超参数：在算法运行前需要决定的参数 模型参数：算法过程中学习的参数

KNN算法没有模型参数 KNN算法中的k是典型的超参数

import numpy as np
from sklearn import datasets

digits = datasets.load_digits()
X = digits.data
y = digits.target

from sklearn.model_selection import train_test_split

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=666)

from sklearn.neighbors import KNeighborsClassifier

knn_clf = KNeighborsClassifier(n_neighbors=3)
knn_clf.fit(X_train, y_train)
knn_clf.score(X_test, y_test)

0.9916666666666667

寻找最好的k

best_score = 0.0
best_k = -1
for k in range(1, 11):
    knn_clf = KNeighborsClassifier(n_neighbors=k)
    knn_clf.fit(X_train, y_train)
    score = knn_clf.score(X_test, y_test)
    if score > best_score:
        best_k = k
        best_score = score
        
print("best_k =", best_k)
print("best_score =", best_score)

best_k = 3
best_score = 0.9916666666666667

考虑距离？不考虑距离？

best_score = 0.0
best_k = -1
best_method = ""
for method in ["uniform", "distance"]:
    for k in range(1, 11):
        knn_clf = KNeighborsClassifier(n_neighbors=k, weights=method)
        knn_clf.fit(X_train, y_train)
        score = knn_clf.score(X_test, y_test)
        if score > best_score:
            best_k = k
            best_score = score
            best_method = method
        
print("best_method =", best_method)
print("best_k =", best_k)
print("best_score =", best_score)

best_method = uniform
best_k = 3
best_score = 0.9916666666666667

sk_knn_clf = KNeighborsClassifier(n_neighbors=4, weights="distance", p=1)
sk_knn_clf.fit(X_train, y_train)
sk_knn_clf.score(X_test, y_test)

0.9833333333333333

搜索明可夫斯基距离相应的p

best_score = 0.0
best_k = -1
best_p = -1

for k in range(1, 11):
    for p in range(1, 6):
        knn_clf = KNeighborsClassifier(n_neighbors=k, weights="distance", p=p)
        knn_clf.fit(X_train, y_train)
        score = knn_clf.score(X_test, y_test)
        if score > best_score:
            best_k = k
            best_p = p
            best_score = score
        
print("best_k =", best_k)
print("best_p =", best_p)
print("best_score =", best_score)

best_k = 3
best_p = 2
best_score = 0.9916666666666667