Day 31

尝试针对之前的心脏病项目ipynb，将他按照今天的示例项目整理成规范的形式，思考下哪些部分可以未来复用。

# src/data/data_loader.py
import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
 
def load_data(file_path: str) -> pd.DataFrame:
    """加载心脏病数据集"""
    try:
        df = pd.read_csv(file_path)
        return df
    except FileNotFoundError:
        print(f"错误: 文件 {file_path} 未找到")
        return None
 
def preprocess_data(df: pd.DataFrame) -> pd.DataFrame:
    """预处理心脏病数据集"""
    # 处理缺失值
    df = df.dropna()
    
    # 数据标准化/归一化
    # ...
    
    return df
 
def split_data(df: pd.DataFrame, target_col: str, test_size: float = 0.2, random_state: int = 42):
    """将数据分为训练集和测试集"""
    X = df.drop(target_col, axis=1)
    y = df[target_col]
    return train_test_split(X, y, test_size=test_size, random_state=random_state)

# src/features/feature_engineering.py
from sklearn.preprocessing import StandardScaler
 
def build_features(X_train, X_test):
    """构建和转换特征"""
    # 特征标准化
    scaler = StandardScaler()
    X_train_scaled = scaler.fit_transform(X_train)
    X_test_scaled = scaler.transform(X_test)
    
    # 特征选择/提取
    # ...
    
    return X_train_scaled, X_test_scaled, scaler

# src/models/model_training.py
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import classification_report, confusion_matrix
import joblib
 
def train_model(X_train, y_train):
    """训练随机森林分类器"""
    model = RandomForestClassifier(n_estimators=100, random_state=42)
    model.fit(X_train, y_train)
    return model
 
def evaluate_model(model, X_test, y_test):
    """评估模型性能"""
    y_pred = model.predict(X_test)
    print("分类报告:")
    print(classification_report(y_test, y_pred))
    
    print("混淆矩阵:")
    print(confusion_matrix(y_test, y_pred))
    
    return y_pred
 
def save_model(model, model_path: str):
    """保存模型到文件"""
    joblib.dump(model, model_path)
 
def load_model(model_path: str):
    """从文件加载模型"""
    return joblib.load(model_path)

@浙大疏锦行