更新 function.py

function.py

@@ -29,34 +29,50 @@ name = "章程鸿"
 import numpy as np
 from sklearn.preprocessing import MinMaxScaler
 from sklearn.model_selection import train_test_split
-def load_data(filepath):
-    data, labels = [], []
-    with open(filepath, 'r') as f:
-        for line in f:
-            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)
+def sigmoid(z):
+    return 1.0 / (1 + np.exp(-z))
 
-    # 检查特征数量
-    num_features = data.shape[1]
+def 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)
+    gradient += (lambda_reg / len(y_batch)) * weights  # L2正则化
+    return gradient
 
-    # 特征选择：去掉特征3（索引2）和特征24~28（索引23~26），确保索引有效
-    indices_to_delete = [2]  # 特征3
-    if num_features > 24:  # 确保特征数量足够
-        indices_to_delete += list(range(24, 27))  # 特征24到27（索引23到26）
+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
+    best_weights = weights.copy()
+    best_accuracy = 0
 
-    # 删除特征
-    data = np.delete(data, indices_to_delete, axis=1)
+    for _ in range(iterations):
+        indices = np.random.permutation(m)
+        X_shuffled = X[indices]
+        y_shuffled = y[indices]
 
-    # 将标签二分类化，特征23（索引22）取值2和3合并为0，其余为1
-    target_variable = np.where((labels == 2) | (labels == 3), 0, 1)
+        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)
+            weights -= learning_rate * gradient
 
-    return data, target_variable
+        # 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()
+
+        # 动态调整学习率
+        if _ % 100 == 0 and train_accuracy > 0.95:  # 达到高准确率时减小学习率
+            learning_rate *= 0.9
+
+    return best_weights
+
+def predict_logreg(X, weights):
+    z = np.dot(X, weights)
+    h = sigmoid(z)
+    return np.where(h >= 0.5, 1, 0)
     
 def load_data(filepath):
     data, labels = [], []
@@ -73,7 +89,6 @@ def load_data(filepath):
 
     # 检查特征数量
     num_features = data.shape[1]
-    print(f"特征数量: {num_features}")
 
     # 特征选择：去掉特征3（索引2）和特征24~28（索引23~26），确保索引有效
     indices_to_delete = [2]  # 特征3