Python实现机器算法-01-DBSCAN

# -*- coding: UTF-8 -*-
"""

~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
@File         :   dbscan.py    
@Contact      :   ffzzyy@126.com
@License      :   (C)Copyright 2017-2019
@Author       :   ffzzyy
@Version      :   0.1
@Modify Time  :   2019/3/28 22:10
@Desciption

dbscan 算法实现

"""
import pandas as pd
import matplotlib.pyplot as plt
import sklearn.cluster as skc
import numpy as np
import math
import seaborn as sns


def dist(a, b):
    """
    输入：向量A, 向量B
    输出：两个向量的欧式距离
    """
    return math.sqrt(np.power(a - b, 2).sum())


class dbscan():
    """dbscan 类

    Parameters
    ----------
    eps,min_samples

    Attributes
    ----------
    core_object_index:list,核心对象序列，对应训练集索引
    _train_set:ndarray,训练集
    labels:ndarray,对应训练集索引的，聚类 id
    _k:int,聚类簇id，从 0 开始

    """
    def __init__(self, eps, min_samples):
        self.eps = eps
        self.min_samples = min_samples
        self.core_object_index = []
        self._train_set = None
        self.labels = []
        self._k = -1
        self.components = []

    def fit(self, train_set):
        self._train_set = train_set
        self.init_core_objects()
        self.labels = np.array([-1] * len(train_set))
        self._k = -1
        unvisited_object_index = range(len(train_set))
        unvisited_core_index = self.core_object_index.copy()  # 深度复制

        while (len(unvisited_core_index) != 0):
            """
            从 未被访问的核心对象中 随机选择一个 queue 序列中，queue 
            来保存 通过第一个核心对象，一个接一个找出其密度可达的 核心对象