子类化 sklearn LinearSVC 以用作 sklearn GridSearchCV 的估计器

Question

我正在尝试从 sklearn.svm.LinearSVC 创建一个子 class 用作 sklearn.model_selection.GridSearchCV 的估算器。 child class 有一个额外的函数，在这个例子中它不做任何事情。但是，当我 运行 时，我最终遇到了一个我似乎无法调试的错误。如果您 copy-paste 代码和 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

一旦我得到他的工作，我希望为方法添加更多功能 transform_this()。

谁能告诉我哪里出错了？基于 this I first thought it was due to some issues with my data. However, since I've reproduced it using the sklearn built-in dataset it seems not to be the case. Also, I believe I'm subclassing this properly based on the response I got for my previous question . Also, I learnt that the GridSearchCV doesn't seem to initialise the estimator in a different way (somehow it first uses default arguments as I see from )

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
不一致

一旦您纠正了那些就可以了：

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])