第1关：什么是集成学习

任务描述

本关任务：根据本节课所学知识完成本关所设置的选择题。

第2关： Boosting

任务描述

本关任务：根据本节课所学知识完成本关所设置的选择题。

第3关：Adaboost算法流程

任务描述

本关任务：用Python实现Adaboost，并通过鸢尾花数据集中鸢尾花的2种属性与种类对Adaboost模型进行训练。我们会调用你训练好的Adaboost模型，来对未知的鸢尾花进行分类。

#encoding=utf8
 
import numpy as np
 
#adaboost算法
class AdaBoost:
    '''
    input:n_estimators(int):迭代轮数
          learning_rate(float):弱分类器权重缩减系数
    '''
    def __init__(self, n_estimators=50, learning_rate=1.0):
        self.clf_num = n_estimators
        self.learning_rate = learning_rate
    
    def init_args(self, datasets, labels):
        
        self.X = datasets
        self.Y = labels
        self.M, self.N = datasets.shape
        
        # 弱分类器数目和集合
        self.clf_sets = []
        
        # 初始化weights
        self.weights = [1.0/self.M]*self.M
        
        # G(x)系数 alpha
        self.alpha = []    
    def _G(self, features, labels, weights):
        '''
        input:features(ndarray):数据特征
              labels(ndarray):数据标签
              weights(ndarray):样本权重系数
        '''
        #********* Begin *********#
        m = len(features)
        error = 100000.0 # 无穷大
        beat_v = 0.0
        #单维features
        features_min = min(features)
        features_max = max(features)
        n_step = (features_max-features_min+self.learning_rate) // self.learning_rate
        direct,compare_array = None,None
        for i in range(1,int(n_step)):
            v = features_min + self.learning_rate * i
 
            if v not in features:
                # 误分类计算
                compare_array_positive = np.array(
                    [1 if features[k] > v else -1 for k in range(m)])
                weight_error_positive = sum([
                    weights[k] for k in range(m)
                    if compare_array_positive[k] != labels[k]
                ])
 
                compare_array_nagetive = np.array(
                    [-1 if features[k] > v else 1 for k in range(m)])
                weight_error_nagetive = sum([
                    weights[k] for k in range(m)
                    if compare_array_nagetive[k] != labels[k]
                ])
 
                if weight_error_positive < weight_error_nagetive:
                    weight_error = weight_error_positive
                    _compare_array = compare_array_positive
                    direct = 'positive'
                else:
                    weight_error = weight_error_nagetive
                    _compare_array = compare_array_nagetive
                    direct = 'nagetive'
 
                # print('v:{} error:{}'.format(v, weight_error))
                if weight_error < error:
                    error = weight_error
                    compare_array = _compare_array
                    best_v = v
        return best_v, direct, error, compare_array
    # 计算alpha
    def _alpha(self, error):
        return 0.5 * np.log((1 - error) / error)
 
    # 规范化因子
    def _Z(self, weights, a, clf):
        return sum([
            weights[i] * np.exp(-1 * a * self.Y[i] * clf[i])
            for i in range(self.M)
        ])
 
    # 权值更新
    def _w(self, a, clf, Z):
        for i in range(self.M):
            self.weights[i] = self.weights[i] * np.exp(
                -1 * a * self.Y[i] * clf[i]) / Z
 
    # G(x)的线性组合
    def _f(self, alpha, clf_sets):
        pass
 
    def G(self, x, v, direct):
        if direct == 'positive':
            return 1 if x > v else -1
        else:
            return -1 if x > v else 1
 
    def fit(self, X, y):
        self.init_args(X, y)
 
        for epoch in range(self.clf_num):
            axis = 0
            final_direct = 'null'
            best_clf_error, best_v, clf_result = 100000, None, None
            # 根据特征维度, 选择误差最小的
            for j in range(self.N):
                features = self.X[:, j]
                # 分类阈值，分类误差，分类结果
                v, direct, error, compare_array = self._G(
                    features, self.Y, self.weights)
 
                if error < best_clf_error:
                    best_clf_error = error
                    best_v = v
                    final_direct = direct
                    clf_result = compare_array
                    axis = j  # axis数字代表第几个属性列
 
                # print('epoch:{}/{} feature:{} error:{} v:{}'.format(epoch, self.clf_num, j, error, best_v))
                if best_clf_error == 0:
                    break
 
            # 计算G(x)系数a
            a = self._alpha(best_clf_error)
            self.alpha.append(a)
            # 记录分类器
            self.clf_sets.append((axis, best_v, final_direct))
            # 规范化因子
            Z = self._Z(self.weights, a, clf_result)
            # 权值更新
            self._w(a, clf_result, Z)
                
 
        #********* End *********#            
    def predict(self, feature):
        result = 0.0
        for i in range(len(self.clf_sets)):
            axis, clf_v, direct = self.clf_sets[i]
            f_input = feature[axis]
            result += self.alpha[i] * self.G(f_input, clf_v, direct)
        # sign
        return 1 if result > 0 else -1
    
    def score(self, X_test, y_test):
        right_count = 0
        for i in range(len(X_test)):
            feature = X_test[i]
            if self.predict(feature) == y_test[i]:
                right_count += 1
        
        return right_count / len(X_test)
 

第4关：sklearn中的Adaboost

任务描述

本关任务：你需要调用sklearn中的Adaboost模型，并通过鸢尾花数据集中鸢尾花的2种属性与种类对Adaboost模型进行训练。我们会调用你训练好的Adaboost模型，来对未知的鸢尾花进行分类。

#encoding=utf8
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import AdaBoostClassifier
 
def ada_classifier(train_data,train_label,test_data):
    '''
    input:train_data(ndarray):训练数据
          train_label(ndarray):训练标签
          test_data(ndarray):测试标签
    output:predict(ndarray):预测结果
    '''
    #********* Begin *********#
    ada=AdaBoostClassifier(base_estimator=DecisionTreeClassifier
         (max_depth=2,min_samples_split=10,min_samples_leaf=5),
         n_estimators=50,learning_rate=0.2)
    ada.fit(train_data,train_label)
    predict=ada.predict(test_data)
 
    
 
    #********* End *********# 
    return predict