题目：基于 Scikit-learn 实现乳腺癌数据集预测 pipeline 要求：补全代码，完成从加载数据、划分数据集、数据归一化到模型网格搜索寻找最优 $K$ 值的 完整流程。 import numpy as np from sklearn.datasets import load_breast_cancer from sklearn.model_selection import train_test_split, GridSearchCV from sklearn.neighbors import KNeighborsClassifier from sklearn.preprocessing import StandardScaler # 1. 加载乳腺癌数据集 data = load_breast_cancer() X, y = data.data, data.target # 2. 划分数据集 (测试集占比 20%, 不洗牌以符合材料示例) X_train, X_test, y_train, y_test = train_test_split(X, y, test_size= 0.2 , shuffle= False ) # 3. 数据归一化 (请使用均值方差归一化) scaler = # [补全代码] # 计算训练集均值标准差并转换 X_train_scaled = scaler.fit_transform(X_train) # 使用相同参数转换测试集 X_test_scaled = # [补全代码] # 4. 设置网格搜索参数 (K值范围: 1-10; 权重: uniform, distance) param_grid = [ { 'n_neighbors' : [i for i in range ( 1 , 11 )], 'weights' : # [补全代码] } ] # 5. 执行网格搜索与交叉验证 (使用 KNeighborsClassifier) knn_clf = KNeighborsClassifier() grid_search = # [补全代码] (estimator=knn_clf, param_grid=param_grid, cv=5) grid_search.fit(X_train_scaled, y_train) # 6. 输出结果 print( "最优参数:" , grid_search.best_params_) print( "最优得分:" , grid_search.best_score_) print( "测试集准确率:" , grid_search.score(X_test_scaled, y_test))