## 一、什幺是集成学习

### 集成学习的方法：

1. 基于投票思想的多数票机制的集成分类器(MajorityVoteClassifier)

2. 于bagging思想的套袋集成技术(BaggingClassifier)

4. 分层模型集成框架stacking(叠加算法)

## 二、基于投票思想的集成分类器

```## 加载相关库
from sklearn.datasets import load_iris   # 加载数据
from sklearn.model_selection import train_test_split  # 切分训练集与测试集
from sklearn.preprocessing import StandardScaler  # 标准化数据
from sklearn.preprocessing import LabelEncoder   # 标签化分类变量```

```## 初步处理数据
X,y = iris.data[50:,[1,2]],iris.target[50:]
le = LabelEncoder()
y = le.fit_transform(y)
X_train,X_test,y_train,y_test = train_test_split(X,y,test_size=0.5,random_state=1,stratify=y)```

```## 我们使用训练集训练三种不同的分类器：逻辑回归 + 决策树 + k-近邻分类器
from sklearn.model_selection import cross_val_score   # 10折交叉验证评价模型
from sklearn.linear_model import LogisticRegression
from sklearn.tree import DecisionTreeClassifier
from sklearn.neighbors import KNeighborsClassifier
from sklearn.pipeline import Pipeline   # 管道简化工作流
clf1 = LogisticRegression(penalty='l2',C=0.001,random_state=1)
clf2 = DecisionTreeClassifier(max_depth=1,criterion='entropy',random_state=0)
clf3 = KNeighborsClassifier(n_neighbors=1,p=2,metric="minkowski")
pipe1 = Pipeline([['sc',StandardScaler()],['clf',clf1]])
pipe3 = Pipeline([['sc',StandardScaler()],['clf',clf3]])
clf_labels = ['Logistic regression','Decision tree','KNN']
print('10-folds cross validation :\n')
for clf,label in zip([pipe1,clf2,pipe3],clf_labels):
scores = cross_val_score(estimator=clf,X=X_train,y=y_train,cv=10,scoring='roc_auc')
print("ROC AUC: %0.2f(+/- %0.2f)[%s]"%(scores.mean(),scores.std(),label))```

```## 我们使用MajorityVoteClassifier集成：
from sklearn.ensemble import VotingClassifier
mv_clf = VotingClassifier(estimators=[('pipe1',pipe1),('clf2',clf2),('pipe3',pipe3)],voting='soft')
clf_labels += ['MajorityVoteClassifier']
all_clf = [pipe1,clf2,pipe3,mv_clf]
print('10-folds cross validation :\n')
for clf,label in zip(all_clf,clf_labels):
scores = cross_val_score(estimator=clf,X=X_train,y=y_train,cv=10,scoring='roc_auc')
print("ROC AUC: %0.2f(+/- %0.2f)[%s]"%(scores.mean(),scores.std(),label))
## 对比下面结果，可以得知多数投票方式的分类算法，抗差能力更强。```

```## 使用ROC曲线评估集成分类器
from sklearn.metrics import roc_curve
from sklearn.metrics import auc
colors = ['black','orange','blue','green']
linestyles = [':','--','-.','-']
plt.figure(figsize=(10,6))
for clf,label,clr,ls in zip(all_clf,clf_labels,colors,linestyles):
y_pred = clf.fit(X_train,y_train).predict_proba(X_test)[:,1]
fpr,tpr,trhresholds = roc_curve(y_true=y_test,y_score=y_pred)
roc_auc = auc(x=fpr,y=tpr)
plt.plot(fpr,tpr,color=clr,linestyle=ls,label='%s (auc=%0.2f)'%(label,roc_auc))
plt.legend(loc='lower right')
plt.plot([0,1],[0,1],linestyle='--',color='gray',linewidth=2)
plt.xlim([-0.1,1.1])
plt.ylim([-0.1,1.1])
plt.xlabel('False positive rate (FPR)')
plt.xlabel('True positive rate (TPR)')
plt.show()```

## 三、基于bagging思想的套袋集成技术

```## 我们使用葡萄酒数据集进行建模(数据处理)
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']
df_wine = df_wine[df_wine['Class label'] != 1]  # drop 1 class
y = df_wine['Class label'].values
X = df_wine[['Alcohol','OD280/OD315 of diluted wines']].values
from sklearn.model_selection import train_test_split  # 切分训练集与测试集
from sklearn.preprocessing import LabelEncoder   # 标签化分类变量
le = LabelEncoder()
y = le.fit_transform(y)
X_train,X_test,y_train,y_test = train_test_split(X,y,test_size=0.2,random_state=1,stratify=y)```

```## 我们使用单一决策树分类：
tree = DecisionTreeClassifier(criterion='entropy',random_state=1,max_depth=None)   #选择决策树为基本分类器
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))```

```## 我们使用BaggingClassifier分类：
from sklearn.ensemble import BaggingClassifier
tree = DecisionTreeClassifier(criterion='entropy',random_state=1,max_depth=None)   #选择决策树为基本分类器
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)
from sklearn.metrics import accuracy_score
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)
print('Bagging train/test accuracies %.3f/%.3f' % (bag_train,bag_test))```

```## 我们来对比下这两个分类方法上的差异
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, 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='green', 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()```

## 四、基于boosting思想的自适应增强方法

#### 与Bagging相比，Boosting思想可以降低偏差。

```## 我们用单一决策树建模：
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))```

```## 我们使用Adaboost集成建模：

```## 我们观察下Adaboost与决策树的异同
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))
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()```

## 五、分层模型集成框架stacking（叠加算法）

Stacking集成算法可以理解为一个两层的集成，第一层含有一个分类器，把预测的结果(元特征)提供给第二层， 而第二层的分类器通常是逻辑回归，他把一层分类器的结果当做特征做拟合输出预测结果。

#### 由于目前sklearn没有Stacking相关的类，因此我们使用mlxtend库！！！！

http://rasbt.github.io/mlxtend/user_guide/classifier/StackingClassifier/

http://rasbt.github.io/mlxtend/user_guide/classifier/StackingCVClassifier/

1. 简单堆叠3折CV分类：

```## 1. 简单堆叠3折CV分类
from sklearn import datasets
X, y = iris.data[:, 1:3], iris.target
from sklearn.model_selection import cross_val_score
from sklearn.linear_model import LogisticRegression
from sklearn.neighbors import KNeighborsClassifier
from sklearn.naive_bayes import GaussianNB
from sklearn.ensemble import RandomForestClassifier
from mlxtend.classifier import StackingCVClassifier
RANDOM_SEED = 42
clf1 = KNeighborsClassifier(n_neighbors=1)
clf2 = RandomForestClassifier(random_state=RANDOM_SEED)
clf3 = GaussianNB()
lr = LogisticRegression()
# Starting from v0.16.0, StackingCVRegressor supports
# `random_state` to get deterministic result.
sclf = StackingCVClassifier(classifiers=[clf1, clf2, clf3],  # 第一层分类器
meta_classifier=lr,   # 第二层分类器
random_state=RANDOM_SEED)
print('3-fold cross validation:\n')
for clf, label in zip([clf1, clf2, clf3, sclf], ['KNN', 'Random Forest', 'Naive Bayes','StackingClassifier']):
scores = cross_val_score(clf, X, y, cv=3, scoring='accuracy')
print("Accuracy: %0.2f (+/- %0.2f) [%s]" % (scores.mean(), scores.std(), label))```

```## 我们画出决策边界
from mlxtend.plotting import plot_decision_regions
import matplotlib.gridspec as gridspec
import itertools
gs = gridspec.GridSpec(2, 2)
fig = plt.figure(figsize=(10,8))
for clf, lab, grd in zip([clf1, clf2, clf3, sclf],
['KNN',
'Random Forest',
'Naive Bayes',
'StackingCVClassifier'],
itertools.product([0, 1], repeat=2)):
clf.fit(X, y)
ax = plt.subplot(gs[grd[0], grd[1]])
fig = plot_decision_regions(X=X, y=y, clf=clf)
plt.title(lab)
plt.show()```

2.使用概率作为元特征：

```## 2.使用概率作为元特征
clf1 = KNeighborsClassifier(n_neighbors=1)
clf2 = RandomForestClassifier(random_state=1)
clf3 = GaussianNB()
lr = LogisticRegression()
sclf = StackingCVClassifier(classifiers=[clf1, clf2, clf3],
use_probas=True,
meta_classifier=lr,
random_state=42)
print('3-fold cross validation:\n')
for clf, label in zip([clf1, clf2, clf3, sclf],
['KNN',
'Random Forest',
'Naive Bayes',
'StackingClassifier']):
scores = cross_val_score(clf, X, y,
cv=3, scoring='accuracy')
print("Accuracy: %0.2f (+/- %0.2f) [%s]"
% (scores.mean(), scores.std(), label))```

3. 堆叠5折CV分类与网格搜索(结合网格搜索调参优化)：

```## 3. 堆叠5折CV分类与网格搜索(结合网格搜索调参优化)
from sklearn.linear_model import LogisticRegression
from sklearn.neighbors import KNeighborsClassifier
from sklearn.naive_bayes import GaussianNB
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import GridSearchCV
from mlxtend.classifier import StackingCVClassifier
# Initializing models
clf1 = KNeighborsClassifier(n_neighbors=1)
clf2 = RandomForestClassifier(random_state=RANDOM_SEED)
clf3 = GaussianNB()
lr = LogisticRegression()
sclf = StackingCVClassifier(classifiers=[clf1, clf2, clf3],
meta_classifier=lr,
random_state=42)
params = {'kneighborsclassifier__n_neighbors': [1, 5],
'randomforestclassifier__n_estimators': [10, 50],
'meta_classifier__C': [0.1, 10.0]}
grid = GridSearchCV(estimator=sclf,
param_grid=params,
cv=5,
refit=True)
grid.fit(X, y)
cv_keys = ('mean_test_score', 'std_test_score', 'params')
for r, _ in enumerate(grid.cv_results_['mean_test_score']):
print("%0.3f +/- %0.2f %r"
% (grid.cv_results_[cv_keys[0]][r],
grid.cv_results_[cv_keys[1]][r] / 2.0,
grid.cv_results_[cv_keys[2]][r]))
print('Best parameters: %s' % grid.best_params_)
print('Accuracy: %.2f' % grid.best_score_)```

```## 如果我们打算多次使用回归算法，我们要做的就是在参数网格中添加一个附加的数字后缀，如下所示：
from sklearn.model_selection import GridSearchCV
# Initializing models
clf1 = KNeighborsClassifier(n_neighbors=1)
clf2 = RandomForestClassifier(random_state=RANDOM_SEED)
clf3 = GaussianNB()
lr = LogisticRegression()
sclf = StackingCVClassifier(classifiers=[clf1, clf1, clf2, clf3],
meta_classifier=lr,
random_state=RANDOM_SEED)
params = {'kneighborsclassifier-1__n_neighbors': [1, 5],
'kneighborsclassifier-2__n_neighbors': [1, 5],
'randomforestclassifier__n_estimators': [10, 50],
'meta_classifier__C': [0.1, 10.0]}
grid = GridSearchCV(estimator=sclf,
param_grid=params,
cv=5,
refit=True)
grid.fit(X, y)
cv_keys = ('mean_test_score', 'std_test_score', 'params')
for r, _ in enumerate(grid.cv_results_['mean_test_score']):
print("%0.3f +/- %0.2f %r"
% (grid.cv_results_[cv_keys[0]][r],
grid.cv_results_[cv_keys[1]][r] / 2.0,
grid.cv_results_[cv_keys[2]][r]))
print('Best parameters: %s' % grid.best_params_)
print('Accuracy: %.2f' % grid.best_score_)```

4.在不同特征子集上运行的分类器的堆叠：

```## 4.在不同特征子集上运行的分类器的堆叠
###不同的1级分类器可以适合训练数据集中的不同特征子集。以下示例说明了如何使用scikit-learn管道和ColumnSelector：
from mlxtend.classifier import StackingCVClassifier
from mlxtend.feature_selection import ColumnSelector
from sklearn.pipeline import make_pipeline
from sklearn.linear_model import LogisticRegression
X = iris.data
y = iris.target
pipe1 = make_pipeline(ColumnSelector(cols=(0, 2)),  # 选择第0,2列
LogisticRegression())
pipe2 = make_pipeline(ColumnSelector(cols=(1, 2, 3)),  # 选择第1,2,3列
LogisticRegression())
sclf = StackingCVClassifier(classifiers=[pipe1, pipe2],
meta_classifier=LogisticRegression(),
random_state=42)
sclf.fit(X, y)```

5.ROC曲线 decision_function：

```## 5.ROC曲线 decision_function
### 像其他scikit-learn分类器一样，它StackingCVClassifier具有decision_function可用于绘制ROC曲线的方法。
### 请注意，decision_function期望并要求元分类器实现decision_function。
from sklearn import model_selection
from sklearn.linear_model import LogisticRegression
from sklearn.neighbors import KNeighborsClassifier
from sklearn.svm import SVC
from sklearn.ensemble import RandomForestClassifier
from mlxtend.classifier import StackingCVClassifier
from sklearn.metrics import roc_curve, auc
from sklearn.model_selection import train_test_split
from sklearn import datasets
from sklearn.preprocessing import label_binarize
from sklearn.multiclass import OneVsRestClassifier
X, y = iris.data[:, [0, 1]], iris.target
# Binarize the output
y = label_binarize(y, classes=[0, 1, 2])
n_classes = y.shape[1]
RANDOM_SEED = 42
X_train, X_test, y_train, y_test = train_test_split(
X, y, test_size=0.33, random_state=RANDOM_SEED)
clf1 =  LogisticRegression()
clf2 = RandomForestClassifier(random_state=RANDOM_SEED)
clf3 = SVC(random_state=RANDOM_SEED)
lr = LogisticRegression()
sclf = StackingCVClassifier(classifiers=[clf1, clf2, clf3],
meta_classifier=lr)
# Learn to predict each class against the other
classifier = OneVsRestClassifier(sclf)
y_score = classifier.fit(X_train, y_train).decision_function(X_test)
# Compute ROC curve and ROC area for each class
fpr = dict()
tpr = dict()
roc_auc = dict()
for i in range(n_classes):
fpr[i], tpr[i], _ = roc_curve(y_test[:, i], y_score[:, i])
roc_auc[i] = auc(fpr[i], tpr[i])
# Compute micro-average ROC curve and ROC area
fpr["micro"], tpr["micro"], _ = roc_curve(y_test.ravel(), y_score.ravel())
roc_auc["micro"] = auc(fpr["micro"], tpr["micro"])
plt.figure()
lw = 2
plt.plot(fpr[2], tpr[2], color='darkorange',
lw=lw, label='ROC curve (area = %0.2f)' % roc_auc[2])
plt.plot([0, 1], [0, 1], color='navy', lw=lw, linestyle='--')
plt.xlim([0.0, 1.0])
plt.ylim([0.0, 1.05])
plt.xlabel('False Positive Rate')
plt.ylabel('True Positive Rate')