K-NN(k近邻算法)基础

对于二维数据集，可以画出所有可能的测试点的预测结果，根据平面中每个点所属的类别，对平面进行着色，这样可以查看决策边界。即算法对类别0和类别1的分界线：
用下面的代码分别将1、3、9个邻居三种情况的决策边界可视化：

import mglearn.plots
import mglearn.datasets

import matplotlib.pyplot as plt

from sklearn.model_selection import train_test_split
from sklearn.neighbors import KNeighborsClassifier
from sklearn.neighbors import KNeighborsRegressor
from sklearn.datasets import load_breast_cancer


def knn_decision_boundary():
    X, y = mglearn.datasets.make_forge()
    X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0)

    # 二维数据集，决策边界可视化
    fig, axes = plt.subplots(1, 3, figsize=(10, 3))
    for n_num, ax in zip([1, 3, 9], axes):
        clf = KNeighborsClassifier(n_neighbors=n_num).fit(X, y)
        mglearn.plots.plot_2d_separator(clf, X, fill=True, ax=ax, alpha=.4)
        mglearn.discrete_scatter(X[:, 0], X[:, 1], y, ax=ax)
        ax.set_title('{