下面是一个简单的KNN算法的Python代码示例:
import numpy as np from collections import Counter def euclidean_distance(x1, x2): return np.sqrt(np.sum((x1 - x2) ** 2)) class KNN: def __init__(self, k=3): self.k = k def fit(self, X, y): self.X_train = X self.y_train = y def predict(self, X): y_pred = [self._predict(x) for x in X] return np.array(y_pred) def _predict(self, x): # 计算所有训练样本与待预测样本的距离 distances = [euclidean_distance(x, x_train) for x_train in self.X_train] # 根据距离排序并获取前k个样本的索引 k_indices = np.argsort(distances)[:self.k] # 获取前k个样本的标签 k_labels = [self.y_train[i] for i in k_indices] # 返回出现次数最多的标签作为预测结果 most_common = Counter(k_labels).most_common(1) return most_common[0][0]
使用示例:
X_train = np.array([[1, 2], [1.5, 1.8], [5, 8], [8, 8], [1, 0.6], [9, 11]]) y_train = np.array([0, 0, 1, 1, 0, 1]) knn = KNN(k=3) knn.fit(X_train, y_train) X_test = np.array([[2, 3], [6, 9], [1, 1]]) y_pred = knn.predict(X_test) print(y_pred) # 输出:[0, 1, 0]
这个示例中使用的是欧氏距离作为距离度量方法,同时实现了一个简单的KNN类,其中的fit()
方法用于训练模型,predict()
方法用于预测新样本的标签。KNN类的_predict()
方法用于计算单个样本的预测结果。