使用KNN算法进行分类

import matplotlib.pyplot as plt
import numpy as np

from sklearn.datasets.samples_generator import make_blobs
# 生成数据
centers = [[-2, 2], [2, 2], [0, 4]]
X, y = make_blobs(n_samples=600, centers=centers, random_state=0, cluster_std=0.60)
# 画出数据
plt.figure(figsize=(16, 10), dpi=144)
c = np.array(centers)
plt.scatter(X[:, 0], X[:, 1], c=y, s=100, cmap='cool');         # 画出样本
plt.scatter(c[:, 0], c[:, 1], s=100, marker='^', c='orange');   # 画出中心点

from sklearn.neighbors import KNeighborsClassifier
from numpy as np
# 模型训练
k = 5
clf = KNeighborsClassifier(n_neighbors=k)
clf.fit(X, y);

# 进行预测
# X_sample = [[0,2],[1,1],[-1,3]]
X_sample = np.array([[0,2],[1,1],[-1,3]],dtype=int)

y_sample = clf.predict(X_sample);
neighbors = clf.kneighbors(X_sample, return_distance=False);

X_sample_disp_x = np.array(X_sample[:,0],dtype=int)
X_sample_disp_y = np.array(X_sample[:,1],dtype=int)
# 画出示意图
plt.figure(figsize=(16, 10), dpi=144)
plt.scatter(X[:, 0], X[:, 1], c=y, s=100, cmap='cool');    # 样本
plt.scatter(c[:, 0], c[:, 1], s=100, marker='^', c='k');   # 中心点
plt.scatter(X_sample_disp_x, X_sample_disp_y, marker="x", 
            c=y_sample, s=100, cmap='cool')    # 待预测的点



for i in neighbors[0]:
    plt.plot([X[i][0], X_sample[0][0]], [X[i][1], X_sample[0][1]],
             'k--', linewidth=0.8);    # 预测点与距离最近的 5 个样本的连线
for i in neighbors[1]:
    plt.plot([X[i][0], X_sample[1][0]], [X[i][1], X_sample[1][1]],
             'k--', linewidth=0.8);
for i in neighbors[2]:
    plt.plot([X[i][0], X_sample[2][0]], [X[i][1], X_sample[2][1]],
             'k--', linewidth=0.8);