Python遇见机器学习 ---- k近邻（kNN）算法(三）

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)
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)
# Out[4]:
# 0.98611111111111116

best_score = 0.0
best_k = -1
for k in range(1, 11): # 搜索1到10中最好的k，分别创建k等于不同值时的分类器，用score方法评判
    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= 7 
# best_score= 0.988888888889

%%time
best_p = -1
best_score = 0.0
best_k = -1​
for k in range(1, 11): # 搜索1到10中最好的k
    for p in range(1, 6): # 距离参数
        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_score = score
            best_p = p
print("best_p=", best_p)
print("best_k=", best_k)
print("best_score=", best_score)
# best_p= 2 
# best_k= 1 
# best_score= 0.994444444444 
# CPU times: user 15.3 s, sys: 51.5 ms, total: 15.4 s Wall time: 15.5 s

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)
# Out[4]:
# 0.98888888888888893

# 定义网格参数，每个字典写上要遍历的参数的取值集合
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()
# 导入网格搜索方法（此方法使用交叉验证CV）
from sklearn.model_selection import GridSearchCV
grid_search = GridSearchCV(knn_clf, param_grid)
%%time
grid_search.fit(X_train, y_train)
# CPU times: user 2min 2s, sys: 320 ms, total: 2min 2s Wall time: 2min 3s
"""
GridSearchCV(cv=None, error_score='raise', estimator=KNeighborsClassifier(algorithm='auto', leaf_size=30, metric='minkowski', 
metric_params=None, n_jobs=1, n_neighbors=5, p=2, weights='uniform'), 
fit_params=None, iid=True, n_jobs=1, param_grid=[{'weights': ['uniform'], 
'n_neighbors': [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]}, {'weights': ['distance'], 
'n_neighbors': [1, 2, 3, 4, 5, 6, 7, 8, 9, 10], 'p': [1, 2, 3, 4, 5]}], 
pre_dispatch='2*n_jobs', refit=True, return_train_score='warn', scoring=None, 
verbose=0)
"""
grid_search.best_estimator_ # 返回最好的分类器，（变量名最后带一个下划线是因为这是根据用户输入所计算出来的）
"""
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_ # 最好方法的准确率
# Out[11]:
# 0.98538622129436326
grid_search.best_params_ # 最优方法的对应参数
# Out[12]:
# {'n_neighbors': 3, 'p': 3, 'weights': 'distance'}
knn_clf = grid_search.best_estimator_
knn_clf.score(X_test, y_test)
# Out[14]:
# 0.98333333333333328
%%time
grid_search = GridSearchCV(knn_clf, param_grid, n_jobs=-1, verbose=2) # n_jobs采用多少核,verbose：执行时输出，整数越大，信息越详细
grid_search.fit(X_train, y_train)