更新 function.py

function.py

@@ -2,6 +2,7 @@
 import numpy as np
 from sklearn.preprocessing import StandardScaler
 from itertools import product
+from sklearn.ensemble import RandomForestClassifier
 
 """
 实验说明:
@@ -42,9 +43,10 @@ def train_logreg(X, y, learning_rate=0.05, iterations=1500, batch_size=64, regul
     - numpy array: 训练得到的权重。
     """
         m, n = X.shape
-    weights = np.random.randn(n) * 0.01  # 随机初始化权重
+    weights = np.random.randn(n) * 0.01
+
     for i in range(iterations):
-        indices = np.random.permutation(m)  # 随机打乱数据
+        indices = np.random.permutation(m)
         X_shuffled = X[indices]
         y_shuffled = y[indices]
 
@@ -63,6 +65,10 @@ def train_logreg(X, y, learning_rate=0.05, iterations=1500, batch_size=64, regul
 
             weights -= learning_rate * gradient
 
+        # 学习率衰减
+        if i % 100 == 0:
+            learning_rate *= 0.95
+
     return weights
 
 
@@ -93,13 +99,12 @@ def load_data(filepath):
     - np.array: 特征数据。
     - np.array: 标签数据。
     """
-    data = []
+    data, labels = [], []
-    labels = []
+
     with open(filepath, 'r') as f:
-        for line in f.readlines():
+        for line in f:
             line = line.strip().split()
-            if len(line) >= 1 and line[-1].isdigit():
+            if line and line[-1].isdigit():
-                # 将缺失值 '?' 填充为 0，并转换为浮点数
                 line_data = [1] + [0 if x == '?' else float(x) for x in line[:-1]]
                 data.append(line_data)
                 labels.append(int(line[-1]))
@@ -107,25 +112,44 @@ def load_data(filepath):
     data = np.array(data)
     labels = np.array(labels)
 
-    # 选择特征，合并目标变量
+    # 映射标签
-    target_variable = labels
+    labels[np.isin(labels, [2, 3])] = 0
-    target_variable[(target_variable == 2) | (target_variable == 3)] = 0  # 合并死亡和安乐死为0
 
-    # 去掉特征3和特征24~28
+    # 删除不需要的列
-    data = np.delete(data, [2] + list(range(23, 28)), axis=1)  # 特征3的索引是2，特征24-28的索引是23-27
+    data = np.delete(data, [2] + list(range(23, 28)), axis=1)
 
+    # 数据标准化
     scaler = StandardScaler()
     data = scaler.fit_transform(data)
 
-    return data, target_variable
+    return data, labels
 
+def accuracy(X, y, weights):
+    """计算模型准确率"""
+    predictions = predict_logreg(X, weights)
+    return np.mean(predictions == y)
 
 if __name__ == "__main__":
-    X_train, y_train = load_data("./data/horse-colic.data")
+    # 加载数据
-    X_test, y_test = load_data("./data/horse-colic.test")
+    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, learning_rate=0.05, iterations=1000, batch_size=16, regularization='L1', lambda_reg=0.05)
+    # 使用随机森林进行初步预测
+    rf_model = RandomForestClassifier(n_estimators=100, random_state=42)
+    rf_model.fit(X_train, y_train)
 
-    # 计算并输出最终测试集的准确率
+    rf_predictions_train = rf_model.predict(X_train)
-    final_accuracy = accuracy(X_test, y_test, final_weights)
+    rf_predictions_test = rf_model.predict(X_test)
+
+    # 将随机森林预测的结果作为新的特征
+    X_train_combined = np.column_stack((X_train, rf_predictions_train))
+    X_test_combined = np.column_stack((X_test, rf_predictions_test))
+
+    # 使用逻辑回归进行训练
+    final_weights = train_logreg(X_train_combined, y_train, learning_rate=0.01,
+                                 iterations=5000, batch_size=32,
+                                 regularization='L1', lambda_reg=0.01)
+
+    # 计算准确率
+    final_accuracy = accuracy(X_test_combined, y_test, final_weights)
     print(f"最终测试集的准确率: {final_accuracy:.4f}")