机器学习(二十一) 异常检测算法之IsolationForest

import numpy as np
import matplotlib.pyplot as plt
from sklearn.ensemble import IsolationForest
rng=np.random.RandomState(42)
# 生成训练数据
X=0.3*rng.randn(100,2) # 100条二维数据
X_train=np.r_[X+2,X-2] # 200条数据（X+2,X-2）拼接而成

X = 0.3 * rng.randn(20, 2)
X_test = np.r_[X + 2, X - 2]
# 基于分布生成一些观测正常的数据
X_outliers=rng.uniform(low=-4,high=4,size=(20,2))
# 训练隔离森林模型
clf=IsolationForest(behaviour='new',max_samples=100,random_state=rng,contamination='auto')
clf.fit(X_train)
y_pred_train=clf.predict(X_train)
y_pred_test=clf.predict(X_test)
y_pred_outliers = clf.predict(X_outliers)
# 画图
xx, yy = np.meshgrid(np.linspace(-5, 5, 50), np.linspace(-5, 5, 50)) # 生成网络数据 https://www.cnblogs.com/lemonbit/p/7593898.html
Z = clf.decision_function(np.c_[xx.ravel(), yy.ravel()])
Z = Z.reshape(xx.shape)

plt.title("IsolationForest")
plt.contourf(xx, yy, Z, cmap=plt.cm.Blues_r) # 等高线

b1 = plt.scatter(X_train[:, 0], X_train[:, 1], c='white',
                 s=20, edgecolor='k')
b2 = plt.scatter(X_test[:, 0], X_test[:, 1], c='green',
                 s=20, edgecolor='k')
c = plt.scatter(X_outliers[:, 0], X_outliers[:, 1], c='red',
                s=20, edgecolor='k')
plt.axis('tight')
plt.xlim((-5, 5))
plt.ylim((-5, 5))
plt.legend([b1, b2, c],
           ["training observations",
            "new regular observations", "new abnormal observations"],
           loc="upper left")
plt.show()