目前，我已经成功定义了一个自定义内核函数（使用def函数预处理内核矩阵），现在我正在使用GridSearchCV函数获取最佳参数。
因此，在自定义内核函数中，共有2个参数需要调整（如下例中的"gamm"和"sea_gamma"），对于SVR模型，还必须调整成本"c"参数。但是到目前为止，我只能使用GridSearchCV来调整"cost c"参数，请参见下文第I部分：示例。
我搜索了一些类似的解决方案：
是否可以在scikit-learn中使用网格搜索调整自定义内核的参数？
它说：“一种方法是使用Pipeline，SVC（kernel ='precomputed'）并将您的自定义内核函数包装为sklearn估计器（BaseEstimator和TransformerMixin的子类）。”但这仍然与我的情况和问题不同，然而，我尝试基于这个解决方案解决问题，但到目前为止，它没有打印任何输出，甚至没有错误。->请参考下文第II部分：使用管道的解决方案。
第I部分：示例-> 我原始的自定义内核和网格搜索评分方法如下：
import numpy as np
import pandas as pd
import sklearn.svm as svm
from sklearn import preprocessing,svm, datasets
from sklearn.preprocessing import StandardScaler, MaxAbsScaler
from sklearn.metrics.pairwise import rbf_kernel
from sklearn.grid_search import GridSearchCV
from sklearn.svm import SVR
from sklearn.pipeline import Pipeline
from sklearn.metrics.scorer import make_scorer
# weighting the vectors
def distance_scale(X,Y):
K = np.zeros((X.shape[0],Y.shape[0]))
gamma_sea =192
for i in range(X.shape[0]):
for j in range(Y.shape[0]):
dis = min(np.abs(X[i]-Y[j]),1-np.abs(X[i]-Y[j]))
K[i,j] = np.exp(-gamma_sea*dis**2)
return K
# custom RBF kernel : kernel matrix calculation
def sea_rbf(X,Y):
gam=1
t1 = X[:, 5:6]
t2 = Y[:, 5:6]
X = X[:, 0:5]
Y = Y[:, 0:5]
d = distance_scale(t1,t2)
return rbf_kernel(X,Y,gamma=gam)*d
def my_custom_loss_func(y_true, y_pred):
error=np.abs((y_true - y_pred)/y_true)
return np.mean(error)*100
my_scorer = make_scorer(my_custom_loss_func,greater_is_better=False)
# Generate sample data
X_train=np.random.random((100,6))
y_train=np.random.random((100,1))
X_test=np.random.random((40,6))
y_test=np.random.random((40,1))
y_train=np.ravel(y_train)
y_test=np.ravel(y_test)
# scale the input and output in training data set, also scale the input
#in testing data set
max_scale = preprocessing.MaxAbsScaler().fit(X_train)
X_train_max = max_scale.transform(X_train)
X_test_max = max_scale.transform(X_test)
max_scale_y = preprocessing.MaxAbsScaler().fit(y_train)
y_train_max = max_scale_y.transform(y_train)
#precompute the kernel matrix
gam=sea_rbf(X_train_max,X_train_max)
#grid search for the model with the custom scoring method, but can only tune the *cost c* parameter in this case.
clf= GridSearchCV(SVR(kernel='precomputed'),
scoring=my_scorer,
cv=5,
param_grid={"C": [0.1,1,2,3,4,5]
})
clf.fit(gam, y_train_max)
print(clf.best_params_)
print(clf.best_score_)
print(clf.grid_scores_)
第二部分：使用Pipeline的解决方案
from __future__ import print_function
from __future__ import division
import sys
import sklearn
from sklearn.base import BaseEstimator, TransformerMixin
from sklearn.pipeline import Pipeline
# Wrapper class for the custom kernel RBF_kernel
class RBF2Kernel(BaseEstimator,TransformerMixin):
def __init__(self, gamma=1,sea_gamma=20):
super(RBF2Kernel,self).__init__()
self.gamma = gamma
self.sea_gamma = sea_gamma
def fit(self, X, y=None, **fit_params):
return self
#calculate the kernel matrix
def transform(self, X):
self.a_train_ = X[:, 0:5]
self.b_train_ = X[:, 0:5]
self.t1_train_ = X[:, 5:6]
self.t2_train_ = X[:, 5:6]
sea=16
K = np.zeros((t1.shape[0],t2.shape[0]))
for i in range(self.t1_train_.shape[0]):
for j in range(self.t2_train_.shape[0]):
dis = min(np.abs(self.t1_train_[i]*sea- self.t2_train_[j]*sea),sea-np.abs(self.t1_train_[i]*sea-self.t2_train_[j]*sea))
K[i,j] = np.exp(-self.gamma_sea *dis**2)
return K
return rbf_kernel(self.a_train_ , self.b_train_, gamma=self.gamma)*K
def main():
print('python: {}'.format(sys.version))
print('numpy: {}'.format(np.__version__))
print('sklearn: {}'.format(sklearn.__version__))
# Generate sample data
X_train=np.random.random((100,6))
y_train=np.random.random((100,1))
X_test=np.random.random((40,6))
y_test=np.random.random((40,1))
y_train=np.ravel(y_train)
y_test=np.ravel(y_test)
# Create a pipeline where our custom predefined kernel RBF2Kernel
# is run before SVR.
pipe = Pipeline([
('sc', MaxAbsScaler()),
('rbf2', RBF2Kernel()),
('svm', SVR()),
])
# Set the parameter 'gamma' of our custom kernel by
# using the 'estimator__param' syntax.
cv_params = dict([
('rbf2__gamma', 10.0**np.arange(-2,2)),
('rbf2__sea_gamma', 10.0**np.arange(-2,2)),
('svm__kernel', ['precomputed']),
('svm__C', 10.0**np.arange(-2,2)),
])
# Do grid search to get the best parameter value of 'gamma'.
# here i am also trying to tune the parameters of the custom kernel
model = GridSearchCV(pipe, cv_params, verbose=1, n_jobs=-1,scoring=my_scorer)
model.fit(X_train, y_train)
y_pred = model.predict(X_test)
acc_test = mean_absolute_error(y_test, y_pred)
mape_100 = my_custom_loss_func (y_test, y_pred)
print("Test accuracy: {}".format(acc_test))
print("mape_100: {}".format(mape_100))
print("Best params:")
print(model.best_params_)
print(model.grid_scores_)
if __name__ == '__main__':
main()
因此，总结一下：
- 这个例子效果很好，但它只能调整默认参数（在本例中是成本参数）。
- 我想要调整来自我在第一部分中定义的自定义内核的额外参数。
- 对于我来说，scikit-learn或Python仍然很新颖，如果解释不清楚，请让我知道是否有任何关于细节的问题。
非常感谢您的阅读，希望长描述会让您更加清晰，欢迎所有建议 :)
print(model.best_params_)- Vivek Kumar