手动实现最邻近算法 KNN算法（分类 回归）

#数据
# 特征
raw_data_x= [[3.393533211,2.331273381],
             [2.110073483,1.781539638],
             [1.343808831,3.368360954],
             [3.582294042,4.679179110],
             [2.280362439,2.866990263],
             [7.423436942,4.696522875],
             [5.745051997,3.533989803],
             [9.172168622,2.511101045],
             [7.792783481,3.424088941],
             [7.939820817,0.791637231]
            ]
# 所属类别
raw_data_y = [0,0,0,0,0,1,1,1,1,1]

np.array(raw_data_x)#将数据转化成numpy类型
X_train=np.array(raw_data_x)
y_train=np.array(raw_data_y)
plt.scatter(X_train[y_train==0, 0],X_train[y_train==0, 1], color =r)
plt.scatter(X_train[y_train==1, 0],X_train[y_train==1, 1], color =g)
plt.show()
from math import sqrt

封装一下上面的代码

from collections import Counter
from math import sqrt
import numpy as np

class KNNClassifier():

    """封装自己KNN算法"""
    def __init__(self, k):
        assert k >= 1, "k 值必须大于1"
        self.k = k
        self._X_train = None # 类似private
        self._y_train = None
    def fit(self, X_train, y_train):
        self._X_train = X_train
        self._y_train = y_train
        return self
    def predict(self, X_predict):
        return np.array([self._predict(x) for x in X_predict])
    # _predict私有方法
    def _predict(self, x_single):
        distances = [sqrt(np.sum((x_train - x_single) ** 2)) for x_train in self._X_train]
        nearst = np.argsort(distances)
        topK_y = [self._y_train[i] for i in nearst[:self.k]]
        votes = Counter(topK_y)
        predict_y = votes.most_common(1)[0][0]
        return predict_y
    def __repr__(self):
        return "KNNClassifier()"

调用试试：

还是用库吧嘿嘿嘿