我正在尝试使用Scikit learn对支持向量机进行集成,特别是优化超参数。我随机得到以下错误:
File "C:\Users\jakub\anaconda3\envs\SVM_ensembles\lib\site-packages\sklearn\svm\_base.py", line 250, in _dense_fit
self.probB_, self.fit_status_ = libsvm.fit(
File "sklearn\svm\_libsvm.pyx", line 191, in sklearn.svm._libsvm.fit
ValueError: Invalid input - all samples with positive weights have the same label.
据我所知,这是来自文件https://github.com/scikit-learn/scikit-learn/blob/master/sklearn/svm/src/libsvm/svm.cpp,与1个类中的示例有关,只进入SVM。我使用的是分层K倍交叉验证,数据集相当平衡(一个类45%,另一个55%),所以无论如何都不应该发生这种情况
我能做什么
优化引发错误的代码:
def get_best_ensemble_params(X_train, y_train, X_test, y_test, n_tries=5):
search_spaces = {
"max_samples": Real(0.1, 1, "uniform"),
"max_features": Real(0.1, 1, "uniform"),
"kernel": Categorical(["linear", "poly", "rbf", "sigmoid"]),
"C": Real(1e-6, 1e+6, "log-uniform"),
"gamma": Real(1e-6, 1e+1, "log-uniform")
}
best_accuracy = 0
best_model = None
for i in range(n_tries):
done = False
while not done:
try:
optimizer = BayesSearchCV(SVMEnsemble(), search_spaces, cv=3, n_iter=10, n_jobs=-1, n_points=10,
verbose=1)
optimizer.fit(X_train, y_train) # <- ERROR HERE
accuracy = accuracy_score(y_test, optimizer)
if accuracy > best_accuracy:
best_accuracy = accuracy
best_model = optimizer
done = True
print(i, "job done")
except:
pass
return best_model.best_params_
if __name__ == "__main__":
dataset_name = "acute_inflammations"
loading_functions = {
"acute_inflammations": load_acute_inflammations,
"breast_cancer_coimbra": load_breast_cancer_coimbra,
"breast_cancer_wisconsin": load_breast_cancer_wisconsin
}
X, y = loading_functions[dataset_name]()
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=0)
scaler = StandardScaler()
X_train = scaler.fit_transform(X_train)
X_test = scaler.fit_transform(X_test)
params = get_best_ensemble_params(X_train, y_train, X_test, y_test)
params["n_jobs"] = -1
params["random_state"] = 0
model = SVMEnsemble(n_estimators=20, **params)
model.fit(X_train, y_train)
y_pred = model.predict(X_test)
print("Accuracy:", accuracy_score(y_test, y_pred))
我的自定义SVMEnsemble是BaggingClassifier
硬编码的SVC
:
import inspect
import numpy as np
from sklearn.ensemble import BaggingClassifier
from sklearn.svm import SVC
from skopt import BayesSearchCV
svm_possible_args = {"C", "kernel", "degree", "gamma", "coef0", "shrinking", "probability", "tol", "cache_size",
"class_weight", "max_iter", "decision_function_shape", "break_ties"}
bagging_possible_args = {"n_estimators", "max_samples", "max_features", "bootstrap", "bootstrap_features",
"oob_score", "warm_start", "n_jobs"}
common_possible_args = {"random_state", "verbose"}
class SVMEnsemble(BaggingClassifier):
def __init__(self, voting_method="hard", n_jobs=-1,
n_estimators=10, max_samples=1.0, max_features=1.0,
C=1.0, kernel="linear", gamma="scale",
**kwargs):
if voting_method not in {"hard", "soft"}:
raise ValueError(f"voting_method {voting_method} is not recognized.")
self._voting_method = voting_method
self._C = C
self._gamma = gamma
self._kernel = kernel
passed_args = {
"n_jobs": n_jobs,
"n_estimators": n_estimators,
"max_samples": max_samples,
"max_features": max_features,
"C": C,
"gamma": gamma,
"cache_size": 1024,
}
kwargs.update(passed_args)
svm_args = {
"probability": True if voting_method == "soft" else False,
"kernel": kernel
}
bagging_args = dict()
for arg_name, arg_val in kwargs.items():
if arg_name in svm_possible_args:
svm_args[arg_name] = arg_val
elif arg_name in bagging_possible_args:
bagging_args[arg_name] = arg_val
elif arg_name in common_possible_args:
svm_args[arg_name] = arg_val
bagging_args[arg_name] = arg_val
else:
raise ValueError(f"argument {voting_method} is not recognized.")
self.svm_args = svm_args
self.bagging_args = bagging_args
base_estimator = SVC(**svm_args)
super().__init__(base_estimator=base_estimator, **bagging_args)
@property
def voting_method(self):
return self._voting_method
@voting_method.setter
def voting_method(self, new_voting_method):
if new_voting_method == "soft":
self._voting_method = new_voting_method
self.svm_args["probability"] = True
base_estimator = SVC(**self.svm_args)
super().__init__(base_estimator=base_estimator, **self.bagging_args)
elif self._voting_method == "soft":
self._voting_method = new_voting_method
self.svm_args["probability"] = False
base_estimator = SVC(**self.svm_args)
super().__init__(base_estimator=base_estimator, **self.bagging_args)
else:
self._voting_method = new_voting_method
@property
def C(self):
return self._C
@C.setter
def C(self, new_C):
self._C = new_C
self.svm_args["C"] = new_C
base_estimator = SVC(**self.svm_args)
super().__init__(base_estimator=base_estimator, **self.bagging_args)
@property
def gamma(self):
return self._gamma
@gamma.setter
def gamma(self, new_gamma):
self._gamma = new_gamma
self.svm_args["gamma"] = new_gamma
base_estimator = SVC(**self.svm_args)
super().__init__(base_estimator=base_estimator, **self.bagging_args)
@property
def kernel(self):
return self._kernel
@kernel.setter
def kernel(self, new_kernel):
self._kernel = new_kernel
self.svm_args["kernel"] = new_kernel
base_estimator = SVC(**self.svm_args)
super().__init__(base_estimator=base_estimator, **self.bagging_args)
def predict(self, X):
if self._voting_method == "hard":
return super().predict(X)
elif self._voting_method == "soft":
probabilities = np.zeros((X.shape[0], self.classes_.shape[0]))
for estimator in self.estimators_:
estimator_probabilities = estimator.predict_proba(X)
probabilities += estimator_probabilities
return self.classes_[probabilities.argmax(axis=1)]
else:
raise ValueError(f"voting_method {self._voting_method} is not recognized.")
从您描述问题的方式(您得到的是“非常随机的”)以及对数据和代码的描述来看,我几乎可以肯定问题在于bagging分类器偶尔随机选择一个类的训练示例子样本。K-fold分层拆分在这里对您没有帮助,因为它只会控制数据到训练/测试中的原始拆分,而不会控制BaggingClassifier如何从训练集中选择
max_samples
的随机子样本。如果你看一下code of how BaggingClassifier picks a subsample,你会发现没有针对这种问题的保护一个非常简单的确定方法是用一些较小的数字替换
"max_samples": Real(0.1, 1, "uniform")
,例如"max_samples": Real(0.02, 0.03, "uniform")
(或设置为某个固定的较小值),并检查您是否开始更频繁地收到错误我不确定您是否真的将它用于
n_tries=5
和n_iter=10
(对于您拥有的所有超参数来说似乎有点小),或者使用更大的值和/或可能使用不同的随机种子多次运行整个脚本,但在任何情况下,让我们计算一下max_samples=0.1
出现此类问题的概率并且拥有一个包含120个示例的数据集,其分割率为55%/45%。假设您有96个45/55分割的训练集示例,例如53+43个示例。现在,启用引导功能后,每次训练一个打包分类器时,它都会随机挑选,比如说96个样本中的10个(由于默认情况下启用了引导功能,所以会进行替换)。从较大的班级中挑选所有学生的机会为(53/96)^10,即大约0.26%。这意味着,如果你像这样连续训练50个分类器,其中一个出现问题的几率现在是12.5%。如果你继续运行这样的搜索,你几乎不可避免地会遇到这个问题(为了简单起见,我在这里使用了max_samples=0.1
,这是不正确的,但是你很可能经常接近这个值)最后一个问题是如何处理这个问题。有几个可能的答案:
max_samples
的最小值,或使其取决于示例数李>还有其他可能性-例如,在训练/测试中分割数据后,您可以通过将每个样本替换为
N
相同的样本(其中N
是例如2或10)来人为地膨胀训练数据,以减少bagging分类器仅随机选取一个类的子样本的机会相关问题 更多 >
编程相关推荐