更新 function.py

function.py

@@ -27,59 +27,10 @@ name = "章程鸿"
 
 # 这里写自己的代码实现
 import numpy as np
-from sklearn.preprocessing import StandardScaler
-
-def sigmoid(z):
-    """Sigmoid 激活函数。"""
-    return 1.0 / (1 + np.exp(-z))
-
-def train_logreg(X, y, learning_rate=0.05, iterations=1500, batch_size=64, reg_lambda=0.01):
-    """训练逻辑回归模型的函数，使用梯度下降算法。"""
-    m, n = X.shape
-    weights = np.random.randn(n) * 0.01  # 初始化权重
-    best_weights = weights.copy()
-    best_accuracy = 0
-    wait = 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]
-            z = np.dot(X_batch, weights)
-            h = sigmoid(z)
-            gradient = np.dot(X_batch.T, (h - y_batch)) / len(y_batch) + reg_lambda * weights
-
-            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()
-            wait = 0
-        else:
-            wait += 1
-
-        # 如果准确率没有提高，提前停止
-        if wait > 50:
-            break
-
-    return best_weights
-
-def predict_logreg(X, weights):
-    """预测函数。"""
-    z = np.dot(X, weights)
-    h = sigmoid(z)
-    return np.where(h > 0.5, 1, 0)
-
+from sklearn.preprocessing import MinMaxScaler
+from sklearn.model_selection import train_test_split
 def load_data(filepath):
-    """加载数据函数。"""
-    data = []
-    labels = []
+    data, labels = [], []
     with open(filepath, 'r') as f:
         for line in f:
             line = line.strip().split()
@@ -90,34 +41,79 @@ def load_data(filepath):
 
     data = np.array(data)
     labels = np.array(labels)
-    target_variable = np.where((labels == 2) | (labels == 3), 0, labels)
-    
-    n_features = data.shape[1]
-    columns_to_delete = [2] + list(range(23, min(28, n_features)))
-    data = np.delete(data, columns_to_delete, axis=1)
-    
-    scaler = StandardScaler()
-    data = scaler.fit_transform(data)
-    
+
+    # 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):
-    """计算准确率。"""
-    predictions = predict_logreg(X, weights)
-    return np.mean(predictions == y)
+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]
+    print(f"特征数量: {num_features}")
+
+    # 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
+
+
+
+# 其余代码保持不变
 if __name__ == "__main__":
-    X_train, y_train = load_data("./horse-colic.data")
-    X_test, y_test = load_data("./horse-colic.test")
+    # 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)
 
-    # 特征标准化
-    scaler = StandardScaler()
+    # 数据归一化
+    scaler = MinMaxScaler()
     X_train = scaler.fit_transform(X_train)
-    X_test = scaler.transform(X_test)
+    X_val = scaler.transform(X_val)
 
     # 训练模型
-    final_weights = train_logreg(X_train, y_train, learning_rate=0.001, iterations=1500, batch_size=64, reg_lambda=0.01)
+    final_weights = train_logreg(X_train, y_train, learning_rate=0.01, iterations=5000, batch_size=64, lambda_reg=0.1)
 
-    # 计算测试集准确率
-    final_accuracy = accuracy(X_test, y_test, final_weights)
-    print(f"最终测试集的准确率: {final_accuracy:.4f}")
+    # 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}")