更新 function.py

function.py

@@ -27,11 +27,13 @@ name = "章程鸿"
 
 # 这里写自己的代码实现
 import numpy as np
+from sklearn.preprocessing import StandardScaler
 
 def sigmoid(z):
-    return 1 / (1 + np.exp(-z))
+    return 1.0 / (1 + np.exp(-z))
 
-def train_logreg(X, y, learning_rate=0.01, iterations=1000):
+
+def train_logreg(X, y, learning_rate=0.05, iterations=1500, batch_size=64):
     """
     对率回归训练函数。
 
@@ -44,18 +46,36 @@ def train_logreg(X, y, learning_rate=0.01, iterations=1000):
     - numpy array: 训练得到的权重。
     """
     m, n = X.shape
-    weights = np.zeros(n)
-    bias = 0
-    for _ in range(iterations):
-        z = np.dot(X, weights) + bias
-        h = sigmoid(z)
-        dw = (1/m) * np.dot(X.T, (h - y))
-        db = (1/m) * np.sum(h - y)
-        weights -= learning_rate * dw
-        bias -= learning_rate * db
-    return weights
+    weights = np.random.randn(n) * 0.01
+    best_weights = weights.copy()
+    best_accuracy = 0
+    wait = 0
 
-def predict_logreg(inX, weights):
+    for i in range(iterations):
+        indices = np.random.permutation(m)
+        X_shuffled = X[indices]
+        y_shuffled = y[indices]
+
+        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):
     """
     对率回归预测函数。
 
@@ -66,10 +86,9 @@ def predict_logreg(inX, weights):
     Returns:
     - int: 预测的分类标签。
     """
-    z = np.dot(inX, weights)
+    z = np.dot(X, weights)
     h = sigmoid(z)
-    return 1 if h >= 0.5 else 0
-
+    return np.where(h > 0.5, 1, 0)
 # 这里也写自己的代码实现
 def load_data(filepath):
     """
@@ -83,38 +102,37 @@ def load_data(filepath):
     - np.array: 标签数据。
     """
     data = []
-    with open(filepath, 'r') as file:
-        for line in file:
-            # 清理无效数据
-            cleaned_line = line.strip().replace('?', '0')  # 将问号替换为0
-            data.append([float(x) for x in cleaned_line.split()])  # 转换为浮点数
+     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)
-    X = data[:, :-1]
-    y = data[:, -1]
-    return X, y
-def standardize(X):
-    """
-    标准化特征数据，使其均值为0，标准差为1。
+    labels = np.array(labels)
 
-    Args:
-    - X (numpy array): 特征数据。
+    target_variable = np.where((labels == 2) | (labels == 3), 0, labels)
 
-    Returns:
-    - numpy array: 标准化后的特征数据。
-    """
-    mean = np.mean(X, axis=0)
-    std = np.std(X, axis=0)
-    return (X - mean) / std
+    return data, target_variable
 
+def accuracy(X, y, weights):
+    predictions = predict_logreg(X, weights)
+    return np.mean(predictions == y)
 
 if __name__ == "__main__":
-    # 加载训练集
-    X_train, y_train = load_data("./data/horse-colic.data")
+    X_train, y_train = load_data("./horse-colic.data")
+    X_test, y_test = load_data("./horse-colic.test")
 
-    # 加载测试集
-    X_test, y_test = load_data("./data/horse-colic.test")
+    # 标准化数据
+    scaler = StandardScaler()
+    X_train = scaler.fit_transform(X_train)
+    X_test = scaler.transform(X_test)
 
-    # 测试单个数据
-    weights = train_logreg(X_train, y_train, learning_rate=0.01, iterations=1000)
-    y_pred = predict_logreg(X_test[11], weights)
-    print(f"预测结果: {y_pred}, 实际结果: {y_test[11]}")
+    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}")