import numpy as np
import matplotlib.pyplot as plt from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier,DecisionTreeRegressor def load_data():
'''
加载用于分类问题的数据集。数据集采用 scikit-learn 自带的 iris 数据集
'''
# scikit-learn 自带的 iris 数据集
iris=datasets.load_iris()
X_train=iris.data
y_train=iris.target
return train_test_split(X_train, y_train,test_size=0.25,random_state=0,stratify=y_train) #分类决策树DecisionTreeClassifier模型
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))) # 产生用于分类问题的数据集
X_train,X_test,y_train,y_test=load_data()
# 调用 test_DecisionTreeClassifier
test_DecisionTreeClassifier(X_train,X_test,y_train,y_test)

def test_DecisionTreeClassifier_criterion(*data):
'''
测试 DecisionTreeClassifier 的预测性能随 criterion 参数的影响
'''
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)
print("criterion:%s"%criterion)
print("Training score:%f"%(clf.score(X_train,y_train)))
print("Testing score:%f"%(clf.score(X_test,y_test))) # 调用 test_DecisionTreeClassifier_criterion
test_DecisionTreeClassifier_criterion(X_train,X_test,y_train,y_test)

def test_DecisionTreeClassifier_splitter(*data):
'''
测试 DecisionTreeClassifier 的预测性能随划分类型的影响
'''
X_train,X_test,y_train,y_test=data
splitters=['best','random']
for splitter in splitters:
clf = DecisionTreeClassifier(splitter=splitter)
clf.fit(X_train, y_train)
print("splitter:%s"%splitter)
print("Training score:%f"%(clf.score(X_train,y_train)))
print("Testing score:%f"%(clf.score(X_test,y_test))) # 调用 test_DecisionTreeClassifier_splitter
test_DecisionTreeClassifier_splitter(X_train,X_test,y_train,y_test)

def test_DecisionTreeClassifier_depth(*data,maxdepth):
'''
测试 DecisionTreeClassifier 的预测性能随 max_depth 参数的影响
'''
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)
training_scores.append(clf.score(X_train,y_train))
testing_scores.append(clf.score(X_test,y_test)) ## 绘图
fig=plt.figure()
ax=fig.add_subplot(1,1,1)
ax.plot(depths,training_scores,label="traing 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() # 调用 test_DecisionTreeClassifier_depth
test_DecisionTreeClassifier_depth(X_train,X_test,y_train,y_test,maxdepth=100)

import os
import pydotplus from io import StringIO
from sklearn.tree import export_graphviz
from sklearn.tree import DecisionTreeClassifier,DecisionTreeRegressor X_train,X_test,y_train,y_test=load_data()
clf = DecisionTreeClassifier()
clf.fit(X_train,y_train)
export_graphviz(clf,"F://out")

吴裕雄 python 机器学习——分类决策树模型的更多相关文章

  1. 吴裕雄 python 机器学习——回归决策树模型

    import numpy as np import matplotlib.pyplot as plt from sklearn import datasets from sklearn.model_s ...

  2. 吴裕雄 python 机器学习——核化PCAKernelPCA模型

    # -*- coding: utf-8 -*- import numpy as np import matplotlib.pyplot as plt from sklearn import datas ...

  3. 吴裕雄 python 机器学习——KNN分类KNeighborsClassifier模型

    import numpy as np import matplotlib.pyplot as plt from sklearn import neighbors, datasets from skle ...

  4. 吴裕雄 python 机器学习——支持向量机SVM非线性分类SVC模型

    import numpy as np import matplotlib.pyplot as plt from sklearn import datasets, linear_model,svm fr ...

  5. 吴裕雄 python 机器学习——支持向量机线性分类LinearSVC模型

    import numpy as np import matplotlib.pyplot as plt from sklearn import datasets, linear_model,svm fr ...

  6. 吴裕雄 python 机器学习——集成学习梯度提升决策树GradientBoostingRegressor回归模型

    import numpy as np import matplotlib.pyplot as plt from sklearn import datasets,ensemble from sklear ...

  7. 吴裕雄 python 机器学习——集成学习随机森林RandomForestClassifier分类模型

    import numpy as np import matplotlib.pyplot as plt from sklearn import datasets,ensemble from sklear ...

  8. 吴裕雄 python 机器学习——集成学习AdaBoost算法分类模型

    import numpy as np import matplotlib.pyplot as plt from sklearn import datasets,ensemble from sklear ...

  9. 吴裕雄 python 机器学习——模型选择分类问题性能度量

    import numpy as np import matplotlib.pyplot as plt from sklearn.svm import SVC from sklearn.datasets ...

随机推荐

  1. 利用chrome浏览器爬取数据

    相关的库自己下载吧,直接上代码 from selenium import webdriver from bs4 import BeautifulSoup import time #手动添加路径 pat ...

  2. 在CentOS 7上安装Nginx

    本教程中的步骤要求用户拥有root权限 第一步 - 添加Nginx存储库要添加CentOS 7 EPEL仓库,请打开终端并使用以下命令: sudo yum install epel-release第二 ...

  3. redhat 开课啦

    今天是三八女神节. 终于开课啦,为考取RHCE准备.

  4. python-pcl

    python-pcl安装和使用 https://blog.csdn.net/joker_hapy/article/details/85006818 Ubuntu16.04下安装PCL及python-p ...

  5. Python3.4 枚举类型的使用

    From: https://majing.io/posts/10000005131196 枚举类型是在Python3.4新增到Python的标准库. 创建枚举 Python提供了两种方法来创建枚举: ...

  6. global的使用

    对于一个全局变量,你的函数里如果只使用到了它的值,而没有对其赋值(指a = XXX这种写法)的话,就不需要声明global. 相反,如果你对其赋了值的话,那么你就需要声明global.声明global ...

  7. java时间日期类(Date、DateFormat、Calendar)学习

    1.Date类 常用方法:long getTime(),用于返回当前时刻的毫秒值 Date d = new Date(2000); System.out.println(d.getTime());// ...

  8. MySQL 错误集-汇总

    Q&A: MySQl报错之@@GLOBAL.GTID_PURGED can only be set when @@GLOBAL.GTID_MODE = ON 导入的时候加入-f参数即可 原因分 ...

  9. 05-Eclispe配置Tomcat插件

    此插件只针对 eclipse-java-indigo-SR2-win32 这个开发工具使用的 1.下载tomcat插件 2.解压到指定位置 3.找到eclispe安装目录 D:\software\ec ...

  10. Layout-2相关代码:3列布局代码演化[一]

    <!doctype html> <html> <head> <meta charset="utf-8"> <title> ...