diff --git a/function.py b/function.py index 72cdde3..9408735 100644 --- a/function.py +++ b/function.py @@ -1,21 +1,14 @@ import numpy as np -""" -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。 -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。 -""" id = "202210423213" name = "熊浩燃" -# 对率回归训练函数，包含调参和优化 -def train_logreg(X, y, learning_rate=0.01, iterations=1000, regularization=0.01, early_stopping_rounds=100): + +# 对率回归训练函数，包含加权损失、正则化、学习率调度和提前停止 +def train_logreg(X, y, learning_rate=0.01, iterations=1000, regularization=0.01, early_stopping_rounds=100, class_weights={0: 1, 1: 1}): """ - 对率回归训练函数，带有学习率调度和正则化。 + 对率回归训练函数，带有加权损失和正则化。 Args: - X (numpy array): 特征数据。 - y (numpy array): 标签数据。 @@ -23,6 +16,7 @@ def train_logreg(X, y, learning_rate=0.01, iterations=1000, regularization=0.01, - iterations (int): 最大迭代次数。 - regularization (float): 正则化参数。 - early_stopping_rounds (int): 提前停止轮数。 + - class_weights (dict): 类别权重字典，控制类别不平衡。 Returns: - numpy array: 训练得到的权重。 """ @@ -31,13 +25,14 @@ def train_logreg(X, y, learning_rate=0.01, iterations=1000, regularization=0.01, stopping_step = 0 for i in range(iterations): - # 预测值：通过对率回归模型得到 + # 预测值 z = np.dot(X, weights) predictions = 1 / (1 + np.exp(-z)) - - # 计算损失（含正则化项） - loss = -np.mean(y * np.log(predictions) + (1 - y) * np.log(1 - predictions)) + regularization * np.sum(weights**2) - + + # 加权损失 + loss = -np.mean(class_weights[1] * y * np.log(predictions) + + class_weights[0] * (1 - y) * np.log(1 - predictions)) + regularization * np.sum(weights**2) + # 提前停止判断 if loss < min_loss: min_loss = loss @@ -48,7 +43,7 @@ def train_logreg(X, y, learning_rate=0.01, iterations=1000, regularization=0.01, print("提前停止于迭代:", i) break - # 计算梯度并更新权重（含正则化项） + # 计算梯度并更新权重 gradient = (np.dot(X.T, (predictions - y)) + regularization * weights) / y.size weights -= learning_rate * gradient @@ -59,18 +54,19 @@ def train_logreg(X, y, learning_rate=0.01, iterations=1000, regularization=0.01, return weights -# 对率回归预测函数 -def predict_logreg(inX, weights): +# 对率回归预测函数，带有自定义阈值 +def predict_logreg(inX, weights, threshold=0.6): """ 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。 + - threshold (float): 分类决策阈值。 Returns: - int: 预测的分类标签。 """ probability = 1 / (1 + np.exp(-np.dot(inX, weights))) - return 1 if probability >= 0.5 else 0 + return 1 if probability >= threshold else 0 # 数据加载函数，包含缺失值填充 def load_data(filepath): @@ -107,7 +103,7 @@ def load_data(filepath): return data, labels # 网格搜索函数 -def grid_search(X, y, learning_rates, iterations_list, regularizations): +def grid_search(X, y, learning_rates, iterations_list, regularizations, class_weights_list): """ 网格搜索来优化对率回归模型。 Args: @@ -116,6 +112,7 @@ def grid_search(X, y, learning_rates, iterations_list, regularizations): - learning_rates (list of float): 学习率列表。 - iterations_list (list of int): 迭代次数列表。 - regularizations (list of float): 正则化参数列表。 + - class_weights_list (list of dict): 类别权重列表。 Returns: - dict: 包含最佳超参数及其对应的权重。 """ @@ -126,17 +123,18 @@ def grid_search(X, y, learning_rates, iterations_list, regularizations): for lr in learning_rates: for iters in iterations_list: for reg in regularizations: - print(f"尝试参数: 学习率={lr}, 迭代次数={iters}, 正则化={reg}") - weights = train_logreg(X, y, learning_rate=lr, iterations=iters, regularization=reg) - z = np.dot(X, weights) - predictions = 1 / (1 + np.exp(-z)) - loss = -np.mean(y * np.log(predictions) + (1 - y) * np.log(1 - predictions)) - print(f"损失: {loss}") + for cw in class_weights_list: + print(f"尝试参数: 学习率={lr}, 迭代次数={iters}, 正则化={reg}, 类别权重={cw}") + weights = train_logreg(X, y, learning_rate=lr, iterations=iters, regularization=reg, class_weights=cw) + z = np.dot(X, weights) + predictions = 1 / (1 + np.exp(-z)) + loss = -np.mean(cw[1] * y * np.log(predictions) + cw[0] * (1 - y) * np.log(1 - predictions)) + print(f"损失: {loss}") - if loss < best_loss: - best_loss = loss - best_weights = weights - best_params = {'learning_rate': lr, 'iterations': iters, 'regularization': reg} + if loss < best_loss: + best_loss = loss + best_weights = weights + best_params = {'learning_rate': lr, 'iterations': iters, 'regularization': reg, 'class_weights': cw} print("最佳参数:", best_params) return best_weights, best_params @@ -149,13 +147,14 @@ if __name__ == "__main__": learning_rates = [0.001, 0.01, 0.1] iterations_list = [1000, 2000, 3000] regularizations = [0.01, 0.1, 1.0] + class_weights_list = [{0: 1, 1: 1}, {0: 1, 1: 2}, {0: 1, 1: 3}] # 进行网格搜索以找到最佳超参数组合 - best_weights, best_params = grid_search(X_train, y_train, learning_rates, iterations_list, regularizations) + best_weights, best_params = grid_search(X_train, y_train, learning_rates, iterations_list, regularizations, class_weights_list) print("最佳权重:", best_weights) # 使用最佳权重进行预测 X_test, y_test = load_data("./data/horse-colic.test") - y_pred = [predict_logreg(x, best_weights) for x in X_test] + y_pred = [predict_logreg(x, best_weights, threshold=0.6) for x in X_test] accuracy = np.mean(y_pred == y_test) print(f"测试集准确率: {accuracy}")