generated from LufsX/Experiment-LogReg
115 lines
3.5 KiB
Python
115 lines
3.5 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 = "202210423213"
|
|
name = "熊浩燃"
|
|
|
|
def sigmoid(z):
|
|
return 1 / (1 + np.exp(-z))
|
|
|
|
def standardize(X):
|
|
""" 数据标准化:均值为0,标准差为1 """
|
|
return (X - np.mean(X, axis=0)) / (np.std(X, axis=0) + 1e-8) # 避免除零
|
|
|
|
def train_logreg(X, y, learning_rate=0.0005, iterations=3000, batch_size=32, lambda_=0.05):
|
|
"""
|
|
对率回归训练函数,包含批量梯度下降和L2正则化。
|
|
|
|
Args:
|
|
- X (numpy array): 特征数据。
|
|
- y (numpy array): 标签数据。
|
|
- learning_rate (float): 学习率。
|
|
- iterations (int): 迭代次数。
|
|
- batch_size (int): 每次更新的样本数。
|
|
- lambda_ (float): L2正则化项的系数。
|
|
|
|
Returns:
|
|
- numpy array: 训练得到的权重。
|
|
"""
|
|
X = standardize(X) # 使用标准化数据
|
|
m, n = X.shape
|
|
weights = np.random.rand(n) * 0.01 # 初始化权重为小的随机数
|
|
|
|
for _ in range(iterations):
|
|
# 确保 batch_size 不超过 m
|
|
effective_batch_size = min(batch_size, m)
|
|
|
|
# 随机选择一个小批量
|
|
indices = np.random.choice(m, effective_batch_size, replace=False)
|
|
X_batch = X[indices]
|
|
y_batch = y[indices]
|
|
|
|
# 计算预测和梯度
|
|
z = np.dot(X_batch, weights)
|
|
h = sigmoid(z)
|
|
gradient = np.dot(X_batch.T, (h - y_batch)) / effective_batch_size + lambda_ * weights
|
|
weights -= learning_rate * gradient
|
|
|
|
return weights
|
|
|
|
def predict_logreg(inX, weights):
|
|
"""
|
|
对率回归预测函数。
|
|
|
|
Args:
|
|
- inX (numpy array): 输入待分类的样本。
|
|
- weights (numpy array): 训练得到的权重。
|
|
|
|
Returns:
|
|
- int: 预测的分类标签。
|
|
"""
|
|
probability = sigmoid(np.dot(inX, weights))
|
|
return 1 if probability >= 0.5 else 0
|
|
|
|
def load_data(filepath):
|
|
"""
|
|
从文件中加载数据,若不自行正确实现,则无法通过评测,**不记录成绩**。
|
|
|
|
Args:
|
|
- filepath (str): 数据文件路径。
|
|
|
|
Returns:
|
|
- np.array: 特征数据。
|
|
- np.array: 标签数据。
|
|
"""
|
|
data = []
|
|
labels = []
|
|
with open(filepath, 'r') as file:
|
|
for line in file:
|
|
line_data = line.strip().split()
|
|
if '?' not in line_data: # 忽略缺失值的行
|
|
data.append([float(x) for x in line_data[:-1]])
|
|
labels.append(int(float(line_data[-1])))
|
|
return np.array(data), np.array(labels)
|
|
|
|
if __name__ == "__main__":
|
|
# 测试数据加载和模型训练预测
|
|
X_train, y_train = load_data("./data/horse-colic.data")
|
|
X_test, y_test = load_data("./data/horse-colic.test")
|
|
|
|
# 训练对率回归模型
|
|
weights = train_logreg(X_train, y_train, learning_rate=0.0005, iterations=3000, batch_size=32, lambda_=0.05)
|
|
|
|
# 测试单个数据
|
|
y_pred = predict_logreg(X_test[11], weights)
|
|
print(f"预测结果: {y_pred}, 实际结果: {y_test[11]}")
|