KNN算法代码练习

#  生成数据
#  使用make_blobs函数生成数据点
from sklearn.datasets.samples_generator import make_blobs

# 开始生成数据
# 先指定中心点
centers = [[-2,2],[2,2],[0,4]]

# n_samples 表示待生成的样本点的数量
# centers 表示中心点，生成的样本围绕它附近
# cluster_std 表示每个类别的标准差，
x,y = make_blobs(n_samples=60, centers=centers, cluster_std=0.6)

x

array([[-0.08600408,  4.76782848],
       [ 1.3264166 ,  2.37070694],
       [-1.72062744,  2.02582475],
       [ 1.82236685,  2.37271542],
       [-0.30905406,  3.33599758],
       [-0.82732245,  5.17405475],
       [-1.21796898,  2.71879751],
       [ 2.56344749,  2.46380225],
       [ 0.52656441,  3.7157634 ],
       [-1.71565964,  1.58782602],
       [-1.99734574,  2.57046735],
       [-0.6105748 ,  4.32747884],
       [-2.47076485,  0.88160997],
       [-3.09683627,  1.41810538],
       [-0.52244609,  2.88409006],
       [ 0.39124443,  3.93395445],
       [-1.06694802,  2.32322413],
       [ 1.90409727,  2.65346845],
       [-1.47557156,  1.61860603],
       [-0.04215071,  4.18023282],
       [ 1.89614869,  2.19559042],
       [ 2.02560988,  1.32335769],
       [ 2.91560799,  2.69000016],
       [ 1.6580168 ,  1.93073504],
       [ 2.21438265,  3.15312259],
       [ 1.36771487,  2.02817708],
       [ 1.47486871,  1.63766953],
       [-1.38453032,  2.39746726],
       [-2.72504984,  0.29416243],
       [ 0.21979213,  4.27991644],
       [-1.9511985 ,  2.93460142],
       [-0.95264873,  3.863339  ],
       [ 0.42596559,  4.23156268],
       [ 1.14964804,  2.04579981],
       [ 2.45720763,  1.15868596],
       [ 0.14417972,  3.2681776 ],
       [ 1.63766699,  1.79797613],
       [-0.46723236,  3.56507274],
       [-2.00768023,  2.37756443],
       [-0.77164142,  3.07097342],
       [-2.656692  ,  3.18641188],
       [-1.9520929 ,  2.09099171],
       [ 2.04712466,  1.48390184],
       [-2.75281105,  2.12433143],
       [ 1.73602442,  1.86827883],
       [-1.92312906,  3.43099513],
       [ 2.74801908,  2.44293206],
       [ 1.78400907,  2.74081806],
       [-1.7443908 ,  2.54702662],
       [ 0.6563619 ,  2.89757851],
       [-2.33900649,  1.57665199],
       [ 0.74381669,  3.35677091],
       [-2.98695279,  1.2417663 ],
       [ 2.05425203,  1.89126521],
       [-0.08953169,  4.82684634],
       [ 2.1258002 ,  3.38440537],
       [-1.61529457,  2.17528076],
       [ 0.11167727,  4.1635114 ],
       [ 0.31234374,  4.37822912],
       [-0.11923692,  4.38824902]])

y   # 每个样本的cluster的整数标签。这里的标签是0，1，2，对应有3个中心点

array([2, 1, 0, 1, 2, 2, 0, 1, 2, 0, 0, 2, 0, 0, 2, 2, 0, 1, 0, 2, 1, 1, 1,
       1, 1, 1, 1, 0, 0, 2, 0, 2, 2, 1, 1, 2, 1, 2, 0, 2, 0, 0, 1, 0, 1, 0,
       1, 1, 0, 2, 0, 2, 0, 1, 2, 1, 0, 2, 2, 2])

len(y)

60

##  生成的样本数据做个可视化看看
import matplotlib.pyplot as plt
import numpy as np

plt.figure(figsize=(20,10))
c= np.array(centers<