KNN调参

from math import sqrt
from sklearn import metrics
import numpy as np
import datetime
from sklearn.neighbors import KNeighborsClassifier
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
from sklearn.model_selection import train_test_split
from sklearn.decomposition import PCA
from sklearn import svm
from sklearn.model_selection import GridSearchCV  # CV，使用交叉验证方式获得模型正确率

# 输入数据路径
data_path = '1rong特征.csv'  # 数据

data = np.loadtxt(open(data_path, 'rb'), dtype=np.float64, delimiter=',', skiprows=1)

# 划分数据标签
cols = data.shape[1]
X = data[:, :-1]

y = data[:, cols - 1:cols]
y = np.array(y.ravel())  # 数列平铺
y = np.squeeze(y)
print("X_filtered", X.shape)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=1)  # 测试集占比1/3
param_grid = [
    {  # 需遍历10次
        'weights': ['uniform'],  # 参数取值范围
        'n_neighbors': [i for i in range(1, 11)]  # 使用其他方式如np.arange()也可以
        # 这里没有p参数
    },
    {  # 需遍历50次
        'weights': ['distance'],
        'n_neighbors': [i for i in range(1, 11)],
        'p': [i for i in range(1, 6)]
    }
]
knn_clf = KNeighborsClassifier()  # 默认参数，创建空分类器



grid_search = GridSearchCV(knn_clf, param_grid, cv=5)  # 网格搜索参数

grid_search.fit(X_train, y_train)  # 网格搜索训练模型，比较耗时，约4分钟

print("Best parameters found: ", grid_search.best_params_)
print("Best cross-validation score: ", grid_search.best_score_)