Python：如何用用户定义的函数拟合模型

Question

我正在研究隔离林。我实现此代码是为了构建包含 iTrees 的隔离林。

import pandas as pd
import numpy as np
import random
from sklearn.model_selection import train_test_split

class ExNode:
    def __init__(self,size):
        self.size=size


class InNode:
    def __init__(self,left,right,splitAtt,splitVal):
        self.left=left
        self.right=right
        self.splitAtt=splitAtt
        self.splitVal=splitVal

def iForest(X,noOfTrees,sampleSize):
forest=[]

hlim=int(np.ceil(np.log2(max(sampleSize, 2))))
for i in range(noOfTrees):
    X_train=X.sample(sampleSize)
    forest.append(iTree(X_train,0,hlim))
return forest


def iTree(X,currHeight,hlim):
if currHeight>=hlim or len(X)<=1:
    return ExNode(len(X))
else:
    Q=X.columns
    q=random.choice(Q)
    p=random.choice(X[q].unique())
    X_l=X[X[q]<p]
    X_r=X[X[q]>=p]
    return InNode(iTree(X_l,currHeight+1,hlim),iTree(X_r,currHeight+1,hlim),q,p)

def pathLength(x,Tree,currHeight):
if isinstance(Tree,ExNode):
    return currHeight
a=Tree.splitAtt
if x[a]<Tree.splitVal:
    return pathLength(x,Tree.left,currHeight+1)
else:
    return pathLength(x,Tree.right,currHeight+1)


def _h(i):
    return np.log2(i) + 0.5772156649 

def _c(n):
    if n > 2:
        h = _h(n-1)
        return 2*h - (2*(n - 1)/n)
    if n == 2:
        return 1
    else:
        return 0


def _anomaly_score(score, n_samples):
    score = -score/_c(n_samples)
    return 2**score

df=pd.read_csv("db.csv")
y_true=df['Target']
df_data=df.drop('Target',1)
sampleSize=256
X_train, X_test, y_train, y_test = train_test_split(df_data, y_true, test_size=0.3)
ifor=iForest(X_train,100,sampleSize)

for index, row in test.iterrows():    
    sxn = 0;
    testLenLst = []
    for tree in ifor:
        testLenLst.append(pathLength(row,tree,0))             
    if(len(testLenLst) != 0):
        ehx = (sum(testLenLst) / float(len(testLenLst)))  
        if(_anomaly_score(ehx,sampleSize) >= .5):
            print("Anomaly S(x,n) " + str(_anomaly_score(ehx,sampleSize)))
        else:
            print("Normal S(x,n) " + str(_anomaly_score(ehx,sampleSize)))

其实真正的问题是我想显示一个iTree。为此，我使用函数 .fit() 来构建模型。但是 .fit () 仅适用于根据 python 上的预定义算法构建的模型。而就我而言，是我开发了隔离森林算法。下面是我如何尝试模型构建以及 iTree 的显示。

from sklearn.tree import export_graphviz
ifor.fit(X_train)
estimator = ifor.tree[1]

export_graphviz(estimator, 
                out_file='tree.dot', 
                feature_names = df.feature_names,
                class_names = df.target_names,
                rounded = True, proportion = False, 
                precision = 2, filled = True)

from subprocess import call

call(['dot', '-Tpng', 'tree.dot', '-o', 'tree.png', '-Gdpi=600'])
from IPython.display import Image 
Image(filename = 'tree.png')

它向我显示以下错误： The error i get when i try to display an iTree

Answer 1

你的问题不清楚，但最好的做法是遵循 How to write a custom estimator in sklearn and use cross-validation on it? 编写自定义估算器并使用适当的规则编写 fit() 方法的实现，否则它可能会非常混乱，

由于Python使用duck typing，尽量避免这种复杂化并使用sklearn.BaseEstimator

Python：如何用用户定义的函数拟合模型

Python: How to fit a model with user defined functions

python

machine-learning

training-data

scikit-learn

anomaly-detection