First, the title name
Classification algorithm to achieve knn
Second, Title Contents
Native Python implementation knn classification algorithm, and uses iris data set to test
Third, the algorithm analysis
knn algorithm is the easiest one machine learning algorithm, classify by measuring the distance between the different feature values. The basic idea is: if a sample in feature space of the k most similar (i.e. nearest neighbors in feature space) in a sample belonging to a certain category of most, the sample may also fall into this category.
The job is mainly to achieve a simulation of the distance between the test data and training data knn solving, sorting, screening nearest k elements. Wherein, using the spatial distance "Euclidean distance" is calculated, the following expression:
Dist above formula [i] is the labeled test data and training data from the i, xt, xi and test data respectively, the subscript i of the training data, the overall flowchart of the algorithm is as follows:
1 knn algorithm flow chart of FIG.
Fourth, debugging screenshots
The main task of debugging data structure is observed: in Python nested structure is complicated, requires a clear dimension of each step of the output data and the specific structure
6.3.5 Operating results
The input job is iris data set, the output is the prediction type iris. Scattergram output originally envisaged, but less raw Python scattergram results, so to direct the output string, to output class, operating results obtained
FIG 4 is poor effect scattergram raw Python
=
FIG string to direct output category 5
Sixth, Problems and Solutions
The main problem encountered in the implementation process is confusing data structure. In knn implementation class, after several list generation, nested data structures can be confusing, so subscript dimension errors and other errors, the solution is simple, debug view the data structure or content direct print output for each step Observed.
FIG 6 subscript error
Seven, the source code
1.knn.py
# !/usr/bin/env python
# -*- encoding: utf-8 -*-
# @Project : machinelearning
# @File : knn.py
# @Author: yanchengxu
# @Contact : [email protected]
# @Time : 2019/10/7 16:14
# @IDE : PyCharm
import numpy as np
import math
class KNNClassifier:
"""
KNN
"""
def __init__(self, k=3):
"""
初始化
X_train 特征测试集
y_train 标量测试集
res_class 预测结果
:param k: 默认值为3
"""
self.k = k
self.X_train = []
self.y_train = []
self.result = []
def fit(self, X_train, y_train):
"""
KNN 训练模型
:param X_train: 训练集特征数据
:param y_train: 训练集目标数据
:return: self
"""
assert X_train.shape[0] == y_train.shape[0], '训练集特征与目标值个数不匹配'
assert self.k <= X_train.shape[0], 'K值超出训练数据范围'
self.X_train = X_train
self.y_train = y_train
# print('K', self.k)
# print('X.shape', self.X_train.shape)
# print('y.shape', self.y_train.shape)
def get_distance(self, x_test):
"""
计算距离
:param x_test: 测试集
:return: list_dist
"""
list_dist = []
for i in range(len(x_test)):
# x_train 是 X_train 中的每个坐标，只有一个维度
list_dist.append(
[math.sqrt(np.sum(x_train[0] - x_test[i][0]) ** 2 + np.sum(x_train[1] - x_test[i][1]) ** 2) for x_train
in self.X_train])
# print('len of list_dist =', len(list_dist[0]))
return list_dist
def get_k_nearest_dist(self, list_dist):
"""
对距离进行排序
:param list_dist: 测试点距离样本的距离
:return: list_k_nearest_dist
"""
k = self.k
list_each_dist = []
for i in range(len(list_dist)):
dict_temp = {}
for j in range(len(list_dist[i])):
dict_temp[j] = list_dist[i][j]
list_each_dist.append(dict_temp)
# print('list_each_dist:', list_each_dist)
# print('len of count_mix:', len(list_each_dist))
list_k_nearest_dist = []
for i in range(len(list_each_dist)):
# 键值对排序
dict_sorted_dist = dict(sorted(list_each_dist[i].items(), key=lambda x: x[1], reverse=False))
# print('dict_sorted_dist', dict_sorted_dist)
top = 0
dict_knearest_distance = {}
for key in dict_sorted_dist:
dict_knearest_distance[key] = dict_sorted_dist[key]
top += 1
if top == self.k:
break
list_k_nearest_dist.append(dict_knearest_distance)
# print('list_k_nearest_dist:', list_k_nearest_dist)
# 注意缩进!!!
return list_k_nearest_dist
def vote(self, k_nearest_dist):
"""
投票
:param k_nearest_dist: k个最近距离
:return: self
"""
# 所有测试点的topK个标签
list_all_test = []
for i in range(len(k_nearest_dist)):
# 每个测试点的topK个标签
list_each_test = []
for key in k_nearest_dist[i]:
# 数据结构
list_each_test.append(self.y_train[key])
# list_each_test.append(self.y_train[key][0])
list_all_test.append(list_each_test)
# print('list_class2', list_each_test)
# print('list_all_test：', list_all_test)
# 利用set去重->优化速度
set_list_class = []
for i in range(len(list_all_test)):
set_list_class.append(set(list_all_test[i]))
# print('set_list_class', set_list_class)
for i in range(len(set_list_class)):
dict_count = {}
for item in set_list_class[i]:
dict_count.update({item: list_all_test[i].count(item)})
# print('dict_count', dict_count)
# 获得字典dict_count中value最大值对应的key，即为每个点的分类结果
each_result = max(dict_count, key=dict_count.get)
# print('each_result', each_result)
self.result.append(each_result)
# print('result:', self.result)
return self.result
def predict(self, X_predict):
"""
预测
:param X_predict: 待测集
:return: self
"""
assert X_predict.shape[1] == self.X_train.shape[1], '特征数不匹配'
# 获取待测点与标准点的距离
distances = self.get_distance(X_predict)
# print("distances：", distances)
# 获取k个最近距离
k_nearest_dist = self.get_k_nearest_dist(distances)
# print("k_nearest_dist：", k_nearest_dist)
# 投票
result = self.vote(k_nearest_dist)
return result
2.test.py
# !/usr/bin/env python
# -*- encoding: utf-8 -*-
# @Project : machinelearning
# @File : test.py
# @Author : yanchengxu
# @Contact : [email protected]
# @Time : 2019/10/7 16:57
# @IDE : PyCharm
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from myknn.knn import KNNClassifier
import numpy as np
import matplotlib.pyplot as plt
# import itertools
# import random
kn = KNNClassifier(3)
# 训练数据
# X = [[1, 1], [1, 2], [1, 3], [2, 1], [2, 2], [2, 3], [3, 1], [3, 2], [3, 3],
# [6, 6], [6, 7], [6, 8], [7, 6], [7, 7], [7, 8], [8, 6], [8, 7], [8, 8],
# [11, 1], [11, 2], [11, 3], [12, 1], [12, 2], [12, 3], [13, 1], [13, 2], [13, 3]]
#无锡做人流多少钱 http://www.xasgyy.net/
# Y = [['A'], ['A'], ['A'], ['A'], ['A'], ['A'], ['A'], ['A'], ['A'],
# ['B'], ['B'], ['B'], ['B'], ['B'], ['B'], ['B'], ['B'], ['B'],
# ['C'], ['C'], ['C'], ['C'], ['C'], ['C'], ['C'], ['C'], ['C']]
# # 随机
# random_list = list(itertools.product(range(1, 13), range(1, 8)))
# X = random.sample(random_list, len(Y))
# # print('random_list', X)
# print('shape y:', y_train.shape)
iris_dataset = load_iris()
# test
# print(iris_dataset)
X_train, X_test, y_train, y_test = train_test_split(iris_dataset['data'], iris_dataset['target'], random_state=0)
X = np.asarray(X_train)
Y = np.asarray(y_train)
# print('X:', X)
# print('Y,shape', Y.shape)
# print('Y.type', type(Y))
# 模型训练
kn.fit(X, Y)
# 数据预测
x_test = [[5, 2.9, 1, 0.2], [6.7, 3.2, 5.2, 2.3], [5.6, 3.1, 4.5, 1.5]]
X_test = np.asarray(x_test)
prediction = kn.predict(X_test)
# 打印预测结果
for i in range(len(prediction)):
print(x_test[i], '->', iris_dataset['target_names'][prediction[i]])
# # 散点图观察
# x1 = []
# y1 = []
#
# # 训练集
# for i in np.asarray(X):
# x1.append(i[0])
# y1.append(i[1])
#
# x2 = []
# y2 = []
# # 测试集
# for i in np.asarray(x_test):
# x2.append(i[0])
# y2.append(i[1])
#
# plt.plot(x1, y1, 'r*')
# plt.plot(x2, y2, 'g+')
# plt.show()