DataWhale集成学习（下）——Task13 Stacking集成学习算法

集成学习中的最后一个成员——stacking
stacking是一种精美而又复杂的，对模型集成的一种策略
可以理解为一个两层的集成：

1. 第一层含有多个基础分类器，把预测的结果（元特征）提供给第二层；
2. 第二层通常为逻辑回归，把第一层的结果当做特征做拟合，输出预测结果。

Stacking集成学习算法

Blending中，通过分割产生验证集，用交叉验证可以得到多组验证集

案例

1. 简单堆叠3折CV分类

# 
from sklearn import datasets

iris = datasets.load_iris()
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))

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

# 
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)

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_)

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 sklearn.datasets import load_iris
from mlxtend.classifier import StackingCVClassifier
from mlxtend.feature_selection import ColumnSelector
from sklearn.pipeline import make_pipeline
from sklearn.linear_model import LogisticRegression

iris = load_iris()
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)

Blending VS Stacking：

• 优点：简单
• 缺点：只使用了很少的数据；可能导致过拟合；stacking使用多次CV会比较稳健。

参考资料：
1.DataWhale开源资料