pythonK近邻算法（k-Nearest Neighbors，KNN）解决分类问题

# 导入必要的库 from sklearn.model_selection import cross_val_score, KFold from sklearn.svm import SVR from sklearn.model_selection import GridSearchCV, train_test_split import numpy as np import pandas as pd import matplotlib.pyplot as plt from matplotlib import pyplot # 创建样本数据 # X = np.array([[0, 0], [2, 2], [4, 4], [6, 6], [8, 8], [10, 10]]) # y = np.array([0, 2.3, 4.6, 6.9, 9.2, 11.5]) X = pd.read_excel('C:/Users/孙海涛/Desktop/k折/n/x.xlsx', sheet_name='Sheet1') # 读取数据 y = pd.read_excel('C:/Users/孙海涛/Desktop/k折/n/y.xlsx', sheet_name='Sheet1') # 读取数据 # 将数据集划分为训练集和测试集（留出法） X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42) # 定义需要使用的SVM模型 svr = SVR() # 创建k折交叉验证对象 kf = KFold(n_splits=3) # 定义超参数空间和网格搜索对象 param_grid = {'kernel': ['linear', 'rbf'], 'C': [0.1, 0.2,0.3,0.4,0.5,0.6,0.7,0.8,0.9,1.1,1.2,1.3,1.4,1.5,1.6,1.7,1.8,1.9,2], 'gamma': ['scale', 'auto']} grid_search = GridSearchCV(svr, param_grid, cv=kf) # 在训练集上使用网格搜索进行超参数寻优 grid_search.fit(X_train, y_train) # 输出最佳超参数组合和在测试集上的性能指标 print("Best parameters:", grid_search.best_params_) print("Test score: %.2f" % grid_search.score(X_test, y_test)) # Best parameters: {'C': 0.6, 'gamma': 'scale', 'kernel': 'rbf'} # Test score: -0.20 #优化后的基模型 # print(grid_search.best_params_['kernel']) model_svr = SVR(C=grid_search.best_params_['C'], kernel=grid_search.best_params_['kernel'], gamma=grid_search.best_params_['gamma']) model_svr.fit(X_train, y_train) predict_results = model_svr.predict(X_test) print(len(predict_results))#10 dat = [] for i in range(1, 11): dat.append(i) # plt.xlim(0, 160) # 限定横轴的范围 palette = pyplot.get_cmap('Set1') # plt.scatter(y_test, predict_results) plt.plot(dat, y_test, color=palette(3), marker='*', label='True') plt.plot(dat, predict_results, color=palette(1), marker='^', label='Predict') plt.xticks(size=15) plt.yticks(size=15) plt.legend() # 让图例生效 # plt.show() plt.show()