generated from LufsX/Experiment-LogReg
This commit is contained in:
+112
-104
@@ -1,122 +1,130 @@
|
||||
import numpy as np
|
||||
from sklearn.model_selection import KFold
|
||||
from sklearn.impute import SimpleImputer
|
||||
"""
|
||||
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。
|
||||
|
||||
# 请在这里填写学号和姓名，不填写即成绩无效。
|
||||
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 = "202210423107"
|
||||
name = "刘燚燊"
|
||||
|
||||
import pandas as pd
|
||||
import numpy as np
|
||||
from sklearn.preprocessing import MinMaxScaler
|
||||
from sklearn.model_selection import train_test_split
|
||||
|
||||
def sigmoid(z):
|
||||
return 1.0 / (1 + np.exp(-z))
|
||||
|
||||
def compute_gradient(X_batch, y_batch, weights, lambda_reg):
|
||||
z = np.dot(X_batch, weights)
|
||||
h = sigmoid(z)
|
||||
gradient = np.dot(X_batch.T, (h - y_batch)) / len(y_batch)
|
||||
gradient += (lambda_reg / len(y_batch)) * weights # L2正则化
|
||||
return gradient
|
||||
|
||||
def train_logreg(X, y, learning_rate=0.001, iterations=10000, batch_size=64, lambda_reg=0.1):
|
||||
m, n = X.shape
|
||||
weights = np.random.randn(n) * np.sqrt(2. / n) # He初始化
|
||||
best_weights = weights.copy()
|
||||
best_accuracy = 0
|
||||
|
||||
for _ in range(iterations):
|
||||
indices = np.random.permutation(m)
|
||||
X_shuffled = X[indices]
|
||||
y_shuffled = y[indices]
|
||||
|
||||
for j in range(0, m, batch_size):
|
||||
X_batch = X_shuffled[j:j + batch_size]
|
||||
y_batch = y_shuffled[j:j + batch_size]
|
||||
gradient = compute_gradient(X_batch, y_batch, weights, lambda_reg)
|
||||
weights -= learning_rate * gradient
|
||||
|
||||
# 计算训练集准确率
|
||||
train_accuracy = accuracy(X, y, weights)
|
||||
if train_accuracy > best_accuracy:
|
||||
best_accuracy = train_accuracy
|
||||
best_weights = weights.copy()
|
||||
|
||||
# 动态调整学习率
|
||||
if _ % 100 == 0 and train_accuracy > 0.95: # 达到高准确率时减小学习率
|
||||
learning_rate *= 0.9
|
||||
|
||||
return best_weights
|
||||
|
||||
def predict_logreg(X, weights):
|
||||
z = np.dot(X, weights)
|
||||
h = sigmoid(z)
|
||||
return np.where(h >= 0.5, 1, 0)
|
||||
|
||||
def load_data(filepath):
|
||||
"""
|
||||
从文件中加载数据，处理缺失值和标签。
|
||||
|
||||
Args:
|
||||
- filepath (str): 数据文件路径。
|
||||
data, labels = [], []
|
||||
with open(filepath, 'r') as f:
|
||||
for line in f:
|
||||
line = line.strip().split()
|
||||
if len(line) >= 1 and line[-1].isdigit():
|
||||
line_data = [0 if x == '?' else float(x) for x in line[:-1]]
|
||||
data.append(line_data)
|
||||
labels.append(int(line[-1]))
|
||||
|
||||
Returns:
|
||||
- np.array: 特征数据。
|
||||
- np.array: 标签数据。
|
||||
"""
|
||||
# 使用pandas读取数据
|
||||
data = pd.read_csv(filepath, header=None, na_values='?')
|
||||
data = np.array(data)
|
||||
labels = np.array(labels)
|
||||
|
||||
# 填充缺失值
|
||||
data.fillna(data.mean(), inplace=True)
|
||||
# 检查特征数量
|
||||
num_features = data.shape[1]
|
||||
|
||||
# 分离特征和标签
|
||||
X = data.iloc[:, :-1].values
|
||||
y = data.iloc[:, -1].values
|
||||
# 特征选择：去掉特征3（索引2）和特征24~28（索引23~26），确保索引有效
|
||||
indices_to_delete = [2] # 特征3
|
||||
if num_features > 24: # 确保特征数量足够
|
||||
indices_to_delete += list(range(24, 27)) # 特征24到27（索引23到26）
|
||||
|
||||
# 过滤掉没有类别标签的数据
|
||||
valid_indices = np.isfinite(y)
|
||||
X = X[valid_indices]
|
||||
y = y[valid_indices]
|
||||
# 删除特征
|
||||
data = np.delete(data, indices_to_delete, axis=1)
|
||||
|
||||
return X, y
|
||||
# 将标签二分类化，特征23（索引22）取值2和3合并为0，其余为1
|
||||
target_variable = np.where((labels == 2) | (labels == 3), 0, 1)
|
||||
|
||||
return data, target_variable
|
||||
|
||||
def accuracy(X, y, weights):
|
||||
predictions = predict_logreg(X, weights)
|
||||
return np.mean(predictions == y)
|
||||
|
||||
def train_logreg(X, y, learning_rate=0.01, iterations=1000, reg_param=0.01):
|
||||
# 初始化权重
|
||||
weights = np.zeros(X.shape[1])
|
||||
|
||||
for i in range(iterations):
|
||||
# 计算线性组合和sigmoid函数
|
||||
linear_model = np.dot(X, weights)
|
||||
y_predicted = 1 / (1 + np.exp(-linear_model))
|
||||
|
||||
# 计算梯度
|
||||
gradient = np.dot(X.T, (y_predicted - y)) / y.size
|
||||
weights -= learning_rate * (gradient + reg_param * weights) # L2 正则化
|
||||
|
||||
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。
|
||||
"""
|
||||
linear_model = np.dot(inX, weights)
|
||||
y_predicted = 1 / (1 + np.exp(-linear_model))
|
||||
return (y_predicted > 0.5).astype(int)
|
||||
|
||||
|
||||
def evaluate_model(X, y, learning_rate, iterations, reg_param, folds=5):
|
||||
"""
|
||||
使用交叉验证评估模型性能。
|
||||
|
||||
Args:
|
||||
- X (numpy array): 特征数据。
|
||||
- y (numpy array): 标签数据。
|
||||
- learning_rate (float): 学习率。
|
||||
- iterations (int): 训练迭代次数。
|
||||
- reg_param (float): 正则化参数。
|
||||
- folds (int): 交叉验证折数。
|
||||
|
||||
Returns:
|
||||
- float: 平均准确率。
|
||||
"""
|
||||
kf = KFold(n_splits=folds)
|
||||
accuracy_list = []
|
||||
|
||||
for train_index, test_index in kf.split(X):
|
||||
X_train, X_test = X[train_index], X[test_index]
|
||||
y_train, y_test = y[train_index], y[test_index]
|
||||
|
||||
weights = train_logreg(X_train, y_train, learning_rate, iterations, reg_param)
|
||||
predictions = predict_logreg(X_test, weights)
|
||||
|
||||
accuracy = np.mean(predictions == y_test)
|
||||
accuracy_list.append(accuracy)
|
||||
|
||||
return np.mean(accuracy_list)
|
||||
|
||||
|
||||
# 其余代码保持不变
|
||||
if __name__ == "__main__":
|
||||
# 加载训练集
|
||||
X_train, y_train = load_data("./data/horse-colic.data")
|
||||
# 加载数据
|
||||
X, y = load_data("./data/horse-colic.data")
|
||||
|
||||
# 调优超参数
|
||||
best_accuracy = 0
|
||||
best_params = {}
|
||||
learning_rates = [0.001, 0.01, 0.1]
|
||||
reg_params = [0.01, 0.1, 1.0]
|
||||
# 拆分训练集和验证集
|
||||
X_train, X_val, y_train, y_val = train_test_split(X, y, test_size=0.2, random_state=42)
|
||||
|
||||
for lr in learning_rates:
|
||||
for reg in reg_params:
|
||||
accuracy = evaluate_model(X_train, y_train, lr, 1000, reg)
|
||||
print(f"尝试参数: {{'learning_rate': {lr}, 'reg_param': {reg}}}, 准确率: {accuracy:.2f}")
|
||||
if accuracy > best_accuracy:
|
||||
best_accuracy = accuracy
|
||||
best_params = {'learning_rate': lr, 'reg_param': reg}
|
||||
# 数据归一化
|
||||
scaler = MinMaxScaler()
|
||||
X_train = scaler.fit_transform(X_train)
|
||||
X_val = scaler.transform(X_val)
|
||||
|
||||
print(f"最佳参数: {best_params}, 最高准确率: {best_accuracy:.2f}")
|
||||
# 训练模型
|
||||
final_weights = train_logreg(X_train, y_train, learning_rate=0.01, iterations=5000, batch_size=64, lambda_reg=0.1)
|
||||
|
||||
# 验证模型
|
||||
val_accuracy = accuracy(X_val, y_val, final_weights)
|
||||
print(f"验证集的准确率: {val_accuracy:.4f}")
|
||||
|
||||
# 加载测试集
|
||||
X_test, y_test = load_data("./data/horse-colic.test")
|
||||
X_test = scaler.transform(X_test)
|
||||
|
||||
# 测试模型
|
||||
final_test_accuracy = accuracy(X_test, y_test, final_weights)
|
||||
print(f"最终测试集的准确率: {final_test_accuracy:.4f}")
|
||||
Reference in New Issue
Block a user