decision_function不返回结果

不确定你想要实现什么。请注意，0将意味着您的样本将位于决策边界，这是不太可能的。下面的代码片段展示了如何根据decision_function报告的距离对样本设置阈值

import numpy as np
from sklearn.datasets import load_iris
from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression

X, y = load_iris(return_X_y=True)
print(y.shape)
clf = make_pipeline(StandardScaler(), LogisticRegression())
y_pred = clf.fit(X, y).decision_function(X)

# check samples closed to zero boundaries
threshold = 1
mask_y_pred = np.any(np.abs(y_pred) <= threshold, axis=1)

non_zero_y_pred = y_pred[~mask_y_pred]
print(non_zero_y_pred.shape)
print(non_zero_y_pred)