这个算法比较简单，就是计算不同特征值之间的距离并进行分类
先写一个计算欧几里得距离的函数
import numpy as np
def euclidean_distance(x1, x2):
distance = np.sqrt(sum((x1 - x2) ** 2))
return distance
from collections import Counter
class KNN:
def __init__(self, k):
self.k = k
def fit(self, X, y):
self.X_train = X
self.y_train = y
def predict(self, X):
predictions = [self._predict(x) for x in X]
return predictions
def _predict(self, x):
# 先计算距离
distances = [euclidean_distance(x, x_train) for x_train in self.X_train]
# 再排序得到最近的k个，得到的k_indices是最近的k个训练样本的索引
# argsort()函数是返回排序后的索引数组，排序默认为升序
k_indices = np.argsort(distances)[:self.k]
k_nearest_labels = [self.y_train[i] for i in k_indices]
# 统计k个最近的样本中各个类别的个数
most_common = Counter(k_nearest_labels).most_common(1)
return most_common[0][0]
训练函数
from sklearn import datasets
from sklearn.model_selection import train_test_split
import matplotlib.pyplot as plt
from matplotlib.colors import ListedColormap
#定义颜色映射
cmap = ListedColormap(['#FF0000', '#00FF00', '#0000FF'])
iris = datasets.load_iris()
X, y = iris.data, iris.target
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=1234)
plt.figure()
plt.scatter(X[:, 2], X[:, 3], c=y, cmap=cmap, edgecolor='k', s=20)
plt.show()
png
clf = KNN(k=5)
clf.fit(X_train, y_train)
predicition = clf.predict(X_test)
print(predicition)
[1, 2, 2, 0, 1, 0, 0, 0, 1, 2, 1, 0, 2, 1, 0, 1, 2, 0, 2, 1, 1, 1, 1, 1, 2, 0, 2, 1, 2, 0]
acc = np.sum(predicition == y_test) / len(y_test)
print(acc)
0.9666666666666667