# encoding:utf-8
import math
"""计算空间中两点之间的距离"""
def L(x, y, p=2):
if len(x) == len(y) and len(x) > 1:
sum = 0
for i in range(len(x)):
sum += math.pow(abs(x[i] - y[i]), p)
return math.pow(sum, 1/p)
else:
return 0
"""数据点x1,x2,x3"""
x1 = [1, 1]
x2 = [5, 1]
x3 = [4, 4]
for i in range(1, 5):
r = {'1-{}'.format(c): L(x1, c, p=i) for c in [x2, x3]}
print(min(zip(r.values(), r.keys())))
# encoding:utf-8
"""遍历所有数据点,找出n个距离最近的点的分类情况,少数服从多数"""
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.datasets import load_iris
from collections import Counter
from sklearn.neighbors import KNeighborsClassifier
"""
train_test_split函数用于将矩阵随机划分为训练子集和测试子集,
并返回划分好的训练集测试集样本和训练集测试集标签。
"""
from sklearn.model_selection import train_test_split
"""加载鸢尾花数据集"""
iris = load_iris()
"""iris.data(获取属性数据),iris.feature_names(获取列属性值)"""
df = pd.DataFrame(iris.data, columns=iris.feature_names)
"""获取类别数据,这里注意的是已经经过处理,targe里0、1、2分别代表三种类别"""
df['label'] = iris.target
df.columns = ['sepal length', 'sepal width', 'petal length', 'petal width', 'label']
"""画出正例和反例的散点图"""
plt.scatter(df[:50]['sepal length'], df[:50]['sepal width'], label='0', color='blue')
plt.scatter(df[50:100]['sepal length'], df[50:100]['sepal width'], label='1', color='orange')
plt.xlabel('sepal length')
plt.ylabel('sepal width')
plt.legend()
plt.show()
class KNN:
def __init__(self, x_train, y_train, n_neighbors=3, p=2):
"""
:param n_neighbors: 临近点个数
:param p: 距离度量
"""
self.n = n_neighbors
self.p = p
self.x_train = x_train
self.y_train = y_train
def predict(self, x):
"""取出n个点"""
knn_list = []
for i in range(self.n):
"""
np.linalg.norm(x, ord=None, axis=None, keepdims=False)
x: 表示矩阵(也可以是一维)
ord: 范数类型
向量的范数(默认二范数,ord=2--二范数,ord=1--一范数,ord=np.inf--无穷范数)
矩阵的范数(ord=1--列和的最大值,ord=2--求特征值,然后求最大特征值的算术平方根,ord=正无穷--行和的最大值)
axis处理类型:
axis=1 表示按行向量处理,求多个行向量的范数
axis=0 表示按列向量处理,求多个列向量的范数
axis-None 表示矩阵范数
keepdims: 是否保持矩阵的二维特性(True表示保持矩阵的二维特性,False相反)
"""
dist = np.linalg.norm(x - self.x_train[i], ord=self.p)
knn_list.append((dist, self.y_train[i]))
for i in range(self.n, len(self.x_train)):
max_index = knn_list.index(max(knn_list, key=lambda x: x[0]))
dist = np.linalg.norm(x - self.x_train[i], ord=self.p)
if knn_list[max_index][0] > dist:
knn_list[max_index] = (dist, self.y_train[i])
"""统计"""
knn = [k[-1] for k in knn_list]
count_pairs = Counter(knn)
"""
add = lambda x, y : x+y————add(1,2) # 结果为3
lambda匿名函数
"""
max_count = sorted(count_pairs.items(), key=lambda x: x[1])[-1][0]
return max_count
def score(self, x_test, y_test):
right_count = 0
n = 10
for x, y in zip(x_test, y_test):
label = self.predict(x)
if label == y:
right_count += 1
return right_count / len(x_test)
"""提取df的前100行的第1列、第2列和最后一列数据"""
data = np.array(df.iloc[:100, [0, 1, -1]])
x, y = data[:, :-1], data[:, -1]
"""
train_test_split(train_data,train_target,test_size, random_state)
train_data: 被划分的样本特征集
train_target: 被划分的样本标签
test_size: 如果是浮点数,在0-1之间,表示样本占比;如果是整数的话就是样本的数量
random_size: 是随机数的种子(随机数种子:其实就是该组随机数的编号,在需要重复试验的时候,
保证得到一组一样的随机数。比如你每次都填1,其他参数一样的情况下你得到的随机数组是一样的。
但填0或不填,每次都会不一样。
随机数的产生取决于种子,随机数和种子之间的关系遵从以下两个规则:
种子不同,产生不同的随机数;种子相同,即使实例不同也产生相同的随机数。)
"""
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.2)
clf = KNN(x_train, y_train)
clf.score(x_test, y_test)
test_point = [6.0, 3.0]
print('Test Point: {}'.format(clf.predict(test_point)))
plt.scatter(df[:50]['sepal length'], df[:50]['sepal width'], label='0', color='blue')
plt.scatter(df[50:100]['sepal length'], df[50:100]['sepal width'], label='1', color='orange')
plt.plot(test_point[0], test_point[1], 'bo', label='test_point', color='red')
plt.xlabel('sepal length')
plt.ylabel('sepal width')
plt.legend()
plt.show()
clf_sk = KNeighborsClassifier()
clf_sk.fit(x_train, y_train)
KNeighborsClassifier(algorithm='auto', leaf_size=30, metric='minkowski', metric_params=None, n_jobs=None, n_neighbors=5, p=2, weights='uniform')
print(clf_sk.score(x_test, y_test))
# encoding:utf-8
"""kd-tree每个结点中主要包含的数据结构如下"""
from math import sqrt
from collections import namedtuple
from time import clock
from random import random
class KdNode(object):
def __init__(self, dom_elt, split, left, right):
"""k维向量结点(k维空间中的一个样本点)"""
self.dom_elt = dom_elt
"""整数(进行分割维度的序号)"""
self.split = split
"""该结点分割超平面左子空间构成的kd-tree"""
self.left = left
"""该结点分割超平面右子空间构成的kd-tree"""
self.right = right
class KdTree(object):
def __init__(self, data):
"""数据维度"""
k = len(data[0])
"""按第split维划分数据集exset创建KdNode"""
def CreateNode(split, data_set):
"""数据集为空"""
if not data_set:
return None
"""
key参数的值为一个函数,此函数只有一个参数且返回一个值用来进行比较
operator模块提供的itemgetter函数用于获取对象的哪些维的数据,参数为需要获取的数据在对象中的序号
data_set.sort(key=itemgetter(split)) 按要进行分割的那一维数据排序
"""
data_set.sort(key=lambda x: x[split])
"""Python中的整数除法"""
split_pos = len(data_set) // 2
"""中位数分割点"""
median = data_set[split_pos]
split_next = (split + 1) % k
"""递归地创建kd树"""
return KdNode(
median,
split,
CreateNode(split_next, data_set[:split_pos]), # 创建左子树
CreateNode(split_next, data_set[split_pos + 1:]) # 创建右子树
)
"""从第0维分量开始构建kd树,返回根结点"""
self.root = CreateNode(0, data)
"""KDTree的前序遍历"""
def preorder(root):
print(root.dom_elt)
"""结点不为空"""
if root.left:
preorder(root.left)
if root.right:
preorder(root.right)
"""
对构建好的kd树进行搜索,寻找与目标最近的样本点
定义一个namedtuple,分别存放最近坐标点,最近距离和访问过的结点数
"""
"""
为了构造一个namedtuple需要两个参数,分别是tuple的名字和其中域的名字
名字是:Result_tuple
域是: nearest_point nearest_dist nodes_visited
"""
result = namedtuple("Result_tuple", "nearest_point nearest_dist nodes_visited")
def find_nearest(tree, point):
k = len(point) # 数据维度
def travel(kd_node, target, max_dist):
if kd_node is None:
"""python中用float("inf")和float("-inf")表示正负无穷"""
return result([0] * k, float("inf"), 0)
nodes_visited = 1
s = kd_node.split # 进行分割的维度
pivot = kd_node.dom_elt # 进行分割的“轴”
if target[s] <= pivot[s]: # 如果目标点第s维小于分割轴的对应值(目标离左子树更近)
nearer_node = kd_node.left # 下一个访问结点为左子树根结点
further_node = kd_node.right # 同时记录下右子树
else: # 目标离右子树更近
nearer_node = kd_node.right # 下一个访问结点为右子树根结点
further_node = kd_node.left
temp1 = travel(nearer_node, target, max_dist) # 进行遍历找到包含目标点的区域
nearest = temp1.nearest_point # 以此叶结点作为"当前最近点"
dist = temp1.nearest_dist # 更新最近距离
nodes_visited += temp1.nodes_visited
if dist < max_dist:
max_dist = dist # 最近点将在以目标点为球心, max_dist为半径的超球体内
temp_dist = abs(pivot[s] - target[s]) # 第s维上目标点与分割超平面的距离
if max_dist < temp_dist: # 判断超球体是否与超平面相交
return result(nearest, dist, nodes_visited) # 不相交则可以直接返回,不用继续判断
"""计算目标点与分割点的欧氏距离"""
temp_dist = sqrt(sum((p1 - p2) ** 2 for p1, p2 in zip(pivot, target)))
if temp_dist < dist: # 如果“更近”
nearest = pivot # 更新最近点
dist = temp_dist # 更新最近距离
max_dist = dist # 更新超球体半径
"""检查另一个子结点对应的区域是否有更近的点"""
temp2 = travel(further_node, target, max_dist)
nodes_visited += temp2.nodes_visited
if temp2.nearest_dist < dist: # 如果另一个子结点内存在更近距离
nearest = temp2.nearest_point # 更新最近点
dist = temp2.nearest_dist # 更新最近距离
return result(nearest, dist, nodes_visited)
return travel(tree.root, point, float("inf")) # 从根结点开始递归
data = [[2, 3], [5, 4], [9, 6], [4, 7], [8, 1], [7, 2]]
kd = KdTree(data)
preorder(kd.root)
def random_point(k): # 产生一个k维随机向量,每维分量值在0~1之间
return [random() for _ in range(k)]
def random_points(k, n): # 产生n个k维随机向量
return [random_point(k) for _ in range(n)]
ret = find_nearest(kd, [3, 4.5])
print(ret)
N = 400000
t0 = clock()
kd2 = KdTree(random_points(3, N)) # 构建包含四十万个3维空间样本点的kd树
ret2 = find_nearest(kd2, [0.1, 0.5, 0.8]) # 四十万个样本点中寻找离目标最近的点
t1 = clock()
print("time: ", t1 - t0, "s")
print(ret2)