[英]how to use GridSearchCV with custom estimator in sklearn?
[英]Subclassing sklearn LinearSVC for use as estimator with sklearn GridSearchCV
我試圖創建一個從子類sklearn.svm.LinearSVC
用作一個估計sklearn.model_selection.GridSearchCV
。 子類有一個額外的函數,在這個例子中它什么都不做。 但是,當我運行它時,我最終遇到了一個我似乎無法調試的錯誤。 如果您復制粘貼代碼並運行,它應該重現以ValueError: Input contains NaN, infinity or a value too large for dtype('float64')
結尾的完整錯誤ValueError: Input contains NaN, infinity or a value too large for dtype('float64')
一旦我開始工作,我希望為方法transform_this()
添加更多功能。
有人可以告訴我我哪里出錯了嗎? 基於此,我首先認為這是由於我的數據存在一些問題。 但是,由於我使用 sklearn 內置數據集對其進行了復制,因此情況似乎並非如此。 另外,我相信我根據我在此處對上一個問題的回復正確地對其進行了子類化。 此外,我了解到 GridSearchCV 似乎沒有以不同的方式初始化估計器(不知何故,它首先使用默認參數,正如我從這篇文章中看到的那樣)
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)
你有幾個問題:
LinearSVC
不收斂一旦你糾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])
聲明:本站的技術帖子網頁,遵循CC BY-SA 4.0協議,如果您需要轉載,請注明本站網址或者原文地址。任何問題請咨詢:yoyou2525@163.com.