generated from LufsX/Experiment-LogReg
96 lines
3.8 KiB
Python
96 lines
3.8 KiB
Python
# function.py
|
|
import numpy as np
|
|
from sklearn.preprocessing import StandardScaler
|
|
from sklearn.metrics import accuracy_score
|
|
"""
|
|
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=0.01, iterations=1000, lambda_reg=0.1):
|
|
m, n = X.shape
|
|
weights = np.zeros(n)
|
|
bias = 0
|
|
|
|
for _ in range(iterations):
|
|
linear_output = np.dot(X, weights) + bias
|
|
y_predicted = 1 / (1 + np.exp(-linear_output))
|
|
|
|
# 计算梯度(包括正则化项)
|
|
dw = (1 / m) * np.dot(X.T, (y_predicted - y)) + (lambda_reg / m) * weights
|
|
db = (1 / m) * np.sum(y_predicted - y)
|
|
|
|
# 更新权重和偏置
|
|
weights -= learning_rate * dw
|
|
bias -= learning_rate * db
|
|
|
|
return weights, bias
|
|
|
|
def predict_logreg(inX, weights, bias):
|
|
linear_output = np.dot(inX, weights) + bias
|
|
y_predicted = 1 if linear_output >= 0 else 0 # 简化阈值判断,因为已经通过sigmoid函数输出
|
|
# 注意:这里为了与原始代码保持一致,使用了0.5作为阈值,但实际上由于sigmoid输出范围在(0,1),可以直接比较linear_output和0
|
|
# return 1 if y_predicted >= 0.5 else 0 # 等价于上面的判断,但多余计算了sigmoid
|
|
return y_predicted
|
|
|
|
# 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:
|
|
parts = line.strip().split()
|
|
# 将缺失值'?'替换为np.nan,然后使用0填充(或选择其他适当的填充策略)
|
|
features = [float(part) if part != '?' else np.nan for part in parts[:-1]]
|
|
# 填充NaN值(这里选择0,但也可以考虑使用均值、中位数等)
|
|
features = np.nan_to_num(features, nan=0.0)
|
|
# 将标签从2转换为1(如果原始标签是1和2的话),这里假设标签已经是0和1
|
|
label = int(parts[-1]) # 假设标签已经是0和1,无需转换
|
|
data.append(features + [label])
|
|
|
|
data_array = np.array(data)
|
|
X = data_array[:, :-1]
|
|
y = data_array[:, -1]
|
|
|
|
# 特征缩放(标准化)
|
|
scaler = StandardScaler()
|
|
X_scaled = scaler.fit_transform(X)
|
|
|
|
return X_scaled, y
|
|
|
|
if __name__ == "__main__":
|
|
# 加载训练集和测试集
|
|
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, bias = train_logreg(X_train, y_train, learning_rate=0.01, iterations=1000, lambda_reg=0.1)
|
|
|
|
# 测试模型并评估性能
|
|
y_pred = [predict_logreg(x, weights, bias) for x in X_test]
|
|
accuracy = accuracy_score(y_test, y_pred)
|
|
print(f"模型准确率: {accuracy}")
|
|
|
|
# 打印单个测试样本的预测结果和实际结果(示例)
|
|
# 注意:索引11可能需要根据实际测试集调整,这里仅作为示例
|
|
sample_index = 11 # 假设要测试的样本索引是11(注意:索引可能需要根据实际数据调整)
|
|
print(f"预测结果: {y_pred[sample_index]}, 实际结果: {y_test[sample_index]}") |