决策树——分类决策树

模型原型
class sklearn.tree.DecisionTreeClassifier(criterion=’gini’,splitter=’best’,
max_depth=None,min_samples_samples_split=2,min_samples_leaf=1,
min_weight_fraction_leaf=0.0,max_features=None,random_state=None, max_leaf_nodes=None,class_weight=None,presor=False)
参数

• criterion:指定切分质量的评分准则
  
  • ’gini’:切分时评价准则是Gini系数
  • ‘entropy’:切分时评价准则是熵
• splitter
• max_depth
• min_samples_split
• min_samples_leaf
• min_weight_fraction_leaf
• max_features
• random_state
• max_leaf_nodes
• class_weight
• presor

属性

• classes_:分类的标签值
• featureimportances
• maxfeatures
• nclasses:分类的数量
• nfeatures
• noutputs
• tree_

方法

• fit(X,y[,sample_weight,check_input,…])
• predict(X[,check_input])
• predict_log_proba(X)
• predict_proda(X)
• score(X,y[,sample_weight])

import numpy as np
import matplotlib.pyplot as plt
from sklearn import datasets
from sklearn.tree import DecisionTreeClassifier
from sklearn import cross_validation

产生随机的数据集

def creat_data(n):
    np.random.seed(0)
    X=5*np.random.rand(n,1)
    y=np.sin(X).ravel()
    noise_num=(int)(n/5)
    y[::5]+=3*(0.5-np.random.rand(noise_num))
    return cross_validation.train_test_split(X,y,test_size=0.25,random_state=1)

加载数据集

def load_data():
    iris=datasets.load_iris()
    X_train=iris.data
    y_train=iris.target
    return cross_validation.train_test_split(X_train,y_train,test_size=0.25,random_state=0,stratify=y_train)

使用DecisionTreeClassifier

def test_DecisionTreeClassifier(*data):
    X_train,X_test,y_train,y_test=data
    clf=DecisionTreeClassifier()
    clf.fit(X_train,y_train)
    print("Training score:%f"%(clf.score(X_train,y_train)))
    print("Testing score:%f"%(clf.score(X_test,y_test)))

X_train,X_test,y_train,y_test=load_data()
test_DecisionTreeClassifier(X_train,X_test,y_train,y_test)

评价准则criterion对分类性能的影响

def test_DecisionTreeClassifier_criterion(*data):
    X_train,X_test,y_train,y_test=data
    criterions=['gini','entropy']
    for criterion in criterions:
        clf=DecisionTreeClassifier(criterion=criterion)
        clf.fit(X_train,y_train.astype('int'))
        print('criterion:%s'%criterion)
        print('Training score:%f'%(clf.score(X_train,
            y_train.astype('int'))))
        print('Testing score:%f'%(clf.score(X_test,y_test.astype('int'))))

X_train,X_test,y_train,y_test=creat_data(100)
test_DecisionTreeClassifier_criterion(X_train,X_test,y_train,y_test)

决策树深度的影响

def test_DecisionTreeClassifier_depth(*data,maxdepth):
    X_train,X_test,y_train,y_test=data
    depths=np.arange(1,maxdepth)
    training_scores=[]
    testing_scores=[]
    for depth in depths:
        clf=DecisionTreeClassifier(max_depth=depth)
        clf.fit(X_train,y_train.astype('int'))
        training_scores.append(clf.score(X_train,y_train.astype('int')))
        testing_scores.append(clf.score(X_test,y_test.astype('int')))
    #绘图
    fig=plt.figure()
    ax=fig.add_subplot(1,1,1)
    ax.plot(depths,training_scores,label='train score',marker='o')
    ax.plot(depths,testing_scores,label='testing score',marker='*')
    ax.set_xlabel('maxdepth')
    ax.set_ylabel('score')
    ax.set_title('Decision Tree Classification')
    ax.legend(framealpha=0.5,loc='best')
    plt.show()

X_train,X_test,y_train,y_test=creat_data(100)
test_DecisionTreeClassifier_depth(X_train,X_test,y_train,y_test,
    maxdepth=100)