更新 function.py
Gitea Actions Experiment Test / Experiment-Actions (push) Successful in 11s

This commit is contained in:
2024-10-29 08:20:44 +08:00
parent f251a8060d
commit d5bd8ba818
+41 -74
View File
@@ -26,97 +26,64 @@ 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):
"""
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 train_logreg(X, y, learning_rate=0.01, iterations=1000, regularization=0.0):
m, n = X.shape
weights = np.zeros(n)
bias = 0
m = len(X) # 重新赋值m,以确保它表示样本数量(在添加正则化时可能需要)
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
linear_output = np.dot(X, weights) + bias # 向量化操作
y_predicted = 1 / (1 + np.exp(-linear_output))
error = y - y_predicted
# 更新权重和偏置,添加正则化项
weights += learning_rate * (error * X.T - regularization * weights) / m
bias += learning_rate * np.sum(error) / m
return weights, bias
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_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
linear_output = np.dot(inX, weights) + bias
y_predicted = 1 if linear_output >= 0 else 0 # 简化判断条件,因为逻辑回归输出已经通过sigmoid函数处理
return y_predicted
# 这里也写自己的代码实现
def load_data(filepath):
"""
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。
"""
# 读取数据,假设数据是用空格分隔的,并且最后一列是标签
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
label = int(parts[-1]) - 1 # 假设标签是{1, 2},转换为{0, 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
X = data_array[:, :-1]
y = data_array[:, -1]
return X, y
def evaluate_model(X, y, weights, bias):
predictions = [predict_logreg(x, weights, bias) for x in X]
accuracy = np.mean(predictions == y)
return accuracy
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)
# 测试单个数据
y_pred = predict_logreg(X_test[11], weights)
X_train, y_train = load_data("./data/horse-colic.data")
X_test, y_test = load_data("./data/horse-colic.test")
# 数据标准化(可选,但通常有助于模型性能)
X_train_mean = np.mean(X_train, axis=0)
X_train_std = np.std(X_train, axis=0)
X_train = (X_train - X_train_mean) / X_train_std
X_test = (X_test - X_train_mean) / X_train_std # 使用训练集的标准差来标准化测试集
# 训练逻辑回归模型
weights, bias = train_logreg(X_train, y_train, learning_rate=0.01, iterations=1000, regularization=0.1)
# 评估模型性能
accuracy = evaluate_model(X_test, y_test, weights, bias)
print(f"测试集准确率: {accuracy:.2f}")
# 测试单个数据(可选)
y_pred = predict_logreg(X_test[11], weights, bias)
print(f"预测结果: {y_pred}, 实际结果: {y_test[11]}")