sklearn中knn算法的应用（三）

    一.K-近邻算法的特性

    参照机器学习的主要流程：

        ● 首先准备X_train,y_train交给机器学习算法

        ● 算法对数据进行拟合形成模型

        ● 输入样例交给模型进行预测，得到输出结果

    二.sklearn中knn算法的应用

        代码实现：

from sklearn.neighbors import KNeighborsClassifier
#创建knn算法的分类器实例
knn_classifier = KNeighborsClassifier(n_neighbors=6)
#拟合训练数据
knn_classifier.fit(X_train,y_train)
#将样本维度变为二维
x1 = x.reshape(1, -1)
#利用knn算法进行预测
y_predict = knn_classifier.predict(x1)
#得出预测结果
y_predict[0]

    重新整合前面的代码

    整合为python代码：

    记做：kNN.py

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, "k must be valid"
      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"""
      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

  def predict(self, X_predict):
      """给定待预测数据集X_predict，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 be equal to X_train"

      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"""
      assert x.shape[0] == self._X_train.shape[1], \
          "the feature number of x must be equal to X_train"

      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]

  def __repr__(self):
      return "KNN(k=%d)" % self.k

    将kNN.py文件放入到和jupyter的代码相同的目录的knn目录下，在jupyter中利用魔法方法进行代码运行

#利用魔法方法加载kNN.py文件
%run knn/kNN.py

#创建实例
knn_clf = KNNClassifier(k=6)
#拟合训练集
knn_clf.fit(X_train,y_train)
#预测输入样例
y_predict = knn_clf.predict(x1)
#得出预测结果
y_predict[0]