运用scikit-learn库进行bagging和AdaBoost

一、bagging

使用酒数据进行分析，数据获取来自该网站数据获取网站，获取数据后，将数据储存为.csv格式。

# 获取数据
import pandas as pd
df_wine = pd.read_csv('wine.csv', header=None)

df_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']

# 删除分类 1
df_wine = df_wine[df_wine['Class label'] != 1]

y = df_wine['Class label'].values
X = df_wine[['Alcohol', 'Hue']].values


# 将数据分为训练数据和测试数据
from sklearn.preprocessing import LabelEncoder
from sklearn.cross_validation import train_test_split

le = LabelEncoder()
y = le.fit_transform(y)

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.40, random_state=1)

# 拟合500棵决策树
from sklearn.ensemble import BaggingClassifier
from sklearn.tree import DecisionTreeClassifier

tree = DecisionTreeClassifier(criterion='entropy', 
                              max_depth=None,
                              random_state=1)

bag = BaggingClassifier(base_estimator=tree,
                        n_estimators=500, 
                        max_samples=1.0, 
                        max_features=1.0, 
                        bootstrap=True, 
                        bootstrap_features=False, 
                        n_jobs=1, 
                        random_state=1)
# 比较 单个决策树 和 bagging 的区别
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)
# 查看训练集和测试集的准确率
print('Decision tree train/test accuracies %.3f/%.3f'
      % (tree_train, tree_test))

bag = bag.fit(X_train, y_train)
y_train_pred = bag.predict(X_train)
y_test_pred = bag.predict(X_test)

bag_train = accuracy_score(y_train, y_train_pred) 
bag_test = accuracy_score(y_test, y_test_pred) 
# 查看训练集和测试集的准确率
print('Bagging train/test accuracies %.3f/%.3f'
      % (bag_train, bag_test))


# 可视化决策区域
% matplotlib inline
import numpy as np
import matplotlib.pyplot as plt
# 使文字可以展示
plt.rcParams['font.sans-serif'] = ['SimHei']
# 使负号可以展示
plt.rcParams['axes.unicode_minus'] = False

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=(8, 3))


for idx, clf, tt in zip([0, 1],
                        [tree, bag],
                        ['Decision Tree', 'Bagging']):
    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('酒精含量', fontsize=12)
plt.text(10.2, -1.2, 
         s='色度', 
         ha='center', va='center', fontsize=12)
    
plt.show()

二、AdaBoost

from sklearn.ensemble import AdaBoostClassifier

tree = DecisionTreeClassifier(criterion='entropy', 
                              max_depth=1,
                              random_state=0)

ada = AdaBoostClassifier(base_estimator=tree,
                         n_estimators=500, 
                         learning_rate=0.1,
                         random_state=0)

# # 比较 决策树 和 Adaboost 的区别
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))

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))

# 可视化决策区域
x_min, x_max = X_train[:, 0].min() - 1, X_train[:, 0].max() + 1
y_min, y_max = X_train[:, 1].min() - 1, 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(1, 2, sharex='col', sharey='row', figsize=(8, 3))


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('酒精含量', fontsize=12)
plt.text(10.2, -1.2, 
         s='色度', 
         ha='center', va='center', fontsize=12)

plt.show()