孤立森林

import numpy as np
import matplotlib.pyplot as plt
from sklearn.ensemble import IsolationForest

rng = np.random.RandomState(42)

# Generate train data 训练集数据
X = 0.3 * rng.randn(100, 2)
X_train = np.r_[X + 2, X - 2]

# Generate some regular novel observations 新的常规的观察数据
X = 0.3 * rng.randn(20, 2)
X_test = np.r_[X + 2, X - 2]

# Generate some abnormal novel observations 新的不正常的观察数据 
X_outliers = rng.uniform(low=-4, high=4, size=(20, 2))

# fit the model
clf = IsolationForest(max_samples=100, random_state=rng) # 实例化模型
clf.fit(X_train) # 带入训练集数据
y_pred_train = clf.predict(X_train) # 
y_pred_test = clf.predict(X_test) #
y_pred_outliers = clf.predict(X_outliers) #

# plot the line, the samples, and the nearest vectors to the plane
xx, yy = np.meshgrid(np.linspace(-5, 5, 50), np.linspace(-5, 5, 50))
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) # 蓝色的背景

b1 = plt.scatter(X_train[:, 0]
                 , X_train[:, 1]
                 , c='white'
                 , s=20
                 , edgecolor='k')# 训练集，白色

b2 = plt.scatter(X_test[:, 0]
                 , X_test[:, 1]
                 , c='green'
                 , s=20
                 , edgecolor='k')# 测试集，绿色
                 
c = plt.scatter(X_outliers[:, 0]
                , X_outliers[:, 1]
                , c='red'
                , s=20
                , edgecolor='k')# 离群点，红色

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()