diff --git a/function.py b/function.py index 6c764ed..0008c6a 100644 --- a/function.py +++ b/function.py @@ -26,118 +26,92 @@ name = "廖运瑞" # 这里写自己的代码实现 -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): - 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])) - - data = np.array(data) - labels = np.array(labels) - - # 检查特征数量 - num_features = data.shape[1] - - # 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） - - # 删除特征 - data = np.delete(data, indices_to_delete, axis=1) - - # 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) - - -# 其余代码保持不变 -if __name__ == "__main__": - # 加载数据 - X, y = load_data("./data/horse-colic.data") - - # 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) - - # 数据归一化 - scaler = MinMaxScaler() - X_train = scaler.fit_transform(X_train) - X_val = scaler.transform(X_val) - - # 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}") \ No newline at end of file +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。 + - learning_rate (float): 学习率，默认为0.01。 + - iterations (int): 迭代次数，默认为1000。 + + Returns: + - numpy array: 训练得到的权重。 + """ + m, n = X.shape + weights = np.zeros(n) + bias = 0 # 偏置项，可以合并到权重中处理，但这里单独处理 + + for _ in range(iterations): + output = sigmoid(np.dot(X, weights) + bias) + error = y - output + weights += learning_rate * np.dot(X.T, error) / m + bias += learning_rate * np.sum(error) / m + + # 如果需要返回偏置项，可以将其添加到权重数组的前面或作为单独的返回值 + # 这里为了与predict_logreg函数接口一致，我们选择不直接修改weights数组 + return weights, bias + +def predict_logreg(inX, weights, bias=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。 + - bias (float): 训练得到的偏置项，默认为0。 + + Returns: + - int: 预测的分类标签（0或1）。 + """ + z = np.dot(inX, weights) + bias + return 1 if sigmoid(z) >= 0.5 else 0 + +def sigmoid(z): + """ + Sigmoid激活函数。 + + Args: + - z (float or numpy array): 输入值。 + + Returns: + - float or numpy array: Sigmoid输出值。 + """ + return 1 / (1 + np.exp(-z)) + +def load_data(filepath): + """ + 从文件中加载数据。 + + Args: + - filepath (str): 数据文件路径。 + + Returns: + - np.array: 特征数据。 + - np.array: 标签数据。 + """ + data = np.loadtxt(filepath, delimiter=' ') + X = data[:, 1:] # 特征数据，假设从第二列开始 + y = data[:, 0] # 标签数据，假设在第一列 + return X, y.astype(int) # 确保标签为整数类型 + +if __name__ == "__main__": + # 加载训练集 + X_train, y_train = load_data("./data/horse-colic.data") + + # 为了处理偏置项，我们在X_train中添加一列全为1的列（或者使用上面的bias参数） + # 但为了与train_logreg函数接口一致，这里我们选择使用bias参数 + # 如果选择将偏置项合并到权重中，则应该这样处理： + # X_train_with_bias = np.c_[np.ones((X_train.shape[0], 1)), X_train] + # 并相应地修改train_logreg函数和predict_logreg函数的接口 + + # 加载测试集 + X_test, y_test = load_data("./data/horse-colic.test") + + # 训练对率回归模型 + weights, bias = 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, bias) + print(f"预测结果: {y_pred}, 实际结果: {y_test[11]}") \ No newline at end of file