将 sklearn LinearSVC 子类化以用作 sklearn GridSearchCV 的估计器

Question

我试图创建一个从子类sklearn.svm.LinearSVC用作一个估计sklearn.model_selection.GridSearchCV 。 子类有一个额外的函数，在这个例子中它什么都不做。 但是，当我运行它时，我最终遇到了一个我似乎无法调试的错误。 如果您复制粘贴代码并运行，它应该重现以ValueError: Input contains NaN, infinity or a value too large for dtype('float64')结尾的完整错误ValueError: Input contains NaN, infinity or a value too large for dtype('float64')

一旦我开始工作，我希望为方法transform_this()添加更多功能。

有人可以告诉我我哪里出错了吗？ 基于此，我首先认为这是由于我的数据存在一些问题。 但是，由于我使用 sklearn 内置数据集对其进行了复制，因此情况似乎并非如此。 另外，我相信我根据我在此处对上一个问题的回复正确地对其进行了子类化。 此外，我了解到 GridSearchCV 似乎没有以不同的方式初始化估计器（不知何故，它首先使用默认参数，正如我从这篇文章中看到的那样）

from sklearn.datasets import load_breast_cancer
from sklearn.svm import LinearSVC
from sklearn.model_selection import GridSearchCV

RANDOM_STATE = 123


class LinearSVCSub(LinearSVC):
    def __init__(self, penalty='l2', loss='squared_hinge', additional_parameter1=1, additional_parameter2=100,
                 dual=True, tol=0.0001, C=1.0, multi_class='ovr', fit_intercept=True, intercept_scaling=1,
                 class_weight=None, verbose=0, random_state=None, max_iter=1000):
        super(LinearSVCSub, self).__init__(penalty=penalty, loss=loss, dual=dual, tol=tol,
                                           C=C, multi_class=multi_class, fit_intercept=fit_intercept,
                                           intercept_scaling=intercept_scaling, class_weight=class_weight,
                                           verbose=verbose, random_state=random_state, max_iter=max_iter)

        self.additional_parameter1 = additional_parameter1
        self.additional_parameter2 = additional_parameter2

    def fit(self, X, y, sample_weight=None):
        X = self.transform_this(X)
        super(LinearSVCSub, self).fit(X, y, sample_weight)

    def predict(self, X):
        X = self.transform_this(X)
        super(LinearSVCSub, self).predict(X)

    def score(self, X, y, sample_weight=None):
        X = self.transform_this(X)
        super(LinearSVCSub, self).score(X, y, sample_weight)

    def decision_function(self, X):
        X = self.transform_this(X)
        super(LinearSVCSub, self).decision_function(X)

    def transform_this(self, X):
        return X


if __name__ == '__main__':
    data = load_breast_cancer()
    X, y = data.data, data.target

    # Parameter tuning with custom LinearSVC
    param_grid = {'C': [0.00001, 0.0001, 0.0005],
                      'dual': (True, False), 'random_state': [RANDOM_STATE],
                      'additional_parameter1': [0.90, 0.80, 0.60, 0.30],
                      'additional_parameter2': [20, 30]}

    gs_model = GridSearchCV(estimator=LinearSVCSub(), verbose=1, param_grid=param_grid,
                            scoring='roc_auc', n_jobs=-1)
    gs_model.fit(X, y)

Answer 1

你有几个问题：

1. 定义的方法没有 return 语句
2. 您选择的数据集与LinearSVC不收敛

一旦你纠正了那些你就可以了：

from sklearn.datasets import make_classification
from sklearn.svm import LinearSVC
from sklearn.model_selection import GridSearchCV

RANDOM_STATE = 123


class LinearSVCSub(LinearSVC):
    def __init__(self, penalty='l2', loss='squared_hinge', additional_parameter1=1, additional_parameter2=100,
                 dual=True, tol=0.0001, C=1.0, multi_class='ovr', fit_intercept=True, intercept_scaling=1,
                 class_weight=None, verbose=0, random_state=None, max_iter=100000):
        super(LinearSVCSub, self).__init__(penalty=penalty, loss=loss, dual=dual, tol=tol,
                                           C=C, multi_class=multi_class, fit_intercept=fit_intercept,
                                           intercept_scaling=intercept_scaling, class_weight=class_weight,
                                           verbose=verbose, random_state=random_state, max_iter=max_iter)

        self.additional_parameter1 = additional_parameter1
        self.additional_parameter2 = additional_parameter2

    def fit(self, X, y, sample_weight=None):
        X = self.transform_this(X)
        super(LinearSVCSub, self).fit(X, y, sample_weight)
        return self

    def predict(self, X):
        X = self.transform_this(X)
        return super(LinearSVCSub, self).predict(X)

    def score(self, X, y, sample_weight=None):
        X = self.transform_this(X)
        return super(LinearSVCSub, self).score(X, y, sample_weight)

    def decision_function(self, X):
        X = self.transform_this(X)
        return super(LinearSVCSub, self).decision_function(X)

    def transform_this(self, X):
        return X


X, y = make_classification()

# Parameter tuning with custom LinearSVC
param_grid = {'C': [0.00001, 0.0001, 0.0005],
                  'dual': (True, False), 'random_state': [RANDOM_STATE],
                  'additional_parameter1': [0.90, 0.80, 0.60, 0.30],
                  'additional_parameter2': [20, 30]
             }

gs_model = GridSearchCV(estimator=LinearSVCSub(), verbose=1, param_grid=param_grid,
                        scoring='roc_auc', n_jobs=1)

gs_model.fit(X, y)
Fitting 5 folds for each of 48 candidates, totalling 240 fits
[Parallel(n_jobs=1)]: Using backend SequentialBackend with 1 concurrent workers.
[Parallel(n_jobs=1)]: Done 240 out of 240 | elapsed:    0.9s finished
GridSearchCV(estimator=LinearSVCSub(), n_jobs=1,
             param_grid={'C': [1e-05, 0.0001, 0.0005],
                         'additional_parameter1': [0.9, 0.8, 0.6, 0.3],
                         'additional_parameter2': [20, 30],
                         'dual': (True, False), 'random_state': [123]},
             scoring='roc_auc', verbose=1)

---

gs_model.predict(X)
array([0, 0, 0, 1, 1, 1, 1, 1, 1, 0, 1, 1, 0, 0, 1, 0, 0, 0, 1, 1, 0, 1,
       1, 1, 1, 0, 1, 0, 0, 0, 1, 0, 0, 1, 0, 0, 1, 0, 0, 0, 1, 1, 0, 1,
       1, 0, 0, 0, 1, 0, 1, 1, 0, 1, 0, 0, 1, 1, 1, 1, 0, 1, 1, 1, 0, 1,
       0, 0, 0, 0, 0, 0, 1, 1, 1, 0, 1, 1, 1, 0, 0, 0, 1, 0, 1, 1, 1, 0,
       0, 0, 1, 0, 1, 1, 1, 1, 1, 0, 0, 1])