KNN算法2-性能测试与超参数的寻找

scikit-learn中的accuracy_score

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)
y_predict = knn_clf.predict(X_test)

from sklearn.metrics import accuracy_score
accuracy_score(y_test, y_predict)

knn_clf.score(X_test, y_test)

超参数

import numpy as np
from sklearn import datasets
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)

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 = 4
best_score = 0.991666666667

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 = 4
best_score = 0.991666666667

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)

0.98333333333333328

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 = 0.988888888889

Grid Search

param_grid = [
    {
        'weights': ['uniform'], 
        'n_neighbors': [i for i in range(1, 11)]
    },
    {
        'weights': ['distance'],
        'n_neighbors': [i for i in range(1, 11)], 
        'p': [i for i in range(1, 6)]
    }
]

knn_clf = KNeighborsClassifier()
from sklearn.model_selection import GridSearchCV

grid_search = GridSearchCV(knn_clf, param_grid)

%%time
grid_search.fit(X_train, y_train)

grid_search.best_estimator_
KNeighborsClassifier(algorithm='auto', leaf_size=30, metric='minkowski',
           metric_params=None, n_jobs=1, n_neighbors=3, p=3,
           weights='distance')
grid_search.best_score_
0.98538622129436326


grid_search.best_params_

knn_clf = grid_search.best_estimator_
knn_clf.score(x_test,y_test)

n_jobs,多核搜索

grid_search = GridSearchCV(knn_clf, param_grid, n_jobs=-1, verbose=2)
grid_search.fit(X_train, y_train)