优化这段代码：import pandas as pd import numpy as np from sklearn.ensemble import RandomForestClassifier from sklearn.feature_selection import SelectKBest, f_classif from sklearn.model_selection import train_test_split, GridSearchCV from sklearn.metrics import accuracy_score # 读取Excel文件 data = pd.read_excel("output.xlsx") # 提取特征和标签 features = data.iloc[:, 1:].values labels = np.where(data.iloc[:, 0] > 59, 1, 0) # 特征选择 selector = SelectKBest(score_func=f_classif, k=11) selected_features = selector.fit_transform(features, labels) # 划分训练集和测试集 X_train, X_test, y_train, y_test = train_test_split(selected_features, labels, test_size=0.2, random_state=42) # 创建随机森林分类器 rf_classifier = RandomForestClassifier() # 定义要调优的参数范围 param_grid = { 'n_estimators': [50, 100, 200], # 决策树的数量 'max_depth': [None, 5, 10], # 决策树的最大深度 'min_samples_split': [2, 5, 10], # 拆分内部节点所需的最小样本数 'min_samples_leaf': [1, 2, 4] # 叶节点上所需的最小样本数 } # 使用网格搜索进行调优 grid_search = GridSearchCV(rf_classifier, param_grid, cv=5) grid_search.fit(X_train, y_train) # 输出最佳参数组合和对应的准确率 print("最佳参数组合：", grid_search.best_params_) print("最佳准确率：", grid_search.best_score_) # 使用最佳参数组合训练模型 best_rf_classifier = grid_search.best_estimator_ best_rf_classifier.fit(X_train, y_train) # 预测 y_pred = best_rf_classifier.predict(X_test) # 计算准确率 accuracy = accuracy_score(y_test, y_pred) # 打印最高准确率分类结果 print("最高准确率分类结果：", accuracy)

优化后的代码如下：

import pandas as pd
import numpy as np
from sklearn.ensemble import RandomForestClassifier
from sklearn.feature_selection import SelectKBest, f_classif
from sklearn.model_selection import train_test_split, GridSearchCV
from sklearn.metrics import accuracy_score

def optimize_classifier():
    # 读取Excel文件
    data = pd.read_excel("output.xlsx")

    # 提取特征和标签
    features = data.iloc[:, 1:].values
    labels = np.where(data.iloc[:, 0] > 59, 1, 0)

    # 特征选择
    selector = SelectKBest(score_func=f_classif, k=11)
    selected_features = selector.fit_transform(features, labels)

    # 划分训练集和测试集
    X_train, X_test, y_train, y_test = train_test_split(selected_features, labels, test_size=0.2, random_state=42)

    # 创建随机森林分类器
    rf_classifier = RandomForestClassifier()

    # 定义要调优的参数范围
    param_grid = {
        'n_estimators': [50, 100, 200],  # 决策树的数量
        'max_depth': [None, 5, 10],  # 决策树的最大深度
        'min_samples_split': [2, 5, 10],  # 拆分内部节点所需的最小样本数
        'min_samples_leaf': [1, 2, 4]  # 叶节点上所需的最小样本数
    }

    # 使用网格搜索进行调优
    grid_search = GridSearchCV(rf_classifier, param_grid, cv=5)
    grid_search.fit(X_train, y_train)

    # 输出最佳参数组合和对应的准确率
    print("最佳参数组合：", grid_search.best_params_)
    print("最佳准确率：", grid_search.best_score_)

    # 使用最佳参数组合训练模型
    best_rf_classifier = grid_search.best_estimator_
    best_rf_classifier.fit(X_train, y_train)

    # 预测
    y_pred = best_rf_classifier.predict(X_test)

    # 计算准确率
    accuracy = accuracy_score(y_test, y_pred)

    # 打印最高准确率分类结果
    print("最高准确率分类结果：", accuracy)

optimize_classifier()

这里将代码包装在一个函数`optimize_classifier()`中，使其更加模块化和可重用。