generated from LufsX/Experiment-LogReg
93 lines
3.1 KiB
Python
93 lines
3.1 KiB
Python
# function.py
|
|
import numpy as np
|
|
|
|
"""
|
|
实验说明:
|
|
- 自行编写实现数据加载与预测病马死亡的对率回归算法。
|
|
|
|
注意事项:
|
|
- 在 function.py 中实现对率回归算法。
|
|
- 可以自行导入其他库,需要在 requirements.txt 添加依赖,若未在 requirements.txt 中添加使用到的依赖,则无法自动评测,成绩为零。
|
|
- 自动评测脚本仅会加载 train_logreg、predict_logreg 和 load_data 函数,请勿修改函数名。
|
|
|
|
测评环境:
|
|
- CPU: Intel Xeon(R) CPU E3-1231 v3 @ 3.40GHz
|
|
- OS: Ubuntu 22.04.4 LTS
|
|
- Python: 3.10.12
|
|
- numpy: 2.1.1
|
|
"""
|
|
|
|
|
|
"""
|
|
请在这里填写学号和姓名,不填写即成绩无效。
|
|
"""
|
|
id = "202210423102"
|
|
name = "周佳成"
|
|
|
|
|
|
# 这里写自己的代码实现
|
|
import pandas as pd
|
|
import requests
|
|
|
|
# 下载病马数据集
|
|
def download_horse_colic_data(url, filename):
|
|
response = requests.get(url)
|
|
with open(filename, 'wb') as f:
|
|
f.write(response.content)
|
|
|
|
# 处理并加载数据
|
|
def load_and_preprocess_horse_colic_data(train_filename, test_filename):
|
|
# 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
|
|
]
|
|
|
|
# 读取训练数据
|
|
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)
|
|
|
|
# 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)
|
|
for column in train_data.columns[:-1]: # 排除目标变量列
|
|
train_data[column].fillna(0, inplace=True)
|
|
for column in test_data.columns[:-1]: # 排除目标变量列
|
|
test_data[column].fillna(0, inplace=True)
|
|
|
|
# 处理目标变量'outcome'的缺失值
|
|
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)
|
|
|
|
# 将目标变量'outcome'转换为数值型
|
|
train_data['outcome'] = train_data['outcome'].astype(int)
|
|
test_data['outcome'] = test_data['outcome'].astype(int)
|
|
|
|
return train_data, test_data
|
|
|
|
# 主函数
|
|
def main():
|
|
# 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'
|
|
|
|
# 保存数据集的文件名
|
|
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()
|