使用KNN实现对鸢尾花数据集或者自定义数据集的的预测

创建自定义数据集：

point1=[[7.7,6.1],[3.1,5.9],[8.6,8.8],[9.5,7.3],[3.9,7.4],[5.0,5.3],[1.0,7.3]]
point2=[[0.2,2.2],[4.5,4.1],[0.5,1.1],[2.7,3.0],[4.7,0.2],[2.9,3.3],[7.3,7.9]]
point3=[[9.2,0.7],[9.2,2.1],[7.3,4.5],[8.9,2.9],[9.5,3.7],[7.7,3.7],[9.4,2.4]]
point_concat = np.concatenate((point1, point2, point3), axis=0)
point_concat_label = np.concatenate((np.zeros(len(point1)), np.ones(len(point2)), np.ones(len(point2)) + 1), axis=0)
print(point_concat_label)

并对以上数据集进行预测

完整代码：

from sklearn.neighbors import KNeighborsClassifier
import numpy as np
import matplotlib.pyplot as plt

point1=[[7.7,6.1],[3.1,5.9],[8.6,8.8],[9.5,7.3],[3.9,7.4],[5.0,5.3],[1.0,7.3]]
point2=[[0.2,2.2],[4.5,4.1],[0.5,1.1],[2.7,3.0],[4.7,0.2],[2.9,3.3],[7.3,7.9]]
point3=[[9.2,0.7],[9.2,2.1],[7.3,4.5],[8.9,2.9],[9.5,3.7],[7.7,3.7],[9.4,2.4]]
point_concat = np.concatenate((point1, point2, point3), axis=0)
point_concat_label = np.concatenate((np.zeros(len(point1)), np.ones(len(point2)), np.ones(len(point2)) + 1), axis=0)
print(point_concat_label)

n_neighbors = 3
knn = KNeighborsClassifier(n_neighbors=n_neighbors, algorithm='kd_tree', p=2)

knn.fit(point_concat, point_concat_label)

x1 = np.linspace(0, 10, 100)
y1 = np.linspace(0, 10, 100)
x_axis, y_axis = np.meshgrid(x1, y1)
print('s')

xy_axis=np.c_[x_axis.ravel(),y_axis.ravel()]
knn_predict_result=knn.predict(xy_axis)

fig=plt.figure(figsize=(5,5))
ax=fig.add_subplot(111)
ax