更新 function.py

function.py

@@ -27,169 +27,100 @@ name = "章程鸿"
 
 # 这里写自己的代码实现
 import numpy as np
-import pandas as pd
-from sklearn.preprocessing import StandardScaler
-from sklearn.model_selection import train_test_split, KFold, GridSearchCV
-from sklearn.linear_model import LogisticRegression
-from sklearn.metrics import confusion_matrix, precision_score, recall_score, f1_score
-import warnings
-
-warnings.filterwarnings("ignore")
+from sklearn.preprocessing import StandardScaler, MinMaxScaler
+from sklearn.model_selection import train_test_split
 
 def sigmoid(z):
-    """Sigmoid 激活函数。"""
-    return 1 / (1 + np.exp(-z))
-
-def train_logreg(X, y, learning_rate=0.01, iterations=5000, lambda_reg=0.01, batch_size=32):
-    """逻辑回归训练函数，随机初始化权重，并在每次迭代前打乱数据。"""
-    m, n = X.shape
-    weights = np.random.randn(n) * 0.01  # 随机初始化权重，取较小值
-
-    for i in range(iterations):
-        # 每次迭代打乱数据
-        indices = np.random.permutation(m)
-        X = X[indices]
-        y = y[indices]
-
-        for j in range(0, m, batch_size):  # 按照 batch size 迭代
-            X_batch = X[j:j + batch_size]
-            y_batch = y[j:j + batch_size]
+    return 1.0 / (1 + np.exp(-z))
 
+def compute_gradient(X_batch, y_batch, weights, lambda_reg):
     z = np.dot(X_batch, weights)
-            predictions = sigmoid(z)
-            gradient = np.dot(X_batch.T, (predictions - y_batch)) / X_batch.shape[0]
+    h = sigmoid(z)
+    gradient = np.dot(X_batch.T, (h - y_batch)) / len(y_batch)
+    # 添加L2正则化
+    gradient += (lambda_reg / len(y_batch)) * weights
+    return gradient
 
-            # L2 正则化
-            gradient += (lambda_reg / m) * weights
+def train_logreg(X, y, learning_rate=0.01, iterations=5000, batch_size=64, lambda_reg=0.01):
+    m, n = X.shape
+    weights = np.random.randn(n) * 0.01
+    best_weights = weights.copy()
+    best_accuracy = 0
 
-            # 更新权重
+    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 i % 1000 == 0:  # 每 1000 次迭代调整一次学习率
-            learning_rate *= 0.9  # 每 1000 次迭代减小学习率
+        if _ % 100 == 0 and train_accuracy > 0.95:  # 达到高准确率时减小学习率
+            learning_rate *= 0.9
 
-        if i % 100 == 0:  # 每 100 次迭代输出一次学习率
-            print(f"Iteration {i}, Learning Rate: {learning_rate}")
+    return best_weights
 
-    return weights
-
-def predict_logreg(inX, weights):
-    """逻辑回归预测函数。"""
-    z = np.dot(inX, weights)
-    prediction_prob = sigmoid(z)
-    return 1 if prediction_prob >= 0.5 else 0
+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):
-    """加载数据并处理缺失值。"""
-    data = []
-    labels = []
-
+    data, labels = [], []
     with open(filepath, 'r') as f:
         for line in f:
-            values = line.strip().replace('?', '0').split()
-            try:
-                values = [float(v) for v in values]
-
-                # 合并特征 23 的取值
-                if values[22] == 2 or values[22] == 3:  # 特征 23（索引 22）
-                    labels.append(0)  # 死亡
-                elif values[22] == 1:
-                    labels.append(1)  # 生存
-                else:
-                    continue  # 无效标签，丢弃
-
-                # 用均值填充缺失值
-                values = [np.nan if v == 0 else v for v in values]
-                nan_indices = np.isnan(values)
-                column_means = np.nanmean(np.array(data), axis=0)
-                for i, is_nan in enumerate(nan_indices):
-                    if is_nan:
-                        values[i] = column_means[i]
-                data.append(values[:2] + values[3:23])  # 保留特征 1, 2 和特征 4 - 23
-            except ValueError:
-                continue
+            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)
+    target_variable = np.where((labels == 2) | (labels == 3), 0, labels)
 
-    return data, labels
+    return data, target_variable
 
-def preprocess_data(X):
-    """特征标准化。"""
-    scaler = StandardScaler()
-    return scaler.fit_transform(X)
+def accuracy(X, y, weights):
+    predictions = predict_logreg(X, weights)
+    return np.mean(predictions == y)
 
 if __name__ == "__main__":
-    # 加载训练集
-    X_train, y_train = load_data("./data/horse-colic.data")
+    # 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)
 
-    # 归一化数据
-    X_train = preprocess_data(X_train)
-    X_test = preprocess_data(X_test)
-
-    # 超参数搜索空间
-    param_grid = {
-        'learning_rate': [0.001, 0.01, 0.1],
-        'iterations': [3000, 5000, 7000],
-        'lambda_reg': [0.001, 0.01, 0.1],
-        'batch_size': [16, 32, 64]
-    }
-
-    # K 折交叉验证
-    k = 5
-    kf = KFold(n_splits=k, shuffle=True, random_state=42)
-    accuracies = []
-
-    for train_index, val_index in kf.split(X_train):
-        X_train_kf, X_val_kf = X_train[train_index], X_train[val_index]
-        y_train_kf, y_val_kf = y_train[train_index], y_train[val_index]
-
-        best_params = None
-        best_score = 0
-
-        for params in GridSearchCV(estimator=LogisticRegression(), param_grid=param_grid, scoring='accuracy', cv=3).fit(X_train_kf, y_train_kf).cv_results_['params']:
-            weights = train_logreg(X_train_kf, y_train_kf, learning_rate=params['learning_rate'], iterations=params['iterations'], lambda_reg=params['lambda_reg'], batch_size=params['batch_size'])
-            val_predictions = [predict_logreg(X_val_kf[i], weights) for i in range(len(X_val_kf))]
-            score = np.mean(val_predictions == y_val_kf)
-            if score > best_score:
-                best_score = score
-                best_params = params
-
-        print(f"Best parameters for fold: {best_params}")
-
-        # 使用最佳参数重新训练
-        weights = train_logreg(X_train_kf, y_train_kf, learning_rate=best_params['learning_rate'], iterations=best_params['iterations'], lambda_reg=best_params['lambda_reg'], batch_size=best_params['batch_size'])
-        val_predictions = [predict_logreg(X_val_kf[i], weights) for i in range(len(X_val_kf))]
-        accuracy = np.mean(val_predictions == y_val_kf)
-        accuracies.append(accuracy)
-
-    # 输出交叉验证的准确率和平均准确率
-    print(f"K 折交叉验证得分: {accuracies}")
-    print(f"平均准确率: {np.mean(accuracies)}")
-
-    # 在测试集上测试模型
-    best_params = None
-    best_score = 0
-
-    for params in GridSearchCV(estimator=LogisticRegression(), param_grid=param_grid, scoring='accuracy', cv=3).fit(X_train, y_train).cv_results_['params']:
-        weights = train_logreg(X_train, y_train, learning_rate=params['learning_rate'], iterations=params['iterations'], lambda_reg=params['lambda_reg'], batch_size=params['batch_size'])
-        test_predictions = [predict_logreg(X_test[i], weights) for i in range(len(X_test))]
-        score = np.mean(test_predictions == y_test)
-        if score > best_score:
-            best_score = score
-            best_params = params
-
-    print(f"Best parameters for test set: {best_params}")
-
-    weights = train_logreg(X_train, y_train, learning_rate=best_params['learning_rate'], iterations=best_params['iterations'], lambda_reg=best_params['lambda_reg'], batch_size=best_params['batch_size'])
-    test_predictions = [predict_logreg(X_test[i], weights) for i in range(len(X_test))]
-    test_accuracy = np.mean(test_predictions == y_test)
-    print(f"测试集准确率: {test_accuracy}")
-
+    # 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}")