From 00d2d4e3a3e46700398077d5cebd3fd9460ae331 Mon Sep 17 00:00:00 2001 From: leiwu <1929652729@qq.com> Date: Sun, 3 Nov 2024 20:05:09 +0800 Subject: [PATCH] =?UTF-8?q?=E6=9B=B4=E6=96=B0=20function.py?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- function.py | 200 +++++++++++++++++++++++++++++----------------------- 1 file changed, 112 insertions(+), 88 deletions(-) diff --git a/function.py b/function.py index a1f5ea0..dcf343d 100644 --- a/function.py +++ b/function.py @@ -1,110 +1,134 @@ import numpy as np +import os +from sklearn.preprocessing import StandardScaler # 导入标准化库 -""" -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。 +# 学号和姓名 +id = "202210423130" +name = "董秋" -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 = "202210423108" -name = "雷武" - - -# 这里写自己的代码实现 def sigmoid(z): - return 1 / (1 + np.exp(-z)) + """计算sigmoid函数""" + return 1.0 / (1 + np.exp(-z)) -def train_logreg(X, y, learning_rate=0.01, iterations=1000): - """ - 对率回归训练函数。 +def compute_gradient(X_batch, y_batch, weights, lambda_reg): + """计算梯度，包含L2正则化""" + 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 - 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=0.001, iterations=10000, batch_size=64, lambda_reg=0.1): + """对率回归训练函数。""" m, n = X.shape - weights = np.zeros(n) - bias = 0 - for i in range(iterations): - linear_model = np.dot(X, weights) + bias - y_pred = sigmoid(linear_model) - - dw = (1 / m) * np.dot(X.T, (y_pred - y)) - db = (1 / m) * np.sum(y_pred - y) - - weights -= learning_rate * dw - bias -= learning_rate * db - return weights, bias - -def predict_logreg(inX, weights, bias): - """ - 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。 - """ + weights = np.random.randn(n) * np.sqrt(2. / n) # He初始化 + print("开始训练对率回归模型") - linear_model = np.dot(inX, weights) + bias - y_pred = sigmoid(linear_model) - return 1 if y_pred >= 0.5 else 0 + for i 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 + + if i % 1000 == 0: # 每1000次迭代打印一次信息 + print(f"迭代 {i}: 当前权重形状: {weights.shape}") + + return weights + +def predict_logreg(inX, weights): + """对率回归预测函数。""" + z = np.dot(inX, weights) + h = sigmoid(z) + return 1 if h >= 0.5 else 0 -# 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**。 + """从文件中加载数据。""" + if not os.path.exists(filepath): + raise FileNotFoundError(f"文件 {filepath} 不存在！") + + data, labels = [], [] + print(f"加载数据中: {filepath}") + 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])) - Args: - - directory (str): 数据文件路径。 + data = np.array(data) + labels = np.array(labels) + + num_features = data.shape[1] + indices_to_remove = [2] # 去掉特征3（索引2） + + if num_features > 23: + indices_to_remove.extend(range(23, min(28, num_features))) - Returns: - - np.array: 特征数据。 - - np.array: 标签数据。 - """ - # 使用 genfromtxt 来加载数据，忽略无法转换的值，并处理缺失值 - data = np.genfromtxt(filepath, delimiter=',', dtype=float, filling_values=np.nan) - # 移除含有NaN的行 - data = data[~np.isnan(data).any(axis=1)] - # 确保数据至少有两列，否则无法分割为特征和标签 - if data.shape[1] < 2: - raise ValueError("数据文件格式不正确，应至少包含两列") - X = data[:, :-1] - y = data[:, -1].astype(int) - return X, y + data = np.delete(data, indices_to_remove, axis=1) + target_variable = np.where((labels == 2) | (labels == 3), 0, 1) + print(f"数据加载成功，数据形状: {data.shape}, 标签形状: {target_variable.shape}") + return data, target_variable + +def k_fold_cross_validation(X, y, k=5, learning_rate=0.001, iterations=10000, batch_size=64, lambda_reg=0.1): + """K折交叉验证。""" + m = X.shape[0] + fold_size = m // k + accuracies = [] + + for i in range(k): + val_start = i * fold_size + val_end = (i + 1) * fold_size if i != k - 1 else m + + X_val = X[val_start:val_end] + y_val = y[val_start:val_end] + X_train = np.concatenate((X[:val_start], X[val_end:])) + y_train = np.concatenate((y[:val_start], y[val_end:])) + + weights = train_logreg(X_train, y_train, learning_rate, iterations, batch_size, lambda_reg) + + val_accuracy = np.mean([predict_logreg(X_val[j], weights) == y_val[j] for j in range(len(y_val))]) + accuracies.append(val_accuracy) + + print(f"Fold {i + 1}/{k} - 验证准确率: {val_accuracy:.4f}") + + return np.mean(accuracies) 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") + try: + X_train, y_train = load_data("./data/horse-colic.data") + except FileNotFoundError as e: + print(e) + exit() + + # 数据归一化处理 + scaler = StandardScaler() + X_train = scaler.fit_transform(X_train) # 使用训练集进行标准化 + + # k折交叉验证 + avg_accuracy = k_fold_cross_validation(X_train, y_train, k=5, learning_rate=0.01, iterations=1000) + print(f"K折交叉验证的平均准确率: {avg_accuracy:.4f}") # 加载测试集 - X_test, y_test = load_data("./data/horse-colic.test") + try: + X_test, y_test = load_data("./data/horse-colic.test") + except FileNotFoundError as e: + print(e) + exit() + + # 测试集也需要进行相同的归一化 + X_test = scaler.transform(X_test) # 使用相同的Scaler进行测试集的标准化 # 训练对率回归模型 - weights, bias = train_logreg(X_train, y_train, learning_rate=0.01, iterations=1000) + 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, bias) - print(f"预测结果: {y_pred}, 实际结果: {y_test[11]}") + y_pred = predict_logreg(X_test[11], weights) + print(f"预测结果: {y_pred}, 实际结果: {y_test[11]}") \ No newline at end of file