K近邻算法

import pandas as pd
import numpy as np
from sklearn.datasets import load_iris
import matplotlib.pyplot as plt

from sklearn.model_selection import train_test_split
from collections import Counter

iris = load_iris()
df = pd.DataFrame(iris.data, columns=iris.feature_names)
df['label'] = iris.target
df.columns = ['sepal length', 'sepal width', 'petal lenght', 'petal width', 'label']

# 绘画出不同类别的鸢尾花的花萼宽度
plt.scatter(df[:50]['sepal length'], df[:50]['sepal width'], label='0')
plt.scatter(df[50:100]['sepal length'], df[50:100]['sepal width'], label='1')
plt.xlabel('sepal length')
plt.ylabel('sepal width')
plt.legend()

data = np.array(df.iloc[0:100,[0,1,-1]])
X,y = data[:, :-1], data[:,-1]
# 划分训练集与测试集
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)

class KNN:
    
    def __init__(self, X_train, y_train, neighbors=3, p=2):
        '''
        neighbors 临近点的个数
        p=2 采用欧氏距离        
        '''
        self.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):
            dist = np.linalg.norm(X - self.X_train[i], ord=self.p)
            # knn_list保存距离和类别值
            knn_list.append((dist, self.y_train[i]))
            
        for i in range(self.n, len(self.X_train)):
            # 取出最大的距离对应的index
            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)
            # 如果最大的值大于当前距离，则将当前距离置于knn_list中
            if knn_list[max_index][0] > dist:
                knn_list[max_index] = ((dist, self.y_train[i]))
                
        #统计
        # 取出最后一列值（类别值）
        knn = [k[-1] for k in knn_list]
        count_pairs = Counter(knn)
        # 以类别数最多的作为被分类的类别 
        max_count = sorted(count_pairs, key=lambda x:x)[-1]
        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)

knn_lists = [[10,5,6],[12,3,2],[8,9,7]]
knn_lists.index(max(knn_lists, key=lambda x:x[0]))

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')
plt.scatter(df[50:100]['sepal length'], df[50:100]['sepal width'], label='1')
plt.plot(test_point[0], test_point[1], 'bo', label='test_point')
plt.xlabel('sepal length')
plt.ylabel('sepal width')
plt.legend()

from sklearn.neighbors import KNeighborsClassifier

clf_sk = KNeighborsClassifier()
clf_sk.fit(X_train, y_train)
clf_sk.score(X_test, y_test)