02-20 kd树(鸢尾花分类)

kd树(鸢尾花分类)

导入模块

import numpy as np
import matplotlib.pyplot as plt![在这里插入图片描述](https://img-blog.csdnimg.cn/20200227200456746.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80NjAzMjM1MQ==,size_16,color_FFFFFF,t_70)
from matplotlib.colors import ListedColormap
from matplotlib.font_manager import FontProperties
from sklearn import datasets
from sklearn.neighbors import KDTree
%matplotlib inline
font = FontProperties(fname='/Library/Fonts/Heiti.ttc')

获取数据

iris_data = datasets.load_iris()
X = iris_data.data[:, [2, 3]]
y = iris_data.target
label_list = ['山鸢尾', '杂色鸢尾', '维吉尼亚鸢尾']

构建决策边界

def plot_decision_regions(X, y, classifier):
    marker_list = ['o', 'x', 's']
    color_list = ['r', 'b', 'g']
    cmap = ListedColormap(color_list[:len(np.unique(y))])

    x1_min, x1_max = X[:, 0].min() - 1, X[:, 0].max() + 1
    x2_min, x2_max = X[:, 1].min() - 1, X[:, 1].max() + 1
    t1 = np.linspace(x1_min, x1_max, 666)
    t2 = np.linspace(x2_min, x2_max, 666)

    x1, x2 = np.meshgrid(t1, t2)
    # y_hat_ind：最近的3个邻居的索引
    # y_hat_dist：距离最近的3个邻居的距离
    y_hat_dist, y_hat_ind = classifier.query(
        np.array([x1.ravel(), x2.ravel()]).T, k=3)  # 搜索最近的3个邻居
    
    # 选出类别最多的邻居作为自己类别
    y_hat_list = []
    for i in range(len(y_hat_ind)):
        y_hat_i = Counter(y_hat_ind[i, :]).most_common(1)[0][0]
        y_hat_list.append(y_hat_i)
        
    y_hat = y[y_hat_list]
    y_hat = y_hat.reshape(x1.shape)
    plt.contourf(x1, x2, y_hat, alpha=0.2, cmap=cmap)
    plt.xlim(x1.min(), x1.max())
    plt.ylim(x2.min(), x2.max())

    for ind, clas in enumerate(np.unique(y)):
        plt.scatter(X[y == clas, 0], X[y == clas, 1], alpha=0.8, s=50,
                    c=color_list[ind], marker=marker_list[ind], label=label_list[clas])

训练模型

kdtree = KDTree(X)

可视化

plot_decision_regions(X, y, classifier=kdtree)
plt.xlabel('花瓣长度（cm）', fontproperties=font)
plt.ylabel('花瓣宽度（cm）', fontproperties=font)
plt.legend(prop=font)
plt.show()

[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-9SqSPqQj-1582805075239)(02-20%20kd%E6%A0%91%28%E9%B8%A2%E5%B0%BE%E8%8A%B1%E5%88%86%E7%B1%BB%29_files/02-20%20kd%E6%A0%91%28%E9%B8%A2%E5%B0%BE%E8%8A%B1%E5%88%86%E7%B1%BB%29_10_0.png)]