task06 Boosting

sklearn实现单一决策树和Adaboost算法

1、导入相关的库

# 引入数据科学相关工具包：
import numpy as np
import pandas as pd 
import matplotlib.pyplot as plt
plt.style.use("ggplot")
%matplotlib inline
import seaborn as sns

2、加载UCI的机器学习库里的开源数据集，葡萄酒数据集，该数据集包含了178个样本和13个特征，从不同的角度对不同的化学特性进行描述，我们的任务是根据这些数据预测红酒属于哪一个类别。

# 加载训练数据：         
wine = pd.read_csv("https://archive.ics.uci.edu/ml/machine-learning-databases/wine/wine.data",header=None)
wine.columns = ['Class label', 'Alcohol', 'Malic acid', 'Ash', 'Alcalinity of ash','Magnesium', 'Total phenols','Flavanoids', 'Nonflavanoid phenols', 
                'Proanthocyanins','Color intensity', 'Hue','OD280/OD315 of diluted wines','Proline']

3、查看数据类型

# 数据查看：
print("Class labels",np.unique(wine["Class label"]))
wine.head()

4、去除一类标签以及转化数据格式

# 数据预处理
# 仅仅考虑2，3类葡萄酒，去除1类
wine = wine[wine['Class label'] != 1]
y = wine['Class label'].values  # dataframe转化为数组格式
X = wine[['Alcohol','OD280/OD315 of diluted wines']].values

5、编码

# 将分类标签变成二进制编码：
from sklearn.preprocessing import LabelEncoder
le = LabelEncoder()
y = le.fit_transform(y)

6、分割数据集

# 按8：2分割训练集和测试集
from sklearn.model_selection import train_test_split
X_train,X_test,y_train,y_test = train_test_split(X,y,test_size=0.2,random_state=1,stratify=y)  # stratify参数代表了按照y的类别等比例抽样

7、单一决策树

# 使用单一决策树建模
from sklearn.tree import DecisionTreeClassifier
tree = DecisionTreeClassifier(criterion='entropy',random_state=1,max_depth=1)
from sklearn.metrics import accuracy_score
tree = tree.fit(X_train,y_train)
y_train_pred = tree.predict(X_train)
y_test_pred = tree.predict(X_test)
tree_train = accuracy_score(y_train,y_train_pred)
tree_test = accuracy_score(y_test,y_test_pred)
print('Decision tree train/test accuracies %.3f/%.3f' % (tree_train,tree_test))

8、Adaboost

# 使用sklearn实现Adaboost(基分类器为决策树)
'''
AdaBoostClassifier相关参数：
base_estimator：基本分类器，默认为DecisionTreeClassifier(max_depth=1)
n_estimators：终止迭代的次数
learning_rate：学习率
algorithm：训练的相关算法，{'SAMME'，'SAMME.R'}，默认='SAMME.R'
random_state：随机种子
'''
from sklearn.ensemble import AdaBoostClassifier
ada = AdaBoostClassifier(base_estimator=tree,n_estimators=500,learning_rate=0.1,random_state=1)
ada = ada.fit(X_train,y_train)
y_train_pred = ada.predict(X_train)
y_test_pred = ada.predict(X_test)
ada_train = accuracy_score(y_train,y_train_pred)
ada_test = accuracy_score(y_test,y_test_pred)
print('Adaboost train/test accuracies %.3f/%.3f' % (ada_train,ada_test))

单层决策树似乎对训练数据欠拟合，而Adaboost模型正确地预测了训练数据的所有分类标签，而且与单层决策树相比，Adaboost的测试性能也略有提高。
9、可视化过程

# 画出单层决策树与Adaboost的决策边界：
x_min = X_train[:, 0].min() - 1
x_max = X_train[:, 0].max() + 1
y_min = X_train[:, 1].min() - 1
y_max = X_train[:, 1].max() + 1
xx, yy = np.meshgrid(np.arange(x_min, x_max, 0.1),np.arange(y_min, y_max, 0.1))
f, axarr = plt.subplots(nrows=1, ncols=2,sharex='col',sharey='row',figsize=(12, 6))
for idx, clf, tt in zip([0, 1],[tree, ada],['Decision tree', 'Adaboost']):
    clf.fit(X_train, y_train)
    Z = clf.predict(np.c_[xx.ravel(), yy.ravel()])
    Z = Z.reshape(xx.shape)
    axarr[idx].contourf(xx, yy, Z, alpha=0.3)
    axarr[idx].scatter(X_train[y_train==0, 0],X_train[y_train==0, 1],c='blue', marker='^')
    axarr[idx].scatter(X_train[y_train==1, 0],X_train[y_train==1, 1],c='red', marker='o')
    axarr[idx].set_title(tt)
axarr[0].set_ylabel('Alcohol', fontsize=12)
plt.tight_layout()
plt.text(0, -0.2,s='OD280/OD315 of diluted wines',ha='center',va='center',fontsize=12,transform=axarr[1].transAxes)
plt.show()

Adaboost模型的决策边界比单层决策树的决策边界复杂。

参考：datawhale8月集成学习