基于make_moons数据集建立并比较集成分类器效果

• 发布日期：2019-10-22
• 难度：较难
• 类别：分类与预测、集成分类器
• 标签：Python、scikit-learn、Bagging、Boosting、随机森林、make_moons

1. 问题描述

下面将在make_moons数据集上对比单个决策树、Bagging算法、AdaBoost算法和RandomForest四种算法的预测效果和可视化图。

2. 程序实现

import sklearn
import numpy as np
import matplotlib.pyplot as plt
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import BaggingClassifier
from sklearn.ensemble import AdaBoostClassifier
from sklearn.ensemble import RandomForestClassifier
from sklearn.datasets import make_moons
from sklearn.model_selection import train_test_split
from matplotlib.colors import ListedColormap

#导入数据，划分为训练集和测试集
X, y = sklearn.datasets.make_moons(300,noise=0.3,random_state=42)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)
#分别建立决策树、Bagging、AdaBoost、随机森林模型
clf_tree=DecisionTreeClassifier(max_depth=None, min_samples_split=2, random_state=1)
clf_bagging=BaggingClassifier(n_estimators=100, random_state=1)
clf_adaboost=AdaBoostClassifier(n_estimators=100, random_state=1)
clf_randomforest=RandomForestClassifier(n_estimators=100, random_state=1)
clf_tree = clf_tree.fit(X_train, y_train)
clf_bagging = clf_bagging.fit(X_train, y_train)
clf_adaboost = clf_adaboost.fit(X_train, y_train)
clf_randomforest = clf_randomforest.fit(X_train, y_train)
#准确率评估
tree_score=clf_tree.score(X_test,y_test)
bagging_score=clf_bagging.score(X_test,y_test)
adaboost_score=clf_adaboost.score(X_test,y_test)
randomforest_score=clf_randomforest.score(X_test,y_test)
print("tree_score:%s" % (tree_score))
print("bagging_score:%s" % (bagging_score))
print("adaboost_score:%s" % (adaboost_score))
print("randomforest_score:%s" % (randomforest_score))

tree_score:0.8444444444444444
bagging_score:0.8888888888888888
adaboost_score:0.9111111111111111
randomforest_score:0.8777777777777778

#接下来对4种模型的可视化效果进行比较
#定义效果图绘制函数
def plot_hyperplane(clf, X, y, h=0.02, title='hyperplan'):
    x_min,x_max=X[:,0].min()-1,X[:,0].max()+1
    y_min,y_max=X[:,1].min()-1,X[:,1].max()+1
    xx, yy = np.meshgrid(np.arange(x_min, x_max, h),
                         np.arange(y_min, y_max, h))
    plt.title(title)
    plt.xlim(xx.min(), xx.max())
    plt.ylim(yy.min(), yy.max())
    plt.xticks(())
    plt.yticks(())
    Z=clf.predict(np.c_[xx.ravel(),yy.ravel()]).reshape(xx.shape)
    cmap_light=ListedColormap(['#FFAAAA','#AFEEEE'])
    cmap_dark=ListedColormap(['#FF0000','#000080'])
    plt.pcolormesh(xx,yy,Z,cmap=cmap_light)
    plt.scatter(X[:,0], X[:,1],c=y,cmap=cmap_dark)
#绘制可视化效果图
plt.figure()
plot_hyperplane(clf_tree,X,y,h=0.05,title='tree')
plt.show()