机器学习 --- AGNES

第1关：距离的计算

import numpy as np


def calc_min_dist(cluster1, cluster2):
    '''
    计算簇间最小距离
    :param cluster1:簇1中的样本数据，类型为ndarray
    :param cluster2:簇2中的样本数据，类型为ndarray
    :return:簇1与簇2之间的最小距离
    '''

    #********* Begin *********#
    min_dist = np.inf
    for i in range(len(cluster1)):
        for j in range(len(cluster2)):
            dist = np.sqrt(np.sum(np.square(cluster1[i] - cluster2[j])))
            if dist < min_dist:
                min_dist = dist
    return min_dist
    #********* End *********#


def calc_max_dist(cluster1, cluster2):
    '''
    计算簇间最大距离
    :param cluster1:簇1中的样本数据，类型为ndarray
    :param cluster2:簇2中的样本数据，类型为ndarray
    :return:簇1与簇2之间的最大距离
    '''

    #********* Begin *********#
    dist_max = 0
    for i in range(len(cluster1)):
        for j in range(len(cluster2)):
            dist = np.sqrt(np.sum(np.square(cluster1[i] - cluster2[j])))
            if dist > dist_max:
                dist_max = dist
    return dist_max
    #********* End *********#


def calc_avg_dist(cluster1, cluster2):
    '''
    计算簇间平均距离
    :param cluster1:簇1中的样本数据，类型为ndarray
    :param cluster2:簇2中的样本数据，类型为ndarray
    :return:簇1与簇2之间的平均距离
    '''

    #********* Begin *********#
    # 计算两个簇中所有样本点之间的距离
    dist = np.zeros((len(cluster1), len(cluster2)))
    for i in range(len(cluster1)):
        for j in range(len(cluster2)):
            dist[i][j] = np.sqrt(np.sum(np.square(cluster1[i] - cluster2[j])))

    # 计算平均距离
    avg_dist = np.mean(dist)

    return avg_dist
    #********* End *********#

第2关：AGNES算法流程

import numpy as np
def AGNES(feature, k):
    '''
    AGNES聚类并返回聚类结果
    假设数据集为`[1, 2], [10, 11], [1, 3]]，那么聚类结果可能为`[[1, 2], [1, 3]], [[10, 11]]]
    :param feature:训练数据集所有特征组成的ndarray
    :param k:表示想要将数据聚成`k`类，类型为`int`
    :return:聚类结果
    '''
    #********* Begin *********#
    # 找到距离最小的下标
    def find_Min(M):
        min = np.inf
        x = 0;
        y = 0
        for i in range(len(M)):
            for j in range(len(M[i])):
                if i != j and M[i][j] < min:
                    min = M[i][j];
                    x = i;
                    y = j
        return (x, y, min)
    #计算簇间最大距离
    def calc_max_dist(cluster1, cluster2):
        max_dist = 0
        for i in range(len(cluster1)):
            for j in range(len(cluster2)):
                dist = np.sqrt(np.sum(np.square(cluster1[i] - cluster2[j])))
                if dist > max_dist:
                    max_dist = dist
        return max_dist
    #初始化C和M
    C = []
    M = []
    for i in feature:
        Ci = []
        Ci.append(i)
        C.append(Ci)
    for i in C:
        Mi = []
        for j in C:
            Mi.append(calc_max_dist(i, j))
        M.append(Mi)
    q = len(feature)
    #合并更新
    while q > k:
        x, y, min = find_Min(M)
        C[x].extend(C[y])
        C.pop(y)
        M = []
        for i in C:
            Mi = []
            for j in C:
                Mi.append(calc_max_dist(i, j))
            M.append(Mi)
        q -= 1
    return C
    #********* End *********#

第3关：红酒聚类

#encoding=utf8
from sklearn.cluster import AgglomerativeClustering
 
def Agglomerative_cluster(data):
    '''
    对红酒数据进行聚类
    :param data: 数据集，类型为ndarray
    :return: 聚类结果，类型为ndarray
    '''
 
    #********* Begin *********#
    from sklearn.preprocessing import StandardScaler
    scaler = StandardScaler()
    data = scaler.fit_transform(data)
    agnes = AgglomerativeClustering(n_clusters=3)
    result = agnes.fit_predict(data)
    return result
 
    #********* End *********#