【2021.05--集成学习（下）-Task13】Stacking简单实践

本次 DataWhale 第二十五期组队学习，其开源内容的链接为：https://github.com/datawhalechina/team-learning-data-mining/tree/master/EnsembleLearning

上一次的任务中简单实践了blending，这一次任务将学习集成学习的最后一部分——stacking。具体原理可参见链接：https://www.cnblogs.com/Christina-Notebook/p/10063146.html

# 载入数据
from sklearn import datasets
iris = datasets.load_iris()
X, y = iris.data[:, 1:3], iris.target
X.shape, y.shape

((150, 2), (150,))

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()

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', 'NaiveBayes','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-fold cross validation:

Accuracy: 0.91 (+/- 0.01) [KNN]
Accuracy: 0.95 (+/- 0.01) [Random Forest]
Accuracy: 0.91 (+/- 0.02) [NaiveBayes]
Accuracy: 0.93 (+/- 0.02) [StackingClassifier]

# 我们画出决策边界
from mlxtend.plotting import plot_decision_regions
import matplotlib.gridspec as gridspec
import itertools
import matplotlib.pyplot as plt
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]]) # 这句应该是选取子图的
    fig = plot_decision_regions(X=X, y=y, clf=clf) # 这个函数真简便，上一个任务都不知道。
    plt.title(lab)
plt.show()

使用第一层所有基分类器所产生的类别概率值作为meta-classfier的输入。需要在StackingClassifier 中增加一个参数设置：use_probas = True。

另外，还有一个参数设置average_probas = True,那么这些基分类器所产出的概率值将按照列被平均，否则会拼接。

例如：

基分类器1：predictions=[0.2,0.2,0.7]

基分类器2：predictions=[0.4,0.3,0.8]

基分类器3：predictions=[0.1,0.4,0.6]

1）若use_probas = True，average_probas = True，

则产生的meta-feature 为：[0.233, 0.3, 0.7]

2）若use_probas = True，average_probas = False，

则产生的meta-feature 为：[0.2,0.2,0.7,0.4,0.3,0.8,0.1,0.4,0.6]

# 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-fold cross validation:

Accuracy: 0.91 (+/- 0.01) [KNN]
Accuracy: 0.95 (+/- 0.01) [Random Forest]
Accuracy: 0.91 (+/- 0.02) [Naive Bayes]
Accuracy: 0.95 (+/- 0.02) [StackingClassifier]

# 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_)

0.947 +/- 0.03 {'kneighborsclassifier__n_neighbors': 1, 'meta_classifier__C': 0.1, 'randomforestclassifier__n_estimators': 10}
0.933 +/- 0.02 {'kneighborsclassifier__n_neighbors': 1, 'meta_classifier__C': 0.1, 'randomforestclassifier__n_estimators': 50}
0.940 +/- 0.02 {'kneighborsclassifier__n_neighbors': 1, 'meta_classifier__C': 10.0, 'randomforestclassifier__n_estimators': 10}
0.940 +/- 0.02 {'kneighborsclassifier__n_neighbors': 1, 'meta_classifier__C': 10.0, 'randomforestclassifier__n_estimators': 50}
0.953 +/- 0.02 {'kneighborsclassifier__n_neighbors': 5, 'meta_classifier__C': 0.1, 'randomforestclassifier__n_estimators': 10}
0.953 +/- 0.02 {'kneighborsclassifier__n_neighbors': 5, 'meta_classifier__C': 0.1, 'randomforestclassifier__n_estimators': 50}
0.953 +/- 0.02 {'kneighborsclassifier__n_neighbors': 5, 'meta_classifier__C': 10.0, 'randomforestclassifier__n_estimators': 10}
0.953 +/- 0.02 {'kneighborsclassifier__n_neighbors': 5, 'meta_classifier__C': 10.0, 'randomforestclassifier__n_estimators': 50}
Best parameters: {'kneighborsclassifier__n_neighbors': 5, 'meta_classifier__C': 0.1, 'randomforestclassifier__n_estimators': 10}
Accuracy: 0.95

## 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_)

0.940 +/- 0.02 {'kneighborsclassifier-1__n_neighbors': 1, 'kneighborsclassifier-2__n_neighbors': 1, 'meta_classifier__C': 0.1, 'randomforestclassifier__n_estimators': 10}
0.940 +/- 0.02 {'kneighborsclassifier-1__n_neighbors': 1, 'kneighborsclassifier-2__n_neighbors': 1, 'meta_classifier__C': 0.1, 'randomforestclassifier__n_estimators': 50}
0.940 +/- 0.02 {'kneighborsclassifier-1__n_neighbors': 1, 'kneighborsclassifier-2__n_neighbors': 1, 'meta_classifier__C': 10.0, 'randomforestclassifier__n_estimators': 10}
0.940 +/- 0.02 {'kneighborsclassifier-1__n_neighbors': 1, 'kneighborsclassifier-2__n_neighbors': 1, 'meta_classifier__C': 10.0, 'randomforestclassifier__n_estimators': 50}
0.960 +/- 0.02 {'kneighborsclassifier-1__n_neighbors': 1, 'kneighborsclassifier-2__n_neighbors': 5, 'meta_classifier__C': 0.1, 'randomforestclassifier__n_estimators': 10}
0.953 +/- 0.02 {'kneighborsclassifier-1__n_neighbors': 1, 'kneighborsclassifier-2__n_neighbors': 5, 'meta_classifier__C': 0.1, 'randomforestclassifier__n_estimators': 50}
0.953 +/- 0.02 {'kneighborsclassifier-1__n_neighbors': 1, 'kneighborsclassifier-2__n_neighbors': 5, 'meta_classifier__C': 10.0, 'randomforestclassifier__n_estimators': 10}
0.953 +/- 0.02 {'kneighborsclassifier-1__n_neighbors': 1, 'kneighborsclassifier-2__n_neighbors': 5, 'meta_classifier__C': 10.0, 'randomforestclassifier__n_estimators': 50}
0.960 +/- 0.02 {'kneighborsclassifier-1__n_neighbors': 5, 'kneighborsclassifier-2__n_neighbors': 1, 'meta_classifier__C': 0.1, 'randomforestclassifier__n_estimators': 10}
0.953 +/- 0.02 {'kneighborsclassifier-1__n_neighbors': 5, 'kneighborsclassifier-2__n_neighbors': 1, 'meta_classifier__C': 0.1, 'randomforestclassifier__n_estimators': 50}
0.953 +/- 0.02 {'kneighborsclassifier-1__n_neighbors': 5, 'kneighborsclassifier-2__n_neighbors': 1, 'meta_classifier__C': 10.0, 'randomforestclassifier__n_estimators': 10}
0.953 +/- 0.02 {'kneighborsclassifier-1__n_neighbors': 5, 'kneighborsclassifier-2__n_neighbors': 1, 'meta_classifier__C': 10.0, 'randomforestclassifier__n_estimators': 50}
0.953 +/- 0.02 {'kneighborsclassifier-1__n_neighbors': 5, 'kneighborsclassifier-2__n_neighbors': 5, 'meta_classifier__C': 0.1, 'randomforestclassifier__n_estimators': 10}
0.953 +/- 0.02 {'kneighborsclassifier-1__n_neighbors': 5, 'kneighborsclassifier-2__n_neighbors': 5, 'meta_classifier__C': 0.1, 'randomforestclassifier__n_estimators': 50}
0.953 +/- 0.02 {'kneighborsclassifier-1__n_neighbors': 5, 'kneighborsclassifier-2__n_neighbors': 5, 'meta_classifier__C': 10.0, 'randomforestclassifier__n_estimators': 10}
0.953 +/- 0.02 {'kneighborsclassifier-1__n_neighbors': 5, 'kneighborsclassifier-2__n_neighbors': 5, 'meta_classifier__C': 10.0, 'randomforestclassifier__n_estimators': 50}
Best parameters: {'kneighborsclassifier-1__n_neighbors': 1, 'kneighborsclassifier-2__n_neighbors': 5, 'meta_classifier__C': 0.1, 'randomforestclassifier__n_estimators': 10}
Accuracy: 0.96

## 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)

StackingCVClassifier(classifiers=[Pipeline(steps=[('columnselector',
                                                   ColumnSelector(cols=(0, 2))),
                                                  ('logisticregression',
                                                   LogisticRegression())]),
                                  Pipeline(steps=[('columnselector',
                                                   ColumnSelector(cols=(1, 2,
                                                                        3))),
                                                  ('logisticregression',
                                                   LogisticRegression())])],
                     meta_classifier=LogisticRegression(), random_state=42)

### 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

iris = datasets.load_iris()
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')
plt.title('Receiver operating characteristic example')
plt.legend(loc="lower right")
plt.show()

这一次学习内容以复现为主，之前用stacking都很稀里糊涂的，经过这次学习，对多个同类分类器以及stacking中的管道才做有了认识。