基于sklearn实现Bagging算法（python）

from sklearn.ensemble import BaggingClassifierfrom sklearn.tree import DecisionTreeClassifierfrom sklearn.preprocessing import StandardScalerimport csvfrom sklearn.cross_validation import train_test_splitfrom sklearn.metrics import accuracy_scorefrom sklearn.metrics import confusion_matrixfrom sklearn.metrics import classification_reportdata=[]traffic_feature=[]traffic_target=[]csv_file = csv.reader(open('packSize_all.csv'))for content in csv_file: content=list(map(float,content)) if len(content)!=0:  data.append(content)  traffic_feature.append(content[0:6])//存放数据集的特征  traffic_target.append(content[-1])//存放数据集的标签print('data=',data)print('traffic_feature=',traffic_feature)print('traffic_target=',traffic_target)scaler = StandardScaler() # 标准化转换scaler.fit(traffic_feature) # 训练标准化对象traffic_feature= scaler.transform(traffic_feature) # 转换数据集feature_train, feature_test, target_train, target_test = train_test_split(traffic_feature, traffic_target, test_size=0.3,random_state=0)tree=DecisionTreeClassifier(criterion='entropy', max_depth=None)# n_estimators=500:生成500个决策树clf = 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)clf.fit(feature_train,target_train)predict_results=clf.predict(feature_test)print(accuracy_score(predict_results, target_test))conf_mat = confusion_matrix(target_test, predict_results)print(conf_mat)print(classification_report(target_test, predict_results))