k-临近 - - - 一个简单的封装类

import numpy as np

# k-临近，K-Nearest Neighbor，也称knn

# 原理：有n个样本的数据集，现给定一个新的样本s，s与n个样本进行比较，选取k个与s相近的样本，查看k个样本属于哪个类型，
#      个数最多的那个类型为s的类型

'''  knn封装类  '''
class KNN(object):
    def __init__(self, k_value, s_data, s_label,  t_data):
        self.k_value = k_value  # 设置的前k个样本的值
        self.s_data = s_data
        self.s_label = s_label
        self.t_data= t_data

    def calculate_distance(self, one, two, cal_type):

        result = 0.0
        if cal_type == 'ED':        # 欧式距离(Euclidean Distance)
            result = np.linalg.norm(one - two)
        elif cal_type == 'MD':      # 曼哈顿距离(Manhattan Distance)
            result = np.sum(np.abs(one - two))
        elif cal_type == 'CD':      # 切比雪夫距离(Chebyshev Distance)
            result = np.max(np.abs(one - two))
        elif cal_type == 'MKD':     # 闵可夫斯基距离(MinkowskiDistance)
            result = np.sqrt(np.sum(np.square(one - two)))
        elif cal_type == 'SED':        # 标准化欧氏距离(Standardized Euclidean distance)
            X = np.vstack([one, two])
            sk = np.var(X, axis=0, ddof=1)
            result = np.sqrt(((one - two) ** 2 /sk).sum())

        return result

    def calculate_value(self, cal_type):

        result_ed1 = list([])
        for s_one in self.s_data:
            dist = self.calculate_distance(self.t_data, s_one, cal_type)
            result_ed1.append(dist)
        result_ed1 = np.array(result_ed1)
        # print('result_ed1=', result_ed1)
        result_ed2 = 1 / (1 + result_ed1)
        # print('result_ed2:', result_ed2)
        result_ed3 = np.argsort(result_ed2, axis=0)  # 得到正序索引值
        result_ed3 = result_ed3[::-1]  # 得到倒序索引值
        # 注：这里做了1 / (1 + result_ed1) 的处理，距离越近这个值越大
        index1 = result_ed3[0: self.k_value]
        result_label = self.s_label[index1]  # 得到距离最近的前k个类别数据
        # print('result_label=', result_label)
        keep = np.unique(result_label, return_counts=True, return_inverse=True)  # 去重
        k_arr1 = keep[0]  # 去重后的数据
        k_arr3 = keep[2]  # 去重后的数据，每个元素出现的次数
        max_value = np.max(k_arr3)
        index2 = np.where(k_arr3 == max_value)
        index2 = index2[0]
        result = k_arr1[index2]
        print('result=', result)

        return result

'''  使用例子     '''
# 创建数据集
def create_data_set():
    group = np.array([[1.0, 1.1], [1.0, 1.0], [0, 0], [0, 1.1]])
    labels = np.array(["A", "A", "B", "B"])
    return group, labels

# 使用KNN分类
def classify():

    group, labels = create_data_set()
    t_data = np.array([0.1, 0.2])
    k_value = 2

    # knn的类初始化
    knn = KNN(k_value, group, labels, t_data)
    knn.calculate_value('ED')

    return

classify()