我想子類化sklearn.svm.LinearSVC并將其用作 的估計器sklearn.model_selection.GridSearchCV。我之前在子類化方面遇到了一些問題，我認為我根據我之前的帖子和所選答案修復了它。然而，現在我的目標是創建一個sklearn.kernel_approximation.RBFSampler對象作為我的新類的屬性。現在這是一個例子，我有一個更廣泛的問題：問題： 最終期望將我的新估計器類與 一起使用GridSearchCV，如何根據傳遞到構造函數的參數值（或缺少參數值）創建屬性？然而，正如我在這里了解到的，GridSearchCV 首先使用默認值啟動估計器對象，并且與feature_importances_中的屬性具有類似的實現sklearn.tree.DecisionTreeClassifier。另外，我從上面的代碼中得到的錯誤是：---------------------------------------------------------------------------NameError Traceback (most recent call last)<ipython-input-6-a11420cc931e> in <module> 66 'sampler_n': [10, 200]} 67 ---> 68 gs_model = GridSearchCV(estimator=LinearSVCSub(), verbose=1, param_grid=param_grid, 69 scoring='roc_auc', n_jobs=-1, cv=2) 70 gs_model.fit(X, y)<ipython-input-6-a11420cc931e> in __init__(self, penalty, loss, sampler_gamma, sampler_n, dual, tol, C, multi_class, fit_intercept, intercept_scaling, class_weight, verbose, random_state, max_iter) 21 self.sampler_n = sampler_n 22 ---> 23 self.sampler = create_sampler() 24 25 NameError: name 'create_sampler' is not defined
1 回答
阿波羅的戰車
TA貢獻1862條經驗 獲得超6個贊
使用__init__構造函數作為存儲屬性的容器。
在方法中執行所有相應的邏輯
from sklearn.datasets import make_classification
from sklearn.svm import LinearSVC
from sklearn.model_selection import GridSearchCV
from sklearn.kernel_approximation import RBFSampler
from sklearn.datasets import load_breast_cancer
RANDOM_STATE = 123
class LinearSVCSub(LinearSVC):
def __init__(self, penalty='l2', loss='squared_hinge', sampler_gamma=None, sampler_n=None,
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, sampler=None):
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.sampler_gamma = sampler_gamma
self.sampler_n = sampler_n
self.sampler = sampler
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):
if self.sampler:
X = RBFSampler(gamma=self.sampler_gamma, n_components=self.sampler_n).fit_transform(X)
return X
data = load_breast_cancer()
X, y = data.data, data.target
# Parameter tuning with custom LinearSVC
param_grid = {'C': [0.00001, 0.0005],
'dual': (True, False), 'random_state': [RANDOM_STATE],
'sampler_gamma': [0.90, 0.60, 0.30],
'sampler_n': [10, 200],
'sampler':[0,1]
}
gs_model = GridSearchCV(estimator=LinearSVCSub(sampler=1), verbose=1, param_grid=param_grid,
scoring='roc_auc', n_jobs=-1, cv=2)
gs_model.fit(X, y)
gs_model.cv_results_
添加回答
舉報
0/150
提交
取消