更新 function.py

function.py

@@ -26,40 +26,19 @@ name = "邓龙树"
 
 # user_cod
 import numpy as np
-import pandas as pd
 from sklearn.preprocessing import StandardScaler
 
 def sigmoid(z):
     """Sigmoid 激活函数。"""
-    return 1 / (1 + np.exp(-z))
-
-def train_logreg(X, y, other_params=None):
-    """
-    对率回归训练函数。
-
-    Args:
-    - X (numpy array): 特征数据。
-    - y (numpy array): 标签数据。
-    - other_params (dict): 其它参数，可选设置。
-
-    Returns:
-    - numpy array: 训练得到的权重。
-    """
-    if other_params is None:
-        other_params = {
-            'learning_rate': 0.1,
-            'iterations': 2000,
-            'lambda_reg': 0.01,
-            'batch_size': 32
-        }
-    
-    learning_rate = other_params.get('learning_rate', 0.1)
-    iterations = other_params.get('iterations', 2000)
-    lambda_reg = other_params.get('lambda_reg', 0.01)
-    batch_size = other_params.get('batch_size', 32)
+    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  # 随机初始化权重，取较小值
+    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)
@@ -69,86 +48,73 @@ def train_logreg(X, y, other_params=None):
         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)
-            predictions = sigmoid(z)
-            gradient = np.dot(X_batch.T, (predictions - y_batch)) / X_batch.shape[0] + (lambda_reg / m) * weights
+            h = sigmoid(z)
+            gradient = np.dot(X_batch.T, (h - y_batch)) / len(y_batch) + reg_lambda * weights
 
             weights -= learning_rate * gradient
 
-        if i % 100 == 0:
-            print(f"Iteration {i}, Learning Rate: {learning_rate}")
+        # 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
 
-    return weights
+        # 如果准确率没有提高，提前停止
+        if wait > 50:
+            break
 
-def predict_logreg(inX, weights):
-    """
-    对率回归预测函数。
+    return best_weights
 
-    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。
-    """
-    z = np.dot(inX, weights)
-    prediction_prob = sigmoid(z)
-    return 1 if prediction_prob >= 0.5 else 0
+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)
 
 def load_data(filepath):
-    """
-    从文件中加载数据。
-
-    Args:
-    - filepath (str): 数据文件路径。
-
-    Returns:
-    - np.array: 特征数据。
-    - np.array: 标签数据。
-    """
+    """加载数据函数。"""
     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]
-                if values[22] == 2 or values[22] == 3:
-                    labels.append(0)
-                    data.append(values[:2] + values[3:23])
-                elif values[22] == 1:
-                    labels.append(1)
-                    data.append(values[:2] + values[3:23])
-                else:
-                    continue
-                
-            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)
+    data = np.delete(data, [2] + list(range(23, 28)), axis=1)
+    
+    scaler = StandardScaler()
+    data = scaler.fit_transform(data)
+    
+    return data, target_variable
 
-
-    return data, labels
+def accuracy(X, y, weights):
+    """计算准确率。"""
+    predictions = predict_logreg(X, weights)
+    return np.mean(predictions == y)
 
 if __name__ == "__main__":
-    # 加载训练集
-    X_train, y_train = load_data("./data/horse-colic.data")
+    X_train, y_train = load_data("./horse-colic.data")
+    X_test, y_test = load_data("./horse-colic.test")
 
-    # 加载测试集
-    X_test, y_test = load_data("./data/horse-colic.test")
+    # 特征标准化
+    scaler = StandardScaler()
+    X_train = scaler.fit_transform(X_train)
+    X_test = scaler.transform(X_test)
 
-    # 训练对率回归模型
-    other_params = {
-        'learning_rate': 0.01,
-        'iterations': 1000,
-        'lambda_reg': 0.01,
-        'batch_size': 32
-    }
-    weights = train_logreg(X_train, y_train, other_params=other_params)
+    # 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)
+
+    # 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}")
 
-    # 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]}")