generated from LufsX/Experiment-LogReg
89 lines
2.9 KiB
Python
89 lines
2.9 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 = "202210423217"
|
|
name = "吴俊煯"
|
|
|
|
|
|
# 这里写自己的代码实现
|
|
def train_logreg(X, y, learning_rate=0.1, iterations=100):
|
|
m, n = X.shape
|
|
weights = np.zeros(n)
|
|
bias = 0
|
|
|
|
for _ in range(iterations):
|
|
for idx, x_i in enumerate(X):
|
|
linear_output = np.dot(x_i, weights) + bias
|
|
y_predicted = 1 / (1 + np.exp(-linear_output))
|
|
|
|
# 计算误差
|
|
error = y[idx] - y_predicted
|
|
|
|
# 更新权重和偏置
|
|
weights += learning_rate * error * x_i
|
|
bias += learning_rate * error
|
|
|
|
return weights
|
|
|
|
def predict_logreg(inX, weights):
|
|
linear_output = np.dot(inX, weights)
|
|
y_predicted = 1 / (1 + np.exp(-linear_output))
|
|
|
|
# 将输出转换为分类标签
|
|
return 1 if y_predicted >= 0.5 else 0
|
|
|
|
# 这里也写自己的代码实现
|
|
def load_data(filepath):
|
|
data = []
|
|
with open(filepath, 'r') as file:
|
|
for line in file:
|
|
# 分割行,并去除任何可能的空白字符
|
|
parts = [part.strip() for part in line.split()]
|
|
# 将缺失值'?'替换为0(或者你可以选择其他适当的处理方式)
|
|
features = [float(part) if part != '?' else 0 for part in parts[:-1]]
|
|
# 将标签从2转换为1(如果原始标签是1和2的话)
|
|
label = int(parts[-1]) - 1 # 假设原始标签是1和2,转换为0和1
|
|
data.append(features + [label])
|
|
|
|
# 将数据转换为numpy数组
|
|
data_array = np.array(data)
|
|
|
|
# 分离特征和标签
|
|
X = data_array[:, :-1] # 所有行,除了最后一列
|
|
y = data_array[:, -1] # 所有行的最后一列
|
|
|
|
return X, y
|
|
|
|
if __name__ == "__main__":
|
|
# 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)
|
|
|
|
# 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]}") |