查看neighbors大小对K近邻分类算法预测准确度和泛化能力的影响

代码：

# -*- coding: utf-8 -*-
"""
Created on Thu Jul 12 09:36:49 2018

@author: zhen
"""
"""
    分析n_neighbors的大小对K近邻算法预测精度和泛化能力的影响
"""
from sklearn.datasets import load_breast_cancer

from sklearn.model_selection import train_test_split

from sklearn.neighbors import KNeighborsClassifier

import matplotlib.pyplot as plt

cancer = load_breast_cancer()

x_train, x_test, y_train, y_test = train_test_split(
        cancer.data, cancer.target, stratify=cancer.target, random_state=66)

training_accuracy = []

test_accuracy = []

# n_neighbors取值从1~10
neighbors_settings = range(1, 11)

for n_neighbors in neighbors_settings:
    # 构建模型
    clf = KNeighborsClassifier(n_neighbors=n_neighbors)
    clf.fit(x_train, y_train)
    # 记录训练集精度S
    training_accuracy.append(clf.score(x_train, y_train))
    # 记录泛化能力
    test_accuracy.append(clf.score(x_test, y_test))
    
plt.plot(neighbors_settings, training_accuracy, label="training accuracy")
plt.plot(neighbors_settings, test_accuracy, label="test accuracy")

plt.xlabel("n_neighbors")
plt.ylabel("Accuracy")

plt.legend()

结果：

总结：在仅考虑单一近邻时，训练集上的预测结果十分完美（接近100%）。但随着邻居个数的增多，模型变得更简单（泛化能力越好），训练集精度也随之下降。为求得较好的预测精度和泛化能力，最佳性能在neighbors为6左右！