From f5862cc849f4ca09304c5a14bb6ec3834f496d23 Mon Sep 17 00:00:00 2001 From: meixiaodong <3081674342@qq.com> Date: Sun, 3 Nov 2024 22:45:25 +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 | 151 +++++++++++++--------------------------------------- 1 file changed, 37 insertions(+), 114 deletions(-) diff --git a/function.py b/function.py index 5887304..55e9bdf 100644 --- a/function.py +++ b/function.py @@ -1,7 +1,3 @@ -import numpy as np -import os -from sklearn.preprocessing import StandardScaler - """ 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。 @@ -27,118 +23,45 @@ id = "202210423211" name = "梅晓东" -def sigmoid(z): - """计算sigmoid函数""" - return 1.0 / (1 + np.exp(-z)) +import pandas as pd +from sklearn.linear_model import LogisticRegression +from sklearn.model_selection import train_test_split +from sklearn.metrics import accuracy_score -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 -def train_logreg(X, y, learning_rate=0.001, iterations=10000, batch_size=64, lambda_reg=0.1): - """逻辑回归训练函数。""" - m, n = X.shape - weights = np.random.randn(n) * np.sqrt(2. / n) # He初始化 - print("开始训练逻辑回归模型") +def load_data(file_path): + """ + 加载数据 + :param file_path: 数据文件路径 + :return: 特征和标签 + """ + data = pd.read_csv(file_path) + X = data.drop('death', axis=1) # 假设 'death' 列为标签 + y = data['death'] + return X, y - for i in range(iterations): - indices = np.random.permutation(m) - X_shuffled = X[indices] - y_shuffled = y[indices] +def train_logreg(X, y): + """ + 训练对率回归模型 + :param X: 特征 + :param y: 标签 + :return: 训练好的模型 + """ + X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42) + model = LogisticRegression() + model.fit(X_train, y_train) + y_pred = model.predict(X_test) + accuracy = accuracy_score(y_test, y_pred) + print(f'Accuracy: {accuracy:.2f}') + return model - 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}") +def predict_logreg(model, X_new): + """ + 使用训练好的模型进行预测 + :param model: 训练好的对率回归模型 + :param X_new: 新的特征数据 + :return: 预测结果 + """ + predictions = model.predict(X_new) + return predictions - return weights - -def predict_logreg(inX, weights): - """逻辑回归预测函数。""" - z = np.dot(inX, weights) - h = sigmoid(z) - return 1 if h >= 0.5 else 0 - -def load_data(filepath): - """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])) - data = np.array(data) - labels = np.array(labels) - num_features = data.shape[1] - indices_to_remove = [2] - if num_features > 23: - indices_to_remove.extend(range(23, min(28, num_features))) - 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__": - # 加载训练集 - 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 - 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 - - # 训练逻辑回归模型 - 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) - print(f"预测结果: {y_pred}, 实际结果: {y_test[11]}")