8、比较特征选择
import numpy as np
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import MinMaxScaler
from sklearn.svm import LinearSVC
import matplotlib.pyplot as plt
plt.rcParams['font.sans-serif'] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False
# iris 数据集
X, y = load_iris(return_X_y=True)
X_train, X_test, y_train, y_test = train_test_split(X, y, stratify=y, random_state=0)
clf = make_pipeline(MinMaxScaler(), LinearSVC())
clf.fit(X_train, y_train)
print(
"Classification accuracy without selecting features: {:.3f}".format(
clf.score(X_test, y_test)
)
)
from sklearn.feature_selection import SelectKBest, f_classif
selector = SelectKBest(f_classif, k=4)
selector.fit(X_train, y_train)
scores = -np.log10(selector.pvalues_)
scores /= scores.max()
svm_weights = np.abs(clf[-1].coef_).sum(axis=0)
svm_weights /= svm_weights.sum()
clf_selected = make_pipeline(SelectKBest(f_classif, k=4), MinMaxScaler(), LinearSVC())
clf_selected.fit(X_train, y_train)
print(
"Classification accuracy after univariate feature selection: {:.3f}".format(
clf_selected.score(X_test, y_test)
)
)
svm_weights_selected = np.abs(clf_selected[-1].coef_).sum(axis=0)
svm_weights_selected /= svm_weights_selected.sum()
X_indices = np.arange(X.shape[-1])
plt.bar(
X_indices - 0.45, scores, width=0.2, label=r"Univariate score ($-Log(p_{value})$)"
)
plt.bar(X_indices - 0.25, svm_weights, width=0.2, label="SVM weight")
plt.bar(
X_indices[selector.get_support()] - 0.05,
svm_weights_selected,
width=0.2,
label="SVM weights after selection",
)
plt.title("比较特征选择")
plt.xlabel("Feature number")
plt.yticks(())
plt.axis("tight")
plt.legend(loc="upper right")
plt.show()
