更新 function.py

function.py

@@ -27,26 +27,21 @@ name = "章程鸿"
 
 # 这里写自己的代码实现
 import numpy as np
-from sklearn.preprocessing import MinMaxScaler
+from sklearn.preprocessing import StandardScaler
-from sklearn.model_selection import train_test_split
 
 def sigmoid(z):
+    """Sigmoid 激活函数。"""
     return 1.0 / (1 + np.exp(-z))
 
-def compute_gradient(X_batch, y_batch, weights, lambda_reg):
+def train_logreg(X, y, learning_rate=0.05, iterations=1500, batch_size=64, reg_lambda=0.01):
-    z = np.dot(X_batch, weights)
+    """训练逻辑回归模型的函数，使用梯度下降算法。"""
-    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
+    weights = np.random.randn(n) * 0.01  # 初始化权重
     best_weights = weights.copy()
     best_accuracy = 0
+    wait = 0
 
-    for _ in range(iterations):
+    for i in range(iterations):
         indices = np.random.permutation(m)
         X_shuffled = X[indices]
         y_shuffled = y[indices]
@@ -54,7 +49,10 @@ def train_logreg(X, y, learning_rate=0.001, iterations=10000, batch_size=64, lam
         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)
+            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
@@ -62,20 +60,26 @@ def train_logreg(X, y, learning_rate=0.001, iterations=10000, batch_size=64, lam
         if train_accuracy > best_accuracy:
             best_accuracy = train_accuracy
             best_weights = weights.copy()
+            wait = 0
+        else:
+            wait += 1
 
-        # 动态调整学习率
+        # 如果准确率没有提高，提前停止
-        if _ % 100 == 0 and train_accuracy > 0.95:  # 达到高准确率时减小学习率
+        if wait > 50:
-            learning_rate *= 0.9
+            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)
+    return np.where(h > 0.5, 1, 0)
 
 def load_data(filepath):
-    data, labels = [], []
+    """加载数据函数。"""
+    data = []
+    labels = []
     with open(filepath, 'r') as f:
         for line in f:
             line = line.strip().split()
@@ -86,41 +90,34 @@ def load_data(filepath):
 
     data = np.array(data)
     labels = np.array(labels)
-    # 将标签二分类化，2和3为0，其余为1
+    target_variable = np.where((labels == 2) | (labels == 3), 0, labels)
-    target_variable = np.where((labels == 2) | (labels == 3), 0, 1)
+    
-
+    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)
+    
     return data, target_variable
 
 def accuracy(X, y, weights):
+    """计算准确率。"""
     predictions = predict_logreg(X, weights)
     return np.mean(predictions == y)
 
 if __name__ == "__main__":
-    # 加载数据
+    X_train, y_train = load_data("./horse-colic.data")
-    X, y = load_data("./data/horse-colic.data")
+    X_test, y_test = load_data("./horse-colic.test")
-    
-    # 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
+    # 特征标准化
-    scaler = MinMaxScaler()
+    scaler = StandardScaler()
     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=0.001, iterations=10000, 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
+    # 训练模型
-    final_test_accuracy = accuracy(X_test, y_test, final_weights)
+    final_weights = train_logreg(X_train, y_train, learning_rate=0.001, iterations=1500, batch_size=64, reg_lambda=0.01)
-    print(f"最终测试集的准确率: {final_test_accuracy:.4f}")
-
-
 
+    # 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}")