更新 function.py

function.py

@@ -21,45 +21,72 @@ import numpy as np
 """
 请在这里填写学号和姓名，不填写即成绩无效。
 """
-id = "202210423xxx"
+id = "202210423102"
-name = "test_name"
+name = "周佳成"
 
 
 # 这里写自己的代码实现
 import pandas as pd
-from sklearn.model_selection import train_test_split
+import requests
-from sklearn.linear_model import LinearRegression
-from sklearn.metrics import mean_squared_error, r2_score
 
-# 数据加载
+# 下载病马数据集
-data_path = 'data/your_dataset.csv'  # 替换为实际数据集路径
+def download_horse_colic_data(url, filename):
-data = pd.read_csv(data_path)
+    response = requests.get(url)
+    with open(filename, 'wb') as f:
+        f.write(response.content)
 
-# 数据预处理
+# 处理并加载数据
-# 检查缺失值
+def load_and_preprocess_horse_colic_data(train_filename, test_filename):
-print(data.isnull().sum())
+    # 定义列名
+    column_names = [
+        'surgery', 'age', 'hospital_number', 'rectal_temperature',
+        # ... 其他列名可以根据需要添加
+        'outcome'  # 假设'outcome'是目标变量，1=lived, 2=died, 3=euthanized
+    ]
 
-# 填补缺失值（可以选择不同策略）
+    # 读取训练数据
-data.fillna(data.mean(), inplace=True)
+    train_data = pd.read_csv(train_filename, delim_whitespace=True, header=None, names=column_names)
+    # 读取测试数据
+    test_data = pd.read_csv(test_filename, delim_whitespace=True, header=None, names=column_names)
 
-# 特征选择
+    # 处理缺失值：用0填充（这里假设除了'outcome'之外的所有特征都可能有缺失值）
-features = ['age', 'health_condition', 'treatment_effectiveness']
+    for column in train_data.columns[:-1]:  # 排除目标变量列
-X = data[features]
+        train_data[column].fillna(0, inplace=True)
-y = data['mortality_rate']
+    for column in test_data.columns[:-1]:  # 排除目标变量列
+        test_data[column].fillna(0, inplace=True)
 
-# 数据集划分
+    # 处理目标变量'outcome'的缺失值
-X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+    train_data['outcome'].fillna(0, inplace=True)  # 可以选择适合的填充方法
+    test_data['outcome'].fillna(0, inplace=True)
 
-# 模型构建
+    # 将目标变量'outcome'转换为数值型
-model = LinearRegression()
+    train_data['outcome'] = train_data['outcome'].astype(int)
-model.fit(X_train, y_train)
+    test_data['outcome'] = test_data['outcome'].astype(int)
 
-# 预测
+    return train_data, test_data
-y_pred = model.predict(X_test)
 
-# 模型评估
+# 主函数
-mse = mean_squared_error(y_test, y_pred)
+def main():
-r2 = r2_score(y_test, y_pred)
+    # 数据集URL
+    train_url = 'http://archive.ics.uci.edu/ml/machine-learning-databases/horse-colic/horse-colic.data'
+    test_url = 'http://archive.ics.uci.edu/ml/machine-learning-databases/horse-colic/horse-colic-test.data'
     
-print(f'Mean Squared Error: {mse}')
+    # 保存数据集的文件名
-print(f'R^2 Score: {r2}')
+    train_filename = 'horse_colic_train.data'
+    test_filename = 'horse_colic_test.data'
+    
+    # 下载数据集
+    download_horse_colic_data(train_url, train_filename)
+    download_horse_colic_data(test_url, test_filename)
+    
+    # 加载并预处理数据
+    train_data, test_data = load_and_preprocess_horse_colic_data(train_filename, test_filename)
+    
+    # 打印前几行数据以验证
+    print("训练数据预览：")
+    print(train_data.head())
+    print("测试数据预览：")
+    print(test_data.head())
+
+if __name__ == "__main__":
+    main()