generated from LufsX/Experiment-LogReg
118 lines
3.3 KiB
Python
118 lines
3.3 KiB
Python
# function.py
|
|
import numpy as np
|
|
from sklearn.preprocessing import StandardScaler
|
|
|
|
"""
|
|
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 = "202210423117"
|
|
name = "程悦"
|
|
|
|
def sigmoid(z):
|
|
return 1.0 / (1 + np.exp(-z))
|
|
|
|
def train_logreg(X, y, learning_rate=0.01, iterations=1000):
|
|
"""
|
|
对率回归训练函数。
|
|
|
|
Args:
|
|
- X (numpy array): 特征数据。
|
|
- y (numpy array): 标签数据。
|
|
|
|
Returns:
|
|
- numpy array: 训练得到的权重。
|
|
"""
|
|
m, n = X.shape
|
|
weights = np.zeros(n)
|
|
for i in range(iterations):
|
|
z = np.dot(X, weights)
|
|
h = sigmoid(z)
|
|
gradient = np.dot(X.T, (h - y)) / m
|
|
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。
|
|
"""
|
|
z = np.dot(inX, weights)
|
|
h = sigmoid(z)
|
|
return 1 if h > 0.5 else 0
|
|
|
|
def load_data(filepath):
|
|
"""
|
|
从文件中加载数据，填充缺失值，并进行特征处理。
|
|
|
|
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 f:
|
|
lines = f.readlines()
|
|
for line in lines:
|
|
line = line.strip().split()
|
|
if len(line) >= 1 and line[-1].isdigit():
|
|
# 将缺失值 '?' 填充为 0，并转换为浮点数
|
|
line_data = [1] + [0 if x == '?' else float(x) for x in line[:-1]]
|
|
data.append(line_data)
|
|
labels.append(int(line[-1]))
|
|
|
|
data = np.array(data)
|
|
labels = np.array(labels)
|
|
|
|
# 选择特征，合并目标变量
|
|
target_variable = labels
|
|
target_variable[(target_variable == 2) | (target_variable == 3)] = 0 # 合并死亡和安乐死为0
|
|
|
|
# 去掉特征3和特征24~28
|
|
data = np.delete(data, [2] + list(range(23, 28)), axis=1) # 特征3的索引是2，特征24-28的索引是23-27
|
|
|
|
scaler = StandardScaler()
|
|
data = scaler.fit_transform(data)
|
|
|
|
return data, target_variable
|
|
|
|
if __name__ == "__main__":
|
|
# 以下代码可用于测试，可自行随意修改
|
|
# 加载训练集
|
|
X_train, y_train = load_data("./data/horse-colic.data")
|
|
|
|
# 加载测试集
|
|
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=0.01, iterations=1000, re
|
|
='l1')
|
|
|
|
# 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]}") |