本文共 2786 字，大约阅读时间需要 9 分钟。

投票法简介

基本实现

Sklearn提供了 VotingRegressor 与 VotingClassifier两个投票方法，两个模型的操作方式相同，采用相同参数，列表中每个模型采用Tuple的结构表示，第

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

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

通过voting参数选择软投票或硬投票

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

使用案例

定义分类数据集

# 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

使用KNN模型作为基模型演示投票法，每个模型采用不同的邻居值K参数

# get a voting ensemble of modelsdef 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

创建一个get_models()为创建模型列表进行评

# get a list of models to evaluatedef 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

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-validationdef 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

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。

# define datasetX, y = get_dataset()# get the models to evaluatemodels = get_models()# evaluate the models and store resultsresults, 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 comparisonpyplot.boxplot(results, labels=names, showmeans=True)pyplot.show()

>knn1 0.873 (0.030)>knn3 0.889 (0.038)>knn5 0.895 (0.031)>knn7 0.899 (0.035)>knn9 0.900 (0.033)>hard_voting 0.902 (0.034)

转载地址：http://qagwi.baihongyu.com/