generated from LufsX/Experiment-LogReg
114 lines
3.2 KiB
Python
114 lines
3.2 KiB
Python
# function.py
|
|
import numpy as np
|
|
import pandas as pd
|
|
from sklearn.preprocessing import StandardScaler
|
|
from sklearn.model_selection import train_test_split
|
|
|
|
|
|
"""
|
|
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 = "202210423130"
|
|
name = "董秋"
|
|
|
|
|
|
# 这里写自己的代码实现
|
|
def train_logreg(X, y, learning_rate=0.01, iterations=1000,lambda_reg=0.01):
|
|
"""
|
|
对率回归训练函数。
|
|
|
|
Args:
|
|
- X (numpy array): 特征数据。
|
|
- y (numpy array): 标签数据。
|
|
- other_params (str): 其它参数，可选设置。若需设置其它参数，必须设置其默认值，否则将**无法通过**自动评测，**成绩为零*。
|
|
|
|
Returns:
|
|
- numpy array: 训练得到的权重。
|
|
"""
|
|
m, n = X.shape
|
|
weights = np.zeros(n)
|
|
|
|
for _ in range(iterations):
|
|
z = np.dot(X, weights)
|
|
predictions = 1 / (1 + np.exp(-z))
|
|
gradient = np.dot(X.T, (predictions - y)) / m
|
|
|
|
# L2正则化
|
|
gradient += (lambda_reg / m) * 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。
|
|
"""
|
|
z = np.dot(inX, weights)
|
|
prediction_prob = 1 / (1 + np.exp(-z))
|
|
return 1 if prediction_prob >= 0.5 else 0
|
|
|
|
# 这里也写自己的代码实现
|
|
def load_data(filepath):
|
|
data = []
|
|
labels = []
|
|
|
|
with open(filepath, 'r') as f:
|
|
for line in f:
|
|
values = line.strip().replace('?', '0').split()
|
|
try:
|
|
values = [float(v) for v in values]
|
|
data.append(values[:-1]) # 特征
|
|
labels.append(values[-1]) # 标签
|
|
except ValueError:
|
|
continue
|
|
|
|
return np.array(data), np.array(labels)
|
|
|
|
def preprocess_data(X):
|
|
# 特征标准化
|
|
scaler = StandardScaler()
|
|
return scaler.fit_transform(X)
|
|
|
|
|
|
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,lambda_reg=0.01)
|
|
X_train, X_test, y_train, y_test = train_test_split(X_scaled, y, test_size=0.2, random_state=42)
|
|
|
|
# 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]}")
|