摘要

本文通过python实现了集成学习中的Bagging和AdaBOOST算法，并将代码进行了封装，方便读者调用。

Bagging算法

import numpy as np import pandas as pd class Cyrus_bagging(object):     def __init__(self,estimator,n_estimators = 20):         self.estimator = estimator         self.n_estimators = n_estimators         self.models = None     def fit(self,x,y):         x = np.array(x)         y = np.array(y).reshape((-1,))         indices = np.arange(x.shape[0])         self.models = [] for i in range(self.n_estimators):             index = np.random.choice(indices,x.shape[0])             x0 = x[index]             y0 = y[index]             self.models.append(self.estimator.fit(x0,y0))     def predict(self,x):         res = np.zeros([x.shape[0],self.n_estimators]) for i in range(self.n_estimators):             res[:,i] = self.models[i].predict(x)         result = [] for i in range(res.shape[0]):             pd_res = pd.Series(res[i,:]).value_counts()             result.append(int(pd_res.argmax())) return np.array(result) 

from sklearn.neighbors import KNeighborsClassifier from sklearn.metrics import classification_report knn = KNeighborsClassifier() model = Cyrus_bagging(knn) model.fit(x_train,y_train) y_pre = model.predict(x_test) print(classification_report(y_test,y_pre)) 

示例使用的数据为了与不使用集成算法的模型的准确率区分开来，所以使用较少特征的数据，因而准确率不是特别高，不过与未使用集成算法的模型相比，准确率已经优出不少。

precision    recall  f1-score   support            0       1.00      1.00      1.00        11           1       0.67      0.67      0.67         9           2       0.70      0.70      0.70        10  avg / total       0.80      0.80      0.80        30 

Adaboost算法

import numpy as np import pandas as pd from sklearn.metrics import accuracy_score class CyrusAdaBoost(object):     def __init__(self,estimator,n_estimators = 20):         self.estimator = estimator         self.n_estimators = n_estimators         self.error_rate = None         self.model = None     def update_w(self,y,pre_y,w):         error_rate = 1 - accuracy_score(y,pre_y) for i in range(w.shape[0]): if y[i] == pre_y[i]:                 w[i] = w[i]*np.exp(-error_rate) else:                 w[i] = w[i]*np.exp(error_rate) return w/w.sum()     def cal_label(self,result,alpha):         label = [] for i in range(result.shape[0]):             count = np.zeros(int(result[i,:].max()+1)) for j in range(result.shape[1]):                 count[int(result[i,j])] += alpha[j]             label.append(count.argmax()) return np.array(label)     def fit(self,x,y):         x = np.array(x)         y = np.array(y).reshape((-1,))         self.error_rate = []         self.model = []         w0 = np.ones(x.shape[0])         w0 = w0/w0.sum()         indices = np.arange(x.shape[0]) for i in range(self.n_estimators):             index = np.random.choice(indices,size = x.shape[0],p = w0)             x0 = x[index]             y0 = y[index]             model0 = self.estimator.fit(x0,y0)             pre_y0 = model0.predict(x0)             error_rate = 1 - accuracy_score(y0,pre_y0)             self.error_rate.append(error_rate)             self.model.append(model0)             w0 = self.update_w(y0,pre_y0,w0)     def predict(self,x):         res = np.zeros([x.shape[0],self.n_estimators]) for i in range(self.n_estimators):             res[:,i] = self.model[i].predict(x)         alpha = 1 - np.array(self.error_rate) return self.cal_label(res,alpha) 

from sklearn.tree import DecisionTreeClassifier model = CyrusAdaBoost(estimator=DecisionTreeClassifier(),n_estimators=50) model.fit(x_train,y_train) y_pre = model.predict(x_test) print(accuracy_score(y_pre,y_test)) 

0.932 

by CyrusMay 2020 06 12

这世界全部的漂亮
不过你的可爱模样
——————五月天（爱情的模样）——————