准备数据

  1. import numpy as np
  2. import matplotlib.pyplot as plt
  4. # raw_data_X 第1列为特征1，第2列为特征2
  5. raw_data_X = [
  6.                 [3.393533211, 2.331273381],
  7.                 [3.110073483, 1.781539638],
  8.                 [1.343808831, 3.368360954],
  9.                 [3.582294042, 4.679179110],
  10.                 [2.280362439, 2.866990263],
  11.                 [7.423436942, 4.696522875],
  12.                 [5.745051997, 3.533989803],
  13.                 [9.172168622, 2.511101045],
  14.                 [7.792783481, 3.424088941],
  15.                 [7.939820817, 0.791637231]
  16.              ]
  18. # 标签
  19. raw_data_y = [0, 0, 0, 0, 0, 1, 1, 1, 1, 1]
  21. # 将list类型转换成ndarray
  22. X_train = np.array(raw_data_X)
  23. y_train = np.array(raw_data_y)

可视化探索

image.png

  1. plt.scatter(X_train[y_train==0,0], X_train[y_train==0,1], color='g')  # 标签0 为绿色
  2. plt.scatter(X_train[y_train==1,0], X_train[y_train==1,1], color='r')  # 标签1 为红色
  3. plt.show()

image.png

预测

  1. x = np.array([8.093607318, 3.365731514])  # 预测点
  3. plt.scatter(X_train[y_train==0,0], X_train[y_train==0,1], color='g')
  4. plt.scatter(X_train[y_train==1,0], X_train[y_train==1,1], color='r')
  5. plt.scatter(x[0], x[1], color='b')
  6. plt.show()

image.png

建模

image.png
image.png

模型封装

简单封装

  1. import numpy as np
  2. from math import sqrt
  3. from collections import Counter
  6. def kNN_classify(k, X_train, y_train, x):
  8.     assert 1 <= k <= X_train.shape[0], "k must be valid"
  9.     assert X_train.shape[0] == y_train.shape[0], \
  10.         "the size of X_train must equal to the size of y_train"
  11.     assert X_train.shape[1] == x.shape[0], \
  12.         "the feature number of x must be equal to X_train"
  14.     distances = [sqrt(np.sum((x_train - x)**2)) for x_train in X_train]
  15.     nearest = np.argsort(distances)
  17.     topK_y = [y_train[i] for i in nearest[:k]]
  18.     votes = Counter(topK_y)
  20.     return votes.most_common(1)[0][0]

image.png

进一步封装

为了将语法和scikit-learn统一

  1. # kNN.py
  2. import numpy as np
  3. from math import sqrt
  4. from collections import Counter
  7. class KNNClassifier:
  9.     def __init__(self, k):
  10.         """初始化kNN分类器"""
  11.         assert k >= 1, "k must be valid"
  12.         self.k = k
  13.         self._X_train = None
  14.         self._y_train = None
  16.     def fit(self, X_train, y_train):
  17.         """根据训练数据集X_train和y_train训练kNN分类器"""
  18.         assert X_train.shape[0] == y_train.shape[0], \
  19.             "the size of X_train must be equal to the size of y_train"
  20.         assert self.k <= X_train.shape[0], \
  21.             "the size of X_train must be at least k."
  23.         self._X_train = X_train
  24.         self._y_train = y_train
  25.         return self
  27.     def predict(self, X_predict):
  28.         """给定待预测数据集X_predict，返回表示X_predict的结果向量"""
  29.         assert self._X_train is not None and self._y_train is not None, \
  30.                 "must fit before predict!"
  31.         assert X_predict.shape[1] == self._X_train.shape[1], \
  32.                 "the feature number of X_predict must be equal to X_train"
  34.         y_predict = [self._predict(x) for x in X_predict]
  35.         return np.array(y_predict)
  37.     def _predict(self, x):
  38.         """给定单个待预测数据x，返回x的预测结果值"""
  39.         assert x.shape[0] == self._X_train.shape[1], \
  40.             "the feature number of x must be equal to X_train"
  42.         distances = [sqrt(np.sum((x_train - x) ** 2))
  43.                      for x_train in self._X_train]
  44.         nearest = np.argsort(distances)
  46.         topK_y = [self._y_train[i] for i in nearest[:self.k]]
  47.         votes = Counter(topK_y)
  49.         return votes.most_common(1)[0][0]
  51.     def __repr__(self):
  52.         return "KNN(k=%d)" % self.k

image.png