Isolation Forests

In [1]:

    

import pandas as pd
import numpy as np
from sklearn.ensemble import IsolationForest


    

In [2]:

    

x = np.random.randint(1, 10, size=(10, 10))
x[-1, -1] = 100  # anomaly
x[-1, -2] = 200


    

In [3]:

    

x


    

    
Out[3]:





array([[  2,   4,   4,   5,   1,   9,   7,   2,   6,   4],
       [  5,   9,   5,   9,   6,   4,   5,   6,   5,   5],
       [  6,   7,   2,   5,   6,   5,   3,   8,   7,   4],
       [  1,   6,   7,   4,   4,   8,   7,   5,   6,   1],
       [  2,   6,   4,   1,   8,   2,   7,   4,   8,   5],
       [  1,   8,   2,   9,   3,   6,   2,   2,   2,   3],
       [  2,   3,   4,   3,   4,   6,   3,   4,   3,   8],
       [  9,   6,   1,   7,   2,   4,   1,   5,   9,   5],
       [  3,   4,   6,   1,   3,   5,   6,   9,   3,   7],
       [  7,   7,   6,   4,   1,   8,   5,   7, 200, 100]])

In [4]:

    

iforest = IsolationForest(contamination=0.1)
iforest.fit(x)


    

    
Out[4]:





IsolationForest(bootstrap=False, contamination=0.1, max_features=1.0,
        max_samples='auto', n_estimators=100, n_jobs=1, random_state=None,
        verbose=0)

In [5]:

    

iforest.predict(x)


    

    
Out[5]:





array([ 1,  1,  1,  1,  1,  1,  1,  1,  1, -1])

In [6]:

    

est = iforest.estimators_[0]
est.tree_.decision_path(x[-1:, :].astype(np.float32)).todense()


    

    
Out[6]:





matrix([[1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1]])

In [8]:

    

est.tree_.children_right


    

    
Out[8]:





array([10,  7,  4, -1,  6, -1, -1,  9, -1, -1, -1])

In [ ]: