machine-learning - 对sklearn对OSVM的实现感到困惑

Question

我最近开始尝试使用 OneClassSVM(使用 Sklearn)进行无监督学习，并且我遵循了 this example 。

我对这些愚蠢的问题表示歉意，但我对两件事有点困惑:

1. 我应该在常规示例案例和异常值上训练支持向量机，还是仅在常规示例上进行训练？

2. OSVM 预测并代表异常值的标签是 1 还是 -1

我再次对这些问题表示歉意，但由于某种原因我找不到此记录的任何软件

Answer 1

由于您引用的这个示例是关于新颖性检测的，因此 docs说:

novelty detection:

The training data is not polluted by outliers, and we are interested in detecting anomalies in new observations.

含义:您应该仅使用常规示例进行训练。

该方法基于:

Schölkopf, Bernhard, et al. "Estimating the support of a high-dimensional distribution." Neural computation 13.7 (2001): 1443-1471.

摘录:

Suppose you are given some data set drawn from an underlying probability distribution P and you want to estimate a “simple” subset S of input space such that the probability that a test point drawn from P lies outside of S equals some a priori specied value between 0 and 1.

We propose a method to approach this problem by trying to estimate a function f that is positive on S and negative on the complement.

上面的文档还说:

Inliers are labeled 1, while outliers are labeled -1.

这也可以在您的示例代码中看到，提取:

# Generate some regular novel observations
X = 0.3 * np.random.randn(20, 2)
X_test = np.r_[X + 2, X - 2]
...
# all regular = inliers (defined above)
y_pred_test = clf.predict(X_test)  
...
# -1 = outlier <-> error as assumed to be inlier
n_error_test = y_pred_test[y_pred_test == -1].size