generated from LufsX/Experiment-LogReg
163 lines
4.6 KiB
Python
163 lines
4.6 KiB
Python
# function.py
|
|
import numpy as np
|
|
import random
|
|
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 = "202210423209"
|
|
name = "万子玉"
|
|
|
|
|
|
# 这里写自己的代码实现
|
|
def sigmoid(z):
|
|
return 1 / (1 + np.exp(-z))
|
|
|
|
def train_logreg(X, y, learning_rate=0.001, iterations=500, batch_size=16, initial_weights=None):
|
|
X = np.insert(X, 0, 1, axis=1) # 添加偏置项
|
|
if initial_weights is None:
|
|
weights = np.zeros(X.shape[1])
|
|
else:
|
|
weights = initial_weights
|
|
|
|
m = X.shape[0]
|
|
|
|
for _ in range(iterations):
|
|
indices = np.arange(m)
|
|
np.random.shuffle(indices)
|
|
X_shuffled = X[indices]
|
|
y_shuffled = y[indices]
|
|
|
|
for i in range(0, m, batch_size):
|
|
end = i + batch_size
|
|
X_batch = X_shuffled[i:end]
|
|
y_batch = y_shuffled[i:end]
|
|
z = np.dot(X_batch, weights)
|
|
h = sigmoid(z)
|
|
gradient = np.dot(X_batch.T, (h - y_batch)) / batch_size
|
|
weights -= learning_rate * gradient
|
|
|
|
return weights
|
|
|
|
"""
|
|
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。
|
|
"""
|
|
|
|
|
|
def predict_logreg(inX, weights):
|
|
inX = np.insert(inX, 0, 1) # 添加偏置项
|
|
z = np.dot(inX, weights)
|
|
h = sigmoid(z)
|
|
return 1 if h >= 0.5 else 0
|
|
|
|
|
|
"""
|
|
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。
|
|
"""
|
|
def evaluate_model(X_val, y_val, weights):
|
|
predictions = np.array([predict_logreg(x, weights) for x in X_val])
|
|
accuracy = np.mean(predictions == y_val)
|
|
return accuracy
|
|
|
|
def split_train_val(X, y, val_size=0.2):
|
|
shuffled_indices = list(range(X.shape[0]))
|
|
random.shuffle(shuffled_indices)
|
|
X_shuffled = X[shuffled_indices]
|
|
y_shuffled = y[shuffled_indices]
|
|
|
|
val_count = int(X.shape[0] * val_size)
|
|
|
|
X_val = X_shuffled[:val_count]
|
|
y_val = y_shuffled[:val_count]
|
|
X_train = X_shuffled[val_count:]
|
|
y_train = y_shuffled[val_count:]
|
|
|
|
return X_train, X_val, y_train, y_val
|
|
|
|
|
|
|
|
# 这里也写自己的代码实现
|
|
def load_data(filepath):
|
|
with open(filepath, 'r') as file:
|
|
lines = file.readlines()
|
|
|
|
data = [line.strip().split() for line in lines if line.strip().split()[-1].isdigit()]
|
|
data = [list(map(lambda x: float(x) if x != '?' else np.nan, row)) for row in data]
|
|
|
|
# 移除类别标签缺失的样本
|
|
data = [row for row in data if not np.isnan(row[-1])]
|
|
|
|
# 使用“0”填充缺失值
|
|
for row in data:
|
|
for i in range(len(row)):
|
|
if np.isnan(row[i]):
|
|
row[i] = 0.0
|
|
|
|
# 合并特征23的值2和3为0
|
|
for row in data:
|
|
if row[22] == 2 or row[22] == 3: # 假设特征23是第23个元素
|
|
row[22] = 0
|
|
|
|
# 移除不需要的特征
|
|
data = [row[:2] + row[3:23] + row[28:] for row in data]
|
|
|
|
# 分离特征和标签
|
|
X = [row[:-1] for row in data]
|
|
y = [row[-1] for row in data]
|
|
|
|
scaler = StandardScaler()
|
|
X = scaler.fit_transform(X)
|
|
|
|
return np.array(X), np.array(y)
|
|
"""
|
|
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:
|
|
- directory (str): 数据文件路径。
|
|
|
|
Returns:
|
|
- np.array: 特征数据。
|
|
- np.array: 标签数据。
|
|
"""
|
|
|
|
if __name__ == "__main__":
|
|
X_train, y_train = load_data("./data/horse-colic.data")
|
|
X_test, y_test = load_data("./data/horse-colic.test")
|
|
|
|
weights = train_logreg(X_train, y_train, learning_rate=0.01, iterations=1000)
|
|
|
|
y_pred = predict_logreg(X_test[11], weights)
|
|
print(f"预测结果: {y_pred}, 实际结果: {y_test[11]}") |