python - 决策树

 决策树(decision tree)是一种基本的分类与回归方法。分类决策树模型是一种描述对实例进行分类的树形结构。决策树由结点(node)和有向边(directed edge)组成。结点有两种类型：内部结点(internal node)和叶结点(leaf node)。内部结点表示一个特征或属性，叶结点表示一个类。

参考：决策树基础篇 https://cuijiahua.com/blog/2017/11/ml_2_decision_tree_1.html

import numpy as np
import scipy.stats as ss
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.externals.six import StringIO
from sklearn.tree import DecisionTreeClassifier,export_graphviz
from sklearn.neighbors import NearestNeighbors,KNeighborsClassifier
from sklearn.metrics import accuracy_score,recall_score,f1_score
from sklearn.externals import joblib

df=pd.DataFrame({"A":ss.norm.rvs(size=100),"B":np.random.randint(low=0,high=10,size=100),\
     "C":np.random.uniform(0, 1, size=100),"D":np.random.randint(low=0,high=2,size=100)})
 
label = df["D"]
df=df.drop("D",axis=1)
 
##切分训练测试、验证集 （6：2：2）
X_tt,X_validation,Y_tt,Y_validation=train_test_split(df.values,label.values,test_size=0.2,random_state=0)
X_train,X_test,Y_train,Y_test=train_test_split(X_tt,Y_tt,test_size=0.25,random_state=0)
   
### tree models

tree_clf = DecisionTreeClassifier()   ### 创建DecisionTreeClassifier()类 ,默认：gini (criterion="entropy" "特征选择标准")
tree_clf.fit(X_train, Y_train)                    ### 使用训练集数据，构建tree


xy_lst = [(X_test, Y_test),(X_validation,Y_validation)]
for i in range(len(xy_lst)):
    x_part = xy_lst[i][0]
    y_part = xy_lst[i][1]
    Y_pred = tree_clf.predict(x_part)                ## 使用验证集的数据进行预测
    print("ACC:", accuracy_score(y_part,Y_pred))  ### sklearn.metrics 评估
    print("REC:", recall_score(y_part,Y_pred))
    print("F-Score:", f1_score(y_part,Y_pred))
    pass

### 存储models
joblib.dump(tree_clf,"tree_clf")    ### joblib 保存模型
##tree_clf = joblib.load("tree_clf")