scikit-learn中的机器学习算法封装——kNN

#先导入我们需要的包
from sklearn.neighbors import KNeighborsClassifier

#特征点的集合
raw_data_X = [[3.393533211, 2.331273381],
              [3.110073483, 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]
             ] 
#0就代表良性肿瘤，1就代表恶性肿瘤
raw_data_y = [0, 0, 0, 0, 0, 1, 1, 1, 1, 1] 
#我们使用raw_data_X和raw_data_y作为我们的训练集
X_train = np.array(raw_data_X)  #训练数据集的特征
Y_train = np.array(raw_data_y)  #训练数据集的结果(标签)

#首先我们需要对包中的KNeighborsClassifier进行实例化，其中可以传入k的值作为参数
kNN_classifier = KNeighborsClassifier(n_neighbors=6)
#然后先执行fit方法进行拟合操作得出模型,将训练数据集作为参数传入
kNN_classifier.fit(X_train,Y_train)
#执行predict预测操作，传入样本数据
#因为使用scikit-learn中的kNN算法是对一组矩阵形式的数据进行一条条的预测，所以我们传入的样本数据集参数也应该先转换为矩阵的形式
X_predict = x.reshape(1,-1) #因为我们已知我们传入的数据只有一行
y_predict = kNN_classifier.predict(X_predict)
In[1]: y_predict
Out[1]: array([1])
#所以此时的y_predict即为我们所需要的样本的预测结果
In[2]: y_predict[0]
Out[2]: 1

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

class KNNClassifier:
    
    def __init__(self, k):
        ‘‘‘初始化KNN分类器‘‘‘
        #使用断言进行判定传入的参数的合法性
        assert k >= 1, "k must be valid"
        self.k = k;
        #此处定义为私有变量，外部成员不可访问进行操作
        self._X_train = None
        self._Y_train = None
       
    def fit(seld, X_train, Y_train):
        ‘‘‘根据训练集X_train和Y_train训练kNN分类器‘‘‘
        assert X_train.shape[0] == Y_train.shape[0],        "the size of X_train must be equal to the size of Y_train"
        assert self.k <= X_train.shape[0],        "the size of X_train must be at least k"
        
        self._X_train = X_train
        self._Y_train = Y_train
        return self
    
    #X_predict 为传入的矩阵形式数据
    def predict(self, X_predict):
        ‘‘‘给定待预测数据集X_train，返回表示X_predict的结果向量‘‘‘
        assert self._X_train is not None and self._Y_train is not None,        "must fit before predict!"
        assert X_predict.shape[1] == self._X_train.shape[1],        "the feature number of X_predict must equal to X_train"
        
        #使用私有方法_predict(x)进行对x进行预测
        #循环遍历X_predict，对其中每一条样本数据集执行私有方法_predict(x)，将预测结果存入y_predict中
        y_predict = [self._predict(x) for x in X_predict]
        return np.array(y_predict)
    
    def _predict(self, x):
        ‘‘‘给定单个待预测数据x，返回x的预测结果值‘‘‘
        ‘‘‘此处的代码逻辑和重写之前的代码逻辑一样‘‘‘
        distances = [sqrt(np.sum(x_train - x) ** 2) for x_train in self._X_train]
        nearest = np.argsort(distances)
        
        topk_y = [self._Y_train[i] for i in nearest[:self.k]]
        votes = Counter(topk_y)
        return votes.most_common(1)[0][0]
    
    #重写对象的“自我描述”
    def __repr__(self):
        return "KNN(k=%d)" % self.k