Python机器学习之scikit-learn库中KNN算法的封装与使用方法

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"""
    assert k >= 1
    """断言判断k的值是否合法"""
    self.k = k
    self._X_train = None
    self._y_train = None
  def fit(self,X_train,y_train):
    """根据训练数据集X_train和Y_train训练KNN分类器，形成模型"""
    assert X_train.shape[0] == y_train.shape[0]
    """数据和标签的大小必须一样
    assert self.k <= X_train.shape[0]
    """k的值不能超过数据的大小"""
    self._X_train = X_train
    self._y_train = y_train
    return self
  def predict(self,X_predict):
    """必须将训练数据集和标签拟合为模型才能进行预测的过程"""
    assert self._X_train is not None and self._y_train is not None
    """训练数据和标签不可以是空的"""
    assert X_predict.shape[1]== self._X_train.shape[1]
    """待预测数据和训练数据的列(特征个数)必须相同"""
    y_predict = [self._predict(x) for x in X_predict]
    return np.array(y_predict)
  def _predict(self,x):
    """给定单个待测数据x,返回x的预测数据结果"""
    assert x.shape[0] == self._X_train.shape[1]
    """x表示一行数据，即一个数组，那么它的特征数据个数，必须和训练数据相同
    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]

from KNN.py import KNNClassifier
raw_data_x = [[3.393,2.331],
       [3.110,1.781],
       [1.343,3.368],
       [3.582,4.679],
       [2.280,2.866],
       [7.423,4.696],
       [5.745,3.533],
       [9.172,2.511],
       [7.792,3.424],
       [7.939,0.791]]
raw_data_y = [0,0,0,0,0,1,1,1,1,1]
X_train = np.array(raw_data_x)
y_train = np.array(raw_data_y)
x = np.array([9.880,3.555])
# 要将x这个矩阵转换成2维的矩阵，一行两列的矩阵
X_predict = x.reshape(1,-1)
"""1，创建一个对象，设置K的值为6"""
knn_clf = KNNClassifier(6)
"""2，将训练数据和训练标签融合"""
knn_clf.fit(X_train,y_train)
"""3，经过2才能跳到这里，传入待预测的数据"""
y_predict = knn_clf.predict(X_predict)
print(y_predict)