[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"$fU8uCaMfgOvu6DxBFWjCGAJeSgrV80w_3MyZ3EzfF9bw":3},{"answer":4,"createTime":5,"id":6,"options":7,"origin":11,"question":18,"related":19,"source":29,"type":30},[],"2024-12-02 08:34:42",168485785,[8,9,10],"距离度量","k值的选择","样本大小",{"count":12,"courseId":13,"courseImg":14,"courseName":15,"workId":16,"workName":17},18,"0a76159e9adfd1f863e37feb673af407","https:\u002F\u002Ftihai-oss-cloud.itihey.com\u002Fimg\u002Fa209d87b62a2bf5b570cd42a9ef82155.jpg","机器学习（2024年）","work_39373865","","k-近邻算法的基本要素不包括",[20,31,40,49,58,67,70,79,87,92],{"answer":21,"createTime":5,"id":22,"options":23,"question":28,"source":29,"type":30},[],168485780,[24,25,26,27],"拆分数据、并对数据做归一化处理","加载数据","选择不同的算法","训练模型并评价模型","在分类实验中,按照正常的顺序对以下的项目执行流程进行排序","v1",1,{"answer":32,"createTime":5,"id":33,"options":34,"question":39,"source":29,"type":30},[],168485781,[35,36,37,38],"红蓝红蓝红","红红蓝蓝蓝","红红红蓝蓝","蓝蓝红红红","\u003Cimg src=\"https:\u002F\u002Ftihai-oss-cloud.itihey.com\u002Fimg\u002F7a8182e1fdc7a62a6c35976ed5114237.png\"> 在上图中,绿色圆点为待定点,若执行KNN算法,请问当K分别为1,2,3,4,5时,绿色圆点分别属于那个类别",{"answer":41,"createTime":5,"id":42,"options":43,"question":48,"source":29,"type":30},[],168485782,[44,45,46,47],"不知道","利用 _square_distance求距离","计算待求的X的每一个样本与原始数据集中每一个样本的距离","计算原始数据集中每一个样本之间的距离","这是一个标准的KNN算法实现 Plain Text# -*- coding: utf-8 -*-import numpy as npimport operatorclass KNN(object): def __init__(self, k=3): self.k = k def fit(self, x, y): self.x = x self.y = y def _square_distance(self, v1, v2): return np.sum(np.square(v1-v2)) def _vote(self, ys): ys_unique = np.unique(ys) vote_dict = {} for y in ys: if y not in vote_dict.keys(): vote_dict[y] = 1 else: vote_dict[y] += 1 sorted_vote_dict = sorted(vote_dict.items(), key=operator.itemgetter(1), reverse=True) return sorted_vote_dict[0][0] def predict(self, x): y_pred = [] for i in range(len(x)): dist_arr = [self._square_distance(x[i], self.x[j]) for j in range(len(self.x))] sorted_index = np.argsort(dist_arr) top_k_index = sorted_index[:self.k] y_pred.append(self._vote(ys=self.y[top_k_index])) return np.array(y_pred) def score(self, y_true=None, y_pred=None): if y_true is None and y_pred is None: y_pred = self.predict(self.x) y_true = self.y score = 0.0 for i in range(len(y_true)): if y_true[i] == y_pred[i]: score += 1 score \u002F= len(y_true) return score 请问以上算法中: Plain Text for i in range(len(x)): dist_arr = [self._square_distance(x[i], self.x[j]) for j in range(len(self.x))] 这两条语句的作用是什么? Plain TextPlain Text",{"answer":50,"createTime":5,"id":51,"options":52,"question":57,"source":29,"type":30},[],168485783,[53,54,55,56],"熵","基尼系数","信息增益","以上都是","在构建决策树时,需要计算每个用来划分数据特征的得分,选择分数最高的特征,以下可以作为得分的是",{"answer":59,"createTime":5,"id":60,"options":61,"question":66,"source":29,"type":30},[],168485784,[62,63,64,65],"k-近邻算法是机器学习","k代表分类个数","k的选择对分类结果没有影响","距离计算方法不同,效果也可能有显著差别","关于k-近邻算法说法错误的是",{"answer":68,"createTime":5,"id":6,"options":69,"question":18,"source":29,"type":30},[],[8,9,10],{"answer":71,"createTime":5,"id":72,"options":73,"question":78,"source":29,"type":30},[],168485786,[74,75,76,77],"回归问题","分类问题","推理问题","聚类问题","Logistics模型解决",{"answer":80,"createTime":5,"id":81,"options":82,"question":86,"source":29,"type":30},[],168485787,[55,83,84,85],"信息增益比","基尼不纯度","卡方检验","在决策树算法中,ID3算法使用什么指标来选择最优特征",{"answer":88,"createTime":5,"id":89,"options":90,"question":91,"source":29,"type":30},[],168485788,[55,83,84,85],"C4.5算法使用什么指标来选择最优特征",{"answer":93,"createTime":5,"id":94,"options":95,"question":100,"source":29,"type":30},[],168485789,[96,97,98,99],"垃圾邮件过滤","新冠疫情什么时候结束","这个学期是否还会返校","剪刀饰头游戏中猜测对方的出什么","在现实生活中,以下属于分类问题的有"]