K近鄰分類

import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
import mglearn


from sklearn.datasets import load_breast_cancer
from sklearn.model_selection import train_test_split
from sklearn.neighbors import KNeighborsClassifier
cancer = load_breast_cancer()

X_train, X_test, y_train, y_test = train_test_split(cancer.data, cancer.target,random_state=66)

training_accuracy = []
test_accuracy = []
neighbors_setting = range(1, 11) #neighbor存成一維陣列

for n_neighbors in neighbors_setting:
    #構建模型
    clf = KNeighborsClassifier(n_neighbors=n_neighbors)
    clf.fit(X_train, y_train)
    #記錄訓練集精度
    training_accuracy.append(clf.score(X_train, y_train))
    #記錄泛化精度
    test_accuracy.append(clf.score(X_test,y_test))

plt.plot(neighbors_setting, training_accuracy, label="training_accuracy")
plt.plot(neighbors_setting, test_accuracy, label='test accuracy')
plt.ylabel("Accuracy")
plt.xlabel("n_neighbors")
plt.legend()
plt.show()