CancetDataset을 이용해서 복잡도와 일반화관계알아보기

코드를 통해서 알아본다 .

 

from sklearn.datasets import load_breast_cancer
from sklearn.model_selection import train_test_split
from sklearn.neighbors import KNeighborsClassifier
import sklearn.datasets
import scipy as sp
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
import mglearn


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)

train_accuracy = []
test_accuracy = []
# 1에서 10까지 이웃을 적용
neighbors_settings = range(1, 11)

for n_neighbors in neighbors_settings:
    # 모델 생성
    clf = KNeighborsClassifier(n_neighbors=n_neighbors).fit(X_train, y_train)
    # 훈련 세트 정확도 저장
    train_accuracy.append(clf.score(X_train, y_train))
    # 일반화 정확도 저장
    test_accuracy.append(clf.score(X_test, y_test))

plt.plot(neighbors_settings, train_accuracy, label="training accuracy")
plt.plot(neighbors_settings, test_accuracy, label="test accuracy")
plt.ylabel("accuracy")
plt.xlabel("n_neighbors")
plt.legend()

plt.show()

cancerDatasetwithComplexandgeneralization