python - 如何在 scikit-learn 中使用管道调整自定义内核函数的参数

Question

目前我已经使用 def 函数成功定义了一个自定义内核函数(预计算内核矩阵)，现在我正在使用 GridSearchCV 函数来获取最佳参数。

因此，在自定义内核函数中，总共有 2 个参数需要调整(即下例中的 gamm 和 sea_gamma)，而且对于 SVR 模型，cost c参数也必须调整。但直到现在，我只能使用 GridSearchCV 调整 cost c 参数 -> 请参阅下面的第一部分:示例。

我已经搜索了一些类似的解决方案，例如:

Is it possible to tune parameters with grid search for custom kernels in scikit-learn?

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)) ”但是这仍然与我的案例和问题不同，但是，我尝试基于此解决方案解决问题，但到目前为止它没有打印任何输出，甚至没有打印任何错误。 -> 请引用第二部分:管道解决方案。

第一部分:示例->我在网格搜索中的原始自定义内核和评分方法是:

    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:管道解决方案

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()

所以，总结一下:

1. 该示例运行良好，但它只能调整默认参数(在本例中为成本参数)
2. 我想调整来自自定义内核的额外参数，我在第 I 部分将其定义为一个函数。
3. scikit-learn 或 python 对我来说还是很新的，如果解释不清楚，如果您对细节有任何疑问，请告诉我。

非常感谢您的阅读，希望详细的描述能让您更清楚一点，欢迎所有建议:)

Answer 1

使用函数包装模型:

def GBC(self):
        model = GradientBoostingRegressor()
        p = [{'learning_rate':[[0.0005,0.01,0.02,0.03]],'n_estimators':[[for i in range(1,100)]],'max_depth':[[4]]}]
        return model,p

然后通过参数网格用内核测试它:

def kernel(self,model,p):
        parameter = ParameterGrid(p)
        clf = GridSearchCV(model, parameter, cv=5, scoring='neg_mean_squared_error',n_jobs=2)
        clf.fit(X,Y)

使用这种方法，您可以在不同的函数上管理函数的种类及其超参数集，直接在 main 中调用该函数

a = the_class()
a.kernel(a.GBC())