KNN最近邻近节点算法

import numpy as np
from math import sqrt
from collections import Counter


class KNNClassifier:

  def __init__(self, k):
    '''初始化KNN分类器'''
    assert k >= 1, "k must be valid"
    self.k = k
    self._X_train = None
    self._y_train = None

  def fit(self, X_train, y_train):
    '''根据训练数据集X_train和 y_trian训练knn分类器'''
    assert X_train.shape[0] == y_train.shape[0], 'the size of X_train must be equal to the size of y_train'
    assert self.k <= X_train.shape[0], 'the size of X_train must be at least k'

    self._X_train = X_train
    self._y_train = y_train
    return self

  def predict(self, X_predict):
    '''给定待预测数据集X_predict，返回表示X_predict的结果向量'''
    assert self._X_train is not None and self._y_train is not None, 'must fit before predict'
    assert X_predict.shape[1] == self._X_train.shape[1], 'the feature number of X_predict must be equal to X_train'
    
    y_predict = [self._predict(x) for x in X_predict]
    return np.array(y_predict)
  
  #  计算k个点离预测点中的距离
  def _predict(self, x):
    '''给定单个待预测数据x，返回x_predict的预测结果值'''
    assert x.shape[0] == self._X_train.shape[1], 'the feature number of x must be equal to X_train'
    
    # 通过欧式距离计算
    distances = [sqrt(np.sum((x_train - x) ** 2) for x_train in self._X_train)]
    
    # 对距离点按照索引排序
    nearset = np.argsort(distances)
    
    # 计算临近点的标签
    topK_y = [self._y_train[i] for i in nearset[:self.k]]
    
    # 计算标签数组中的每个标签次数
    votes = Counter(topK_y)
    # 返回最大标签数值
    return votes.most_common(1)[0][0]

  def __repr__(self):
    return 'KNN(K=%d)' % self.k

#先创建实例化对象
knn_clf = KNNClassifier(k=3)
#训练模型
knn_clf.fit(X_train,y_train)
# 预测向量
predict_y = knn_clf.predict(x)