eckity.sklearn_compatible.sk_classifier

 1from sklearn.base import ClassifierMixin
 2from sklearn.utils.validation import check_is_fitted
 3
 4from eckity.sklearn_compatible.sklearn_wrapper import SklearnWrapper
 5from eckity.sklearn_compatible.classification_evaluator import (
 6    ClassificationEvaluator,
 7)
 8
 9
10class SKClassifier(SklearnWrapper, ClassifierMixin):
11    def predict(self, X):
12        """
13        Compute output using best evolved individual.
14        Use `predict` in a sklearn setting.
15        Input is a numpy array.
16
17        Parameters
18        ----------
19        X : array-like or sparse matrix of (num samples, num feautres)
20
21        Returns
22        -------
23        y : array, shape (num samples,)
24            Returns predicted values after applying classification.
25        """
26
27        # Check is fit had been called
28        check_is_fitted(self)
29
30        clf_eval: ClassificationEvaluator = (
31            self.algorithm.get_individual_evaluator()
32        )
33
34        # ignore y since we only need execute result and evolution is finished
35        clf_eval.set_context((X, None))
36
37        return clf_eval.classify_individual(self.algorithm.best_of_run_)
38
39    def predict_proba(self, X):
40        raise NotImplementedError("not implemented yet")
41
42    def predict_log_proba(self, X):
43        raise NotImplementedError("not implemented yet")
class SKClassifier(eckity.sklearn_compatible.sklearn_wrapper.SklearnWrapper, sklearn.base.ClassifierMixin):
11class SKClassifier(SklearnWrapper, ClassifierMixin):
12    def predict(self, X):
13        """
14        Compute output using best evolved individual.
15        Use `predict` in a sklearn setting.
16        Input is a numpy array.
17
18        Parameters
19        ----------
20        X : array-like or sparse matrix of (num samples, num feautres)
21
22        Returns
23        -------
24        y : array, shape (num samples,)
25            Returns predicted values after applying classification.
26        """
27
28        # Check is fit had been called
29        check_is_fitted(self)
30
31        clf_eval: ClassificationEvaluator = (
32            self.algorithm.get_individual_evaluator()
33        )
34
35        # ignore y since we only need execute result and evolution is finished
36        clf_eval.set_context((X, None))
37
38        return clf_eval.classify_individual(self.algorithm.best_of_run_)
39
40    def predict_proba(self, X):
41        raise NotImplementedError("not implemented yet")
42
43    def predict_log_proba(self, X):
44        raise NotImplementedError("not implemented yet")

Sklearn-compatible wrapper to support evolution using sklearn methods.

Parameters
  • algorithm (Algorithm): Wrapped Evolutionary algorithm. The Wrapper invokes 'evolve' and 'execute' methods of the algorithm during the fitting and prediction process, respectively.
Attributes
  • is_fitted (bool): Determines if the model is fitted (evolved).
def predict(self, X):
12    def predict(self, X):
13        """
14        Compute output using best evolved individual.
15        Use `predict` in a sklearn setting.
16        Input is a numpy array.
17
18        Parameters
19        ----------
20        X : array-like or sparse matrix of (num samples, num feautres)
21
22        Returns
23        -------
24        y : array, shape (num samples,)
25            Returns predicted values after applying classification.
26        """
27
28        # Check is fit had been called
29        check_is_fitted(self)
30
31        clf_eval: ClassificationEvaluator = (
32            self.algorithm.get_individual_evaluator()
33        )
34
35        # ignore y since we only need execute result and evolution is finished
36        clf_eval.set_context((X, None))
37
38        return clf_eval.classify_individual(self.algorithm.best_of_run_)

Compute output using best evolved individual. Use predict in a sklearn setting. Input is a numpy array.

Parameters
  • X (array-like or sparse matrix of (num samples, num feautres)):
Returns
  • y (array, shape (num samples,)): Returns predicted values after applying classification.
def predict_proba(self, X):
40    def predict_proba(self, X):
41        raise NotImplementedError("not implemented yet")
def predict_log_proba(self, X):
43    def predict_log_proba(self, X):
44        raise NotImplementedError("not implemented yet")
def set_partial_fit_request(unknown):

Descriptor for defining set_{method}_request methods in estimators.

New in version 1.3.

Parameters
  • name (str): The name of the method for which the request function should be created, e.g. "fit" would create a set_fit_request function.
  • keys (list of str): A list of strings which are accepted parameters by the created function, e.g. ["sample_weight"] if the corresponding method accepts it as a metadata.
  • validate_keys (bool, default=True): Whether to check if the requested parameters fit the actual parameters of the method.
Notes

This class is a descriptor 1 and uses PEP-362 to set the signature of the returned function 2.

References
def set_score_request(unknown):

Descriptor for defining set_{method}_request methods in estimators.

New in version 1.3.

Parameters
  • name (str): The name of the method for which the request function should be created, e.g. "fit" would create a set_fit_request function.
  • keys (list of str): A list of strings which are accepted parameters by the created function, e.g. ["sample_weight"] if the corresponding method accepts it as a metadata.
  • validate_keys (bool, default=True): Whether to check if the requested parameters fit the actual parameters of the method.
Notes

This class is a descriptor 1 and uses PEP-362 to set the signature of the returned function 2.

References