18.网格搜索

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

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

0.9916666666666667

Grid Search

para_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)]
    }
]
#para_grid是一个数组，其中每个元素是一个字典，每一个字典就是需要进行的一组网格搜索
#每一组网格搜索要列出相应参数的取值范围
#z字典的键是参数名称，值是一个列表，存放参数所有可能的取值范围

knn_clf = KNeighborsClassifier()

from sklearn.model_selection import GridSearchCV

grid_search = GridSearchCV(knn_clf,para_grid)
#传入的参数表示对哪个算法进行网格搜索以及网格搜索的参数

%%time
grid_search.fit(X_train, y_train)

Wall time: 33.1 s
GridSearchCV(cv='warn', error_score='raise-deprecating',
estimator=KNeighborsClassifier(algorithm='auto', leaf_size=30,
metric='minkowski',
metric_params=None, n_jobs=None,
n_neighbors=5, p=2,
weights='uniform'),
iid='warn', n_jobs=None,
param_grid=[{'n_neighbors': [1, 2, 3, 4, 5, 6, 7, 8, 9, 10],
'weights': ['uniform']},
{'n_neighbors': [1, 2, 3, 4, 5, 6, 7, 8, 9, 10],
'p': [1, 2, 3, 4, 5], 'weights': ['distance']}],
pre_dispatch='2*n_jobs', refit=True, return_train_score=False,
scoring=None, verbose=0)

grid_search.best_estimator_
#返回值即 对该分类器进行网格搜索的最佳参数

KNeighborsClassifier(algorithm='auto', leaf_size=30, metric='minkowski',
metric_params=None, n_jobs=None, n_neighbors=3, p=3,
weights='distance')

grid_search.best_score_
#对应的准确度，因为对算法的评判标准是多种的，可能这里的准确度不如之前的高

0.9853862212943633

grid_search.best_params_
#对于我们所搜索的数组而言，最佳的参数

#将最佳参数传给分类器
knn_clf = grid_search.best_estimator_

#使用最佳参数的kNN分类器的结果
knn_clf.score(X_test, y_test)

0.9833333333333333

%time
grid_search = GridSearchCV(knn_clf,para_grid, n_jobs = -1, verbose = 2)
#n_jobs代表调用cpu的核心数，默认值是1，-1表示调用全部核心
#verbose表示在搜索过程中的输出信息，是一个整数，一般用2
grid_search.fit(X_train, y_train)

Wall time: 0 ns
Fitting 3 folds for each of 60 candidates, totalling 180 fits
[Parallel(n_jobs=-1)]: Using backend LokyBackend with 12 concurrent workers.
[Parallel(n_jobs=-1)]: Done 17 tasks | elapsed: 2.8s
[Parallel(n_jobs=-1)]: Done 138 tasks | elapsed: 7.3s
[Parallel(n_jobs=-1)]: Done 180 out of 180 | elapsed: 9.0s finished
GridSearchCV(cv='warn', error_score='raise-deprecating',
estimator=KNeighborsClassifier(algorithm='auto', leaf_size=30,
metric='minkowski',
metric_params=None, n_jobs=None,
n_neighbors=3, p=3,
weights='distance'),
iid='warn', n_jobs=-1,
param_grid=[{'n_neighbors': [1, 2, 3, 4, 5, 6, 7, 8, 9, 10],
'weights': ['uniform']},
{'n_neighbors': [1, 2, 3, 4, 5, 6, 7, 8, 9, 10],
'p': [1, 2, 3, 4, 5], 'weights': ['distance']}],
pre_dispatch='2*n_jobs', refit=True, return_train_score=False,
scoring=None, verbose=2)