5.20打卡

@浙大疏锦行

DAY 31 文件的规范拆分和写法

知识点回顾

1.  规范的文件命名

2.  规范的文件夹管理

3.  机器学习项目的拆分

4.  编码格式和类型注解

作业：尝试针对之前的心脏病项目，准备拆分的项目文件，思考下哪些部分可以未来复用。

预处理：

import pandas as pd
import numpy as np
from typing import Tuple, Dict

def load_data(file_path: str) -> pd.DataFrame:
    """加载数据文件

    Args:
        file_path: 数据文件路径

    Returns:
        加载的数据框
    """
    return pd.read_csv(file_path)


def handle_missing_values(data: pd.DataFrame) -> pd.DataFrame:
    """处理缺失值

    Args:
        data: 包含缺失值的数据框

    Returns:
        处理后的数据框
    """
    data_clean = data.copy()
    continuous_features = data.select_dtypes(include=['int64', 'float64']).columns.tolist()
    
    for feature in continuous_features:
        mode_value = data[feature].mode()[0]
        data_clean[feature].fillna(mode_value, inplace=True)
    
    return data_clean

if __name__ == "__main__":
    # 测试代码
    data = load_data(r"C:\Users\wangzhikai\Desktop\python60-days-challenge-master\day31练习\data\raw\heart.csv")
    data_clean = handle_missing_values(data)
    print("数据预处理完成！") 

训练：

# -*- coding: utf-8 -*-

import sys
import os
sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))

from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import train_test_split
from sklearn.metrics import classification_report, confusion_matrix
import time
import joblib # 用于保存模型
from typing import Tuple # 用于类型注解

from data.preprocessing import load_data,handle_missing_values

def prepare_data() -> Tuple:
    """准备训练数据

    Returns:
        训练集和测试集的特征和标签
    """
    # 加载和预处理数据
    data = load_data(r"C:\Users\wangzhikai\Desktop\python60-days-challenge-master\day31练习\data\raw\heart.csv")
    data_clean = handle_missing_values(data)
    
    # 分离特征和标签
    X = data_clean.drop(['target'], axis=1)
    y = data_clean['target']
    
    # 划分训练集和测试集
    X_train, X_test, y_train, y_test = train_test_split(
        X, y, test_size=0.2, random_state=42
    )
    
    return X_train, X_test, y_train, y_test

def train_model(X_train, y_train, model_params=None) -> RandomForestClassifier:
    """训练随机森林模型

    Args:
        X_train: 训练特征
        y_train: 训练标签
        model_params: 模型参数字典

    Returns:
        训练好的模型
    """
    if model_params is None:
        model_params = {'random_state': 42}
    
    model = RandomForestClassifier(**model_params)
    model.fit(X_train, y_train)
    return model

def evaluate_model(model, X_test, y_test) -> None:
    """评估模型性能

    Args:
        model: 训练好的模型
        X_test: 测试特征
        y_test: 测试标签
    """
    y_pred = model.predict(X_test)
    print("\n分类报告：")
    print(classification_report(y_test, y_pred))
    print("\n混淆矩阵：")
    print(confusion_matrix(y_test, y_pred))

def save_model(model, model_path: str) -> None:
    """保存模型

    Args:
        model: 训练好的模型
        model_path: 模型保存路径
    """
    os.makedirs(os.path.dirname(model_path), exist_ok=True)
    joblib.dump(model, model_path)
    print(f"\n模型已保存至: {model_path}")

if __name__ == "__main__":
    # 准备数据
    X_train, X_test, y_train, y_test = prepare_data()
    
    # 记录开始时间
    start_time = time.time()
    
    # 训练模型
    model = train_model(X_train, y_train)
    
    # 记录结束时间
    end_time = time.time()
    print(f"\n训练耗时: {end_time - start_time:.4f} 秒")
    
    # 评估模型
    evaluate_model(model, X_test, y_test)
    
    # 保存模型
    save_model(model, "models/random_forest_model.joblib") 

可视化：

import matplotlib.pyplot as plt
import seaborn as sns
import shap
import numpy as np
from typing import Any

def plot_feature_importance_shap(model: Any, X_test, save_path: str = None) -> None:
    """绘制SHAP特征重要性图

    Args:
        model: 训练好的模型
        X_test: 测试数据
        save_path: 图片保存路径
    """
    # 初始化SHAP解释器
    explainer = shap.TreeExplainer(model)
    shap_values = explainer.shap_values(X_test)
    
    # 绘制特征重要性条形图
    plt.figure(figsize=(12, 8))
    shap.summary_plot(shap_values[:, :, 0], X_test, plot_type="bar", show=False)
    plt.title("SHAP特征重要性")
    
    if save_path:
        plt.savefig(save_path)
        print(f"特征重要性图已保存至: {save_path}")
    plt.show()

def plot_confusion_matrix(y_true, y_pred, save_path: str = None) -> None:
    """绘制混淆矩阵热力图

    Args:
        y_true: 真实标签
        y_pred: 预测标签
        save_path: 图片保存路径
    """
    plt.figure(figsize=(8, 6))
    cm = confusion_matrix(y_true, y_pred)
    sns.heatmap(cm, annot=True, fmt='d', cmap='Blues')
    plt.title('混淆矩阵')
    plt.ylabel('真实标签')
    plt.xlabel('预测标签')
    
    if save_path:
        plt.savefig(save_path)
        print(f"混淆矩阵图已保存至: {save_path}")
    plt.show()

def set_plot_style():
    """设置绘图样式"""
    plt.style.use('seaborn')
    plt.rcParams['font.sans-serif'] = ['SimHei']
    plt.rcParams['axes.unicode_minus'] = False

if __name__ == "__main__":
    # 设置绘图样式
    set_plot_style()
    
    # 这里可以添加测试代码
    print("可视化模块加载成功！")