------
        list of str
            The parameter names of the search parameters.
        """
        return list(self.estimator.get_params().keys())

    def _score(self, params):
        """Score the parameters.

        Parameters
        ----------
        params : dict with string keys
            Parameters to score.

        Returns
        -------
        float
            The score of the parameters.
        dict
            Additional metadata about the search.
        """
        estimator = clone(self.estimator)
        estimator.set_params(**params)

        cv_results = cross_validate(
            estimator,
            self.X,
            self.y,
            cv=self._cv,
        )

        add_info_d = {
            "score_time": cv_results["score_time"],
            "fit_time": cv_results["fit_time"],
            "n_test_samples": _num_samples(self.X),
        }

        return cv_results["test_score"].mean(), add_info_d

    @classmethod
    def get_test_params(cls, parameter_set="default"):
        """Return testing parameter settings for the skbase object.

        ``get_test_params`` is a unified interface point to store
        parameter settings for testing purposes. This function is also
        used in ``create_test_instance`` and ``create_test_instances_and_names``
        to construct test instances.

        ``get_test_params`` should return a single ``dict``, or a ``list`` of ``dict``.

        Each ``dict`` is a parameter configuration for testing,
        and can be used to construct an "interesting" test instance.
        A call to ``cls(**params)`` should
        be valid for all dictionaries ``params`` in the return of ``get_test_params``.

        The ``get_test_params`` need not return fixed lists of dictionaries,
        it can also return dynamic or stochastic parameter settings.

        Parameters
        ----------
        parameter_set : str, default="default"
            Name of the set of test parameters to return, for use in tests. If no
            special parameters are defined for a value, will return `"default"` set.

        Returns
        -------
        params : dict or list of dict, default = {}
            Parameters to create testing instances of the class
            Each dict are parameters to construct an "interesting" test instance, i.e.,
            `MyClass(**params)` or `MyClass(**params[i])` creates a valid test instance.
            `create_test_instance` uses the first (or only) dictionary in `params`
        """
        from sklearn.datasets import load_diabetes, load_iris
        from sklearn.svm import SVC, SVR
        from sklearn.metrics import accuracy_score, mean_absolute_error
        from sklearn.model_selection import KFold

        X, y = load_iris(return_X_y=True)
        params_classif = {
            "estimator": SVC(),
            "scoring": accuracy_score,
            "cv": KFold(n_splits=3, shuffle=True),
            "X": X,
            "y": y,
        }

        X, y = load_diabetes(return_X_y=True)
        params_regress = {
            "estimator": SVR(),
            "scoring": mean_absolute_error,
            "cv": 2,
            "X": X,
            "y": y,
        }

        X, y = load_diabetes(return_X_y=True)
        params_all_default = {
            "estimator": SVR(),
            "X": X,
            "y": y,
        }

        return [params_classif, params_regress, params_all_default]

    @classmethod
    def _get_score_params(self):
        """Return settings for the score function.

        Returns a list, the i-th element corresponds to self.get_test_params()[i].
        It should be a valid call for self.score.

        Returns
        -------
        list of dict
            The parameters to be used for scoring.
        """
        score_params_classif = {"C": 1.0, "kernel": "linear"}
        score_params_regress = {"C": 1.0, "kernel": "linear"}
        score_params_defaults = {"C": 1.0, "kernel": "linear"}
        return [score_params_classif, score_params_regress, score_params_defaults]


1			"""Experiment adapter for sklearn cross-validation experiments."""
2
3			from sklearn import clone
4			from sklearn.metrics import check_scoring
5			from sklearn.model_selection import cross_validate
6			from sklearn.utils.validation import _num_samples
7
8			from hyperactive.base import BaseExperiment
9
10			class SklearnCvExperiment(BaseExperiment):
11			"""Experiment adapter for sklearn cross-validation experiments.
12
13			This class is used to perform cross-validation experiments using a given
14			sklearn estimator. It allows for hyperparameter tuning and evaluation of
15			the model's performance using cross-validation.
16
17			The score returned is the mean of the cross-validation scores,
18			of applying cross-validation to ``estimator`` with the parameters given in
19			``score`` ``params``.
20
21			The cross-validation performed is specified by the ``cv`` parameter,
22			and the scoring metric is specified by the ``scoring`` parameter.
23			The ``X`` and ``y`` parameters are the input data and target values,
24			which are used in fit/predict cross-validation.
25
26			Parameters
27			----------
28			estimator : sklearn estimator
29			The estimator to be used for the experiment.
30			X : array-like, shape (n_samples, n_features)
31			The input data for the model.
32			y : array-like, shape (n_samples,) or (n_samples, n_outputs)
33			The target values for the model.
34			cv : int or cross-validation generator, default = KFold(n_splits=3, shuffle=True)
35			The number of folds or cross-validation strategy to be used.
36			If int, the cross-validation used is KFold(n_splits=cv, shuffle=True).
37			scoring : callable or str, default = accuracy_score or mean_squared_error
38			sklearn scoring function or metric to evaluate the model's performance.
39			Default is determined by the type of estimator:
40			``accuracy_score`` for classifiers, and
41			``mean_squared_error`` for regressors, as per sklearn convention
42			through the default ``score`` method of the estimator.
43
44			Example
45			-------
46			>>> from hyperactive.experiment.integrations import SklearnCvExperiment
47			>>> from sklearn.datasets import load_iris
48			>>> from sklearn.svm import SVC
49			>>> from sklearn.metrics import accuracy_score
50			>>> from sklearn.model_selection import KFold
51			>>>
52			>>> X, y = load_iris(return_X_y=True)
53			>>>
54			>>> sklearn_exp = SklearnCvExperiment(
55			... estimator=SVC(),
56			... scoring=accuracy_score,
57			... cv=KFold(n_splits=3, shuffle=True),
58			... X=X,
59			... y=y,
60			... )
61			>>> params = {"C": 1.0, "kernel": "linear"}
62			>>> score, add_info = sklearn_exp.score(params)
63
64			For default choices of ``scoring`` and ``cv``:
65			>>> sklearn_exp = SklearnCvExperiment(
66			... estimator=SVC(),
67			... X=X,
68			... y=y,
69			... )
70			>>> params = {"C": 1.0, "kernel": "linear"}
71			>>> score, add_info = sklearn_exp.score(params)
72
73			Quick call without metadata return or dictionary:
74			>>> score = sklearn_exp(C=1.0, kernel="linear")
75			"""
76
77			def __init__(self, estimator, X, y, scoring, cv):
78			self.estimator = estimator
79			self.X = X
80			self.y = y
81			self.scoring = scoring
82			self.cv = cv
83
84			super().__init__()
85
86			if cv is None:
87			from sklearn.model_selection import KFold
88
89			self._cv = KFold(n_splits=3, shuffle=True)
90			elif isinstance(cv, int):
91			from sklearn.model_selection import KFold
92
93			self._cv = KFold(n_splits=cv, shuffle=True)
94			else:
95			self._cv = cv
96
97			self._scoring = check_scoring(estimator=estimator, scoring=scoring)
98
99			def _paramnames(self):
100			"""Return the parameter names of the search.
101
102			Returns
103			-------
104			list of str
105			The parameter names of the search parameters.
106			"""
107			return list(self.estimator.get_params().keys())
108
109			def _score(self, params):
110			"""Score the parameters.
111
112			Parameters
113			----------
114			params : dict with string keys
115			Parameters to score.
116
117			Returns
118			-------
119			float
120			The score of the parameters.
121			dict
122			Additional metadata about the search.
123			"""
124			estimator = clone(self.estimator)
125			estimator.set_params(**params)
126
127			cv_results = cross_validate(
128			estimator,
129			self.X,
130			self.y,
131			cv=self._cv,
132			)
133
134			add_info_d = {
135			"score_time": cv_results["score_time"],
136			"fit_time": cv_results["fit_time"],
137			"n_test_samples": _num_samples(self.X),
138			}
139
140			return cv_results["test_score"].mean(), add_info_d
141
142			@classmethod
143			def get_test_params(cls, parameter_set="default"):
144			"""Return testing parameter settings for the skbase object.
145
146			``get_test_params`` is a unified interface point to store
147			parameter settings for testing purposes. This function is also
148			used in ``create_test_instance`` and ``create_test_instances_and_names``
149			to construct test instances.
150
151			``get_test_params`` should return a single ``dict``, or a ``list`` of ``dict``.
152
153			Each ``dict`` is a parameter configuration for testing,
154			and can be used to construct an "interesting" test instance.
155			A call to ``cls(**params)`` should
156			be valid for all dictionaries ``params`` in the return of ``get_test_params``.
157
158			The ``get_test_params`` need not return fixed lists of dictionaries,
159			it can also return dynamic or stochastic parameter settings.
160
161			Parameters
162			----------
163			parameter_set : str, default="default"
164			Name of the set of test parameters to return, for use in tests. If no
165			special parameters are defined for a value, will return `"default"` set.
166
167			Returns
168			-------
169			params : dict or list of dict, default = {}
170			Parameters to create testing instances of the class
171			Each dict are parameters to construct an "interesting" test instance, i.e.,
172			`MyClass(params)` or `MyClass(params[i])` creates a valid test instance.
173			`create_test_instance` uses the first (or only) dictionary in `params`
174			"""
175			from sklearn.datasets import load_diabetes, load_iris
176			from sklearn.svm import SVC, SVR
177			from sklearn.metrics import accuracy_score, mean_absolute_error
178			from sklearn.model_selection import KFold
179
180			X, y = load_iris(return_X_y=True)
181			params_classif = {
182			"estimator": SVC(),
183			"scoring": accuracy_score,
184			"cv": KFold(n_splits=3, shuffle=True),
185			"X": X,
186			"y": y,
187			}
188
189			X, y = load_diabetes(return_X_y=True)
190			params_regress = {
191			"estimator": SVR(),
192			"scoring": mean_absolute_error,
193			"cv": 2,
194			"X": X,
195			"y": y,
196			}
197
198			X, y = load_diabetes(return_X_y=True)
199			params_all_default = {
200			"estimator": SVR(),
201			"X": X,
202			"y": y,
203			}
204
205			return [params_classif, params_regress, params_all_default]
206
207			@classmethod
208			def _get_score_params(self):
209			"""Return settings for the score function.
210
211			Returns a list, the i-th element corresponds to self.get_test_params()[i].
212			It should be a valid call for self.score.
213
214			Returns
215			-------
216			list of dict
217			The parameters to be used for scoring.
218			"""
219			score_params_classif = {"C": 1.0, "kernel": "linear"}
220			score_params_regress = {"C": 1.0, "kernel": "linear"}
221			score_params_defaults = {"C": 1.0, "kernel": "linear"}
222			return [score_params_classif, score_params_regress, score_params_defaults]
223

SimonBlanke / Hyperactive

Pull Request — master (#110)

SklearnCvExperiment.__init__() A

Complexity

Size

Duplication

Importance

Duplication Side-by-Side

Filter issues like

SklearnCvExperiment.init() A