更新 function.py

function.py

@@ -24,62 +24,87 @@ import numpy as np
 id = "202210423222"
 name = "邓龙树"
 
-# user_code.py
+# user_cod
-
 import numpy as np
 from sklearn.preprocessing import StandardScaler
 
-def sigmoid(intX):
-    return 1.0 / (1 + np.exp(-intX))
 
-def train_logreg(X, y, numIter=150):
+def sigmoid(z):
+    return 1.0 / (1 + np.exp(-z))
+
+
+def train_logreg(X, y, learning_rate=0.05, iterations=1500, batch_size=64):
     m, n = X.shape
-    weights = np.zeros(n)  # 初始化权重为0而不是1
+    weights = np.random.randn(n) * 0.01
-    for j in range(numIter):
+    best_weights = weights.copy()
-        dataIndex = list(range(m))
+    best_accuracy = 0
-        for i in range(m):
+    wait = 0
-            alpha = 4 / (1.0 + j + i) + 0.01
+
-            randIndex = int(np.random.uniform(0, len(dataIndex)))
+    for i in range(iterations):
-            h = sigmoid(np.dot(X[randIndex], weights))
+        indices = np.random.permutation(m)
-            error = y[randIndex] - h
+        X_shuffled = X[indices]
-            weights = weights + alpha * error * X[randIndex]
+        y_shuffled = y[indices]
-            del(dataIndex[randIndex])
+
-    return weights
+        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)
+            h = sigmoid(z)
+            gradient = np.dot(X_batch.T, (h - y_batch)) / len(y_batch)
+
+            weights -= learning_rate * gradient
+
+        # 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 best_weights
+
 
 def predict_logreg(X, weights):
-    predictions = []
+    z = np.dot(X, weights)
-    for x in X:
+    h = sigmoid(z)
-        prob = sigmoid(np.dot(x, weights))
+    return np.where(h > 0.5, 1, 0)
-        predictions.append(1 if prob > 0.5 else 0)
-    return predictions
 
 def load_data(filepath):
     data = []
     labels = []
     with open(filepath, 'r') as f:
-        lines = f.readlines()
+        for line in f:
-        for line in lines:
             line = line.strip().split()
             if len(line) >= 1 and line[-1].isdigit():
-                line_data = [1] + [0 if x == '?' else float(x) for x in line[:-1]]
+                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 = labels
+
-    target_variable[np.logical_or(target_variable == 2, target_variable == 3)] = 0
+    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
 
+
 def accuracy(X, y, weights):
     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)
+
+    # 标准化数据
+    scaler = StandardScaler()
+    X_train = scaler.fit_transform(X_train)
+    X_test = scaler.transform(X_test)
+
+    final_weights = train_logreg(X_train, y_train, learning_rate=0.001, iterations=1500, batch_size=64)
+
     final_accuracy = accuracy(X_test, y_test, final_weights)
     print(f"最终测试集的准确率: {final_accuracy:.4f}")