更新 function.py

function.py

@@ -28,14 +28,28 @@ name = "邓龙树"
 import numpy as np
 from sklearn.preprocessing import StandardScaler
 
+def sigmoid(intX):  #激活函数，逻辑回归中，将线性组合转换为概率
+    return 1.0 / (1 + np.exp(-intX))
+
+def train_logreg(X, y, numIter=150):   #训练逻辑回归模型的函数，使用梯度下降算法。
 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。"""
+
+def train_logreg(X, y, learning_rate=0.05, iterations=1500, batch_size=64):
     m, n = X.shape
-    weights = np.random.randn(n) * 0.01  # 初始化权重
+    weights = np.zeros(n)  # 初始化权重为0而不是1
+    for j in range(numIter):
+        dataIndex = list(range(m))
+        for i in range(m):
+            alpha = 4 / (1.0 + j + i) + 0.01
+            randIndex = int(np.random.uniform(0, len(dataIndex)))
+            h = sigmoid(np.dot(X[randIndex], weights))
+            error = y[randIndex] - h
+            weights = weights + alpha * error * X[randIndex]
+            del(dataIndex[randIndex])
+    return weights
+    weights = np.random.randn(n) * 0.01
     best_weights = weights.copy()
     best_accuracy = 0
     wait = 0
@@ -50,7 +64,7 @@ def train_logreg(X, y, learning_rate=0.05, iterations=1500, batch_size=64, reg_l
             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
+            gradient = np.dot(X_batch.T, (h - y_batch)) / len(y_batch)
 
             weights -= learning_rate * gradient
 
@@ -63,23 +77,25 @@ def train_logreg(X, y, learning_rate=0.05, iterations=1500, batch_size=64, reg_l
         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。"""
+    predictions = []
+    for x in X:
+        prob = sigmoid(np.dot(x, weights))
+        predictions.append(1 if prob > 0.5 else 0)
+    return predictions
     z = np.dot(X, weights)
     h = sigmoid(z)
     return np.where(h > 0.5, 1, 0)
 
 def load_data(filepath):
-    """加载数据函数。"""
     data = []
     labels = []
     with open(filepath, 'r') as f:
+        lines = f.readlines()
+        for line in lines:
         for line in f:
             line = line.strip().split()
             if len(line) >= 1 and line[-1].isdigit():
@@ -89,35 +105,34 @@ 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)
-    
+    target_variable = labels
+    target_variable[np.logical_or(target_variable == 2, target_variable == 3)] = 0
+    data = np.delete(data, [2] + list(range(23, 28)), axis=1)
     scaler = StandardScaler()
     data = scaler.fit_transform(data)
-    
+
+    target_variable = np.where((labels == 2) | (labels == 3), 0, labels)
+
     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__':
+
 if __name__ == "__main__":
     X_train, y_train = load_data("./horse-colic.data")
     X_test, y_test = load_data("./horse-colic.test")
+    final_weights = train_logreg(X_train, y_train)
 
-    # 特征标准化
+    # 标准化数据
     scaler = StandardScaler()
     X_train = scaler.fit_transform(X_train)
     X_test = scaler.transform(X_test)
 
-    # 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=0.001, iterations=1500, batch_size=64)
 
-    # 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}")
-