更新 function.py

function.py

@@ -28,14 +28,14 @@ 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, PolynomialFeatures
+from sklearn.preprocessing import StandardScaler
 from sklearn.model_selection import train_test_split, KFold
 
 def sigmoid(z):
     """Sigmoid 激活函数。"""
     return 1 / (1 + np.exp(-z))
 
-def train_logreg(X, y, learning_rate=0.1, iterations=2000, lambda_reg=0.01, batch_size=32):
+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
@@ -61,7 +61,11 @@ def train_logreg(X, y, learning_rate=0.1, iterations=2000, lambda_reg=0.01, batc
             weights -= learning_rate * gradient
 
         # 动态调整学习率
-        learning_rate *= 0.99  # 每次迭代稍微减小学习率
+        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 i % 100 == 0:  # 每100次迭代输出一次学习率
+            print(f"Iteration {i}, Learning Rate: {learning_rate}")
 
     return weights
 
@@ -81,7 +85,7 @@ def load_data(filepath):
             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
@@ -89,7 +93,7 @@ def load_data(filepath):
                     labels.append(1)  # 生存
                 else:
                     continue  # 无效标签，丢弃
-
+                
                 # 用0填充缺失值
                 values = [0 if v == 0 else v for v in values]  # 直接用0填充
                 data.append(values[:2] + values[3:23])  # 保留特征1, 2 和特征4-23
@@ -102,25 +106,20 @@ def load_data(filepath):
     return data, labels
 
 def preprocess_data(X):
-    """特征标准化并增加多项式特征。"""
+    """特征标准化。"""
     scaler = StandardScaler()
-    X_scaled = scaler.fit_transform(X)
+    return scaler.fit_transform(X)
-
-    # 添加多项式特征
-    poly = PolynomialFeatures(degree=2, include_bias=False)
-    X_poly = poly.fit_transform(X_scaled)
-
-    return X_poly
 
 if __name__ == "__main__":
-    # 加载数据集
+    # 加载训练集
-    X, y = load_data("./data/horse-colic.data")
+    X_train, y_train = load_data("./data/horse-colic.data")
+    
+    # 加载测试集
+    X_test, y_test = load_data("./data/horse-colic.test")
 
     # 归一化数据
-    X = preprocess_data(X)
+    X_train = preprocess_data(X_train)
-
+    X_test = preprocess_data(X_test)
-    # 使用 train_test_split 打乱并随机抽取数据
-    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
 
     # K折交叉验证
     k = 5
@@ -133,7 +132,7 @@ if __name__ == "__main__":
 
         # 训练逻辑回归模型，设置 batch size
         batch_size = 32
-        weights = train_logreg(X_train_kf, y_train_kf, learning_rate=0.1, iterations=2000, lambda_reg=0.01, batch_size=batch_size)
+        weights = train_logreg(X_train_kf, y_train_kf, learning_rate=0.01, iterations=5000, lambda_reg=0.01, batch_size=batch_size)
 
         # 验证模型
         val_predictions = [predict_logreg(X_val_kf[i], weights) for i in range(len(X_val_kf))]
@@ -144,7 +143,16 @@ if __name__ == "__main__":
     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
+    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]}")
 
+
+
+
+