task7

from sklearn.linear_model 
import LogisticRegression 
from sklearn.svm import SVC 
from sklearn.ensemble import VotingClassifier
from sklearn.pipeline import make_pipeline 
from sklearn.preprocessing import StandardScaler

models = [('lr',LogisticRegression()),('svm',SVC())] 
ensemble = VotingClassifier(estimators=models)

#有时某些模型需要一些预处理操作，我们可以为他们定义Pipeline完成模型预处理工作：
models = [('lr',LogisticRegression()), ('svm',make_pipeline(StandardScaler(),SVC()))] 
ensemble = VotingClassifier(estimators=models)

#模型还提供了voting参数让我们选择软投票或者硬投票：
models = [('lr',LogisticRegression()),('svm',SVC())] 
ensemble = VotingClassifier(estimators=models, voting='soft')

下面我们使用一个完整的例子演示投票法的使用：
首先我们创建一个1000个样本，20个特征的随机数据集：

# test classification dataset
from sklearn.datasets import make_classification
# define dataset
def get_dataset():
    X, y = make_classification(n_samples=1000, n_features=20, n_informative=15, n_redundant=5, random_state=2)
    # summarize the dataset
    return X,y

我们使用多个KNN模型作为基模型演示投票法，其中每个模型采用不同的邻居值K参数：

# get a voting ensemble of models
def get_voting():
    # define the base models
    models = list()
    models.append(('knn1', KNeighborsClassifier(n_neighbors=1)))
    models.append(('knn3', KNeighborsClassifier(n_neighbors=3)))
    models.append(('knn5', KNeighborsClassifier(n_neighbors=5)))
    models.append(('knn7', KNeighborsClassifier(n_neighbors=7)))
    models.append(('knn9', KNeighborsClassifier(n_neighbors=9)))
    # define the voting ensemble
    ensemble = VotingClassifier(estimators=models, voting='hard')
    return ensemble

然后，我们可以创建一个模型列表来评估投票带来的提升，包括KNN模型配置的每个独立版本和硬投票模型。下面的get_models()函数可以为我们创建模型列表进行评估。

# get a list of models to evaluate
def get_models():
    models = dict()
    models['knn1'] = KNeighborsClassifier(n_neighbors=1)
    models['knn3'] = KNeighborsClassifier(n_neighbors=3)
    models['knn5'] = KNeighborsClassifier(n_neighbors=5)
    models['knn7'] = KNeighborsClassifier(n_neighbors=7)
    models['knn9'] = KNeighborsClassifier(n_neighbors=9)
    models['hard_voting'] = get_voting()
    return models

下面的evaluate_model()函数接收一个模型实例，并以分层10倍交叉验证三次重复的分数列表的形式返回。

# evaluate a give model using cross-validation
from sklearn.model_selection import cross_val_score   #Added by ljq
def evaluate_model(model, X, y):
    cv = RepeatedStratifiedKFold(n_splits=10, n_repeats=3, random_state=1)
    scores = cross_val_score(model, X, y, scoring='accuracy', cv=cv, n_jobs=-1, error_score='raise')
    return scores

然后，我们可以报告每个算法的平均性能，还可以创建一个箱形图和须状图来比较每个算法的精度分数分布。

from sklearn.neighbors import KNeighborsClassifier
from matplotlib import pyplot

# define dataset
X, y = get_dataset()
# get the models to evaluate
models = get_models()
# evaluate the models and store results
results, names = list(), list()
for name, model in models.items():
    scores = evaluate_model(model, X, y)
    results.append(scores)
    names.append(name)
    print('>%s %.3f (%.3f)' % (name, mean(scores), std(scores)))
# plot model performance for comparison
pyplot.boxplot(results, labels=names, showmeans=True)
pyplot.show()