确定 sklearn 中 SVM 分类器最有贡献的特征

Question

我有一个数据集，我想根据该数据训练我的模型。训练后，我需要知道在 SVM 分类器的分类中起主要作用的特征。

森林算法有一个叫做特征重要性的东西，有没有类似的东西？

Answer 1

是的，SVM 分类器有属性 coef_，但它仅适用于具有 线性内核 的 SVM。对于其他内核，这是不可能的，因为数据通过内核方法转换为另一个 space，这与输入 space 无关，检查 explanation.

from matplotlib import pyplot as plt
from sklearn import svm

def f_importances(coef, names):
    imp = coef
    imp,names = zip(*sorted(zip(imp,names)))
    plt.barh(range(len(names)), imp, align='center')
    plt.yticks(range(len(names)), names)
    plt.show()

features_names = ['input1', 'input2']
svm = svm.SVC(kernel='linear')
svm.fit(X, Y)
f_importances(svm.coef_, features_names)

函数的输出如下所示：

Answer 2

仅需一行代码：

拟合 SVM 模型：

from sklearn import svm
svm = svm.SVC(gamma=0.001, C=100., kernel = 'linear')

并按如下方式实现情节：

pd.Series(abs(svm.coef_[0]), index=features.columns).nlargest(10).plot(kind='barh')

结果为：

the most contributing features of the SVM model in absolute values

Answer 3

我创建了一个也适用于 Python 3 的解决方案，它基于 Jakub Macina 的代码片段。

from matplotlib import pyplot as plt
from sklearn import svm

def f_importances(coef, names, top=-1):
    imp = coef
    imp, names = zip(*sorted(list(zip(imp, names))))

    # Show all features
    if top == -1:
        top = len(names)

    plt.barh(range(top), imp[::-1][0:top], align='center')
    plt.yticks(range(top), names[::-1][0:top])
    plt.show()

# whatever your features are called
features_names = ['input1', 'input2', ...] 
svm = svm.SVC(kernel='linear')
svm.fit(X_train, y_train)

# Specify your top n features you want to visualize.
# You can also discard the abs() function 
# if you are interested in negative contribution of features
f_importances(abs(clf.coef_[0]), feature_names, top=10)

Answer 4

如果您正在使用 rbf（径向基函数）内核，您可以按如下方式使用 sklearn.inspection.permutation_importance 来获取特征重要性。 [doc]

from sklearn.inspection import permutation_importance
import numpy as np
import matplotlib.pyplot as plt
%matplotlib inline

svc =  SVC(kernel='rbf', C=2)
svc.fit(X_train, y_train)

perm_importance = permutation_importance(svc, X_test, y_test)

feature_names = ['feature1', 'feature2', 'feature3', ...... ]
features = np.array(feature_names)

sorted_idx = perm_importance.importances_mean.argsort()
plt.barh(features[sorted_idx], perm_importance.importances_mean[sorted_idx])
plt.xlabel("Permutation Importance")

确定 sklearn 中 SVM 分类器最有贡献的特征

Determining the most contributing features for SVM classifier in sklearn

python

machine-learning

svm

scikit-learn