更新 function.py

function.py

@@ -1,108 +1,133 @@
 import numpy as np
+from sklearn.impute import SimpleImputer
+from sklearn.feature_selection import SelectKBest, f_classif
 
+# 填写学号和姓名
 id = "202210423213"
 name = "熊浩燃"
 
-# 对率回归训练函数，包含加权损失、正则化、学习率调度和提前停止
-def train_logreg(X, y, learning_rate=0.01, iterations=1000, regularization=0.01, early_stopping_rounds=100, class_weights={0: 1, 1: 1}):
-    weights = np.zeros(X.shape[1])
-    min_loss = float('inf')
-    stopping_step = 0
+def load_data(filepath, k_features=20):
+    """
+    从文件中加载数据并进行预处理，包括缺失值填充和特征选择。
 
-    for i in range(iterations):
-        z = np.dot(X, weights)
-        predictions = 1 / (1 + np.exp(-z))
+    Args:
+    - filepath (str): 数据文件路径。
+    - k_features (int): 选择的特征数量。
 
-        loss = -np.mean(class_weights[1] * y * np.log(predictions) + 
-                        class_weights[0] * (1 - y) * np.log(1 - predictions)) + regularization * np.sum(weights**2)
-
-        if loss < min_loss:
-            min_loss = loss
-            stopping_step = 0
-        else:
-            stopping_step += 1
-        if stopping_step >= early_stopping_rounds:
-            print("提前停止于迭代:", i)
-            break
-
-        gradient = (np.dot(X.T, (predictions - y)) + regularization * weights) / y.size
-        weights -= learning_rate * gradient
-
-        if i % 100 == 0 and i != 0:
-            learning_rate *= 0.9  # 每100轮衰减学习率
-            print(f"迭代 {i}，损失: {loss}，学习率: {learning_rate}")
-
-    return weights
-
-# 对率回归预测函数，带有自定义阈值
-def predict_logreg(inX, weights, threshold=0.6):
-    probability = 1 / (1 + np.exp(-np.dot(inX, weights)))
-    return 1 if probability >= threshold else 0
-
-# 数据加载函数，包含缺失值填充
-def load_data(filepath):
+    Returns:
+    - np.array: 特征数据。
+    - np.array: 标签数据。
+    """
     data = []
     labels = []
     with open(filepath, 'r') as file:
         for line in file:
-            fields = line.strip().split()
-            features = [float(x) if x != '?' else None for x in fields[:-1]]
-            label = float(fields[-1])
-            data.append(features)
-            labels.append(label)
+            line = line.strip().split()
+            if line:
+                features = []
+                for feature in line[:-1]:  # 最后一个元素是标签
+                    try:
+                        features.append(float(feature))
+                    except ValueError:
+                        features.append(np.nan)  # 用 NaN 表示缺失值
+                label = int(line[-1])
+                data.append(features)
+                labels.append(label)
 
-    data = np.array(data, dtype=float)
-    labels = np.array(labels, dtype=float)
+    # 转换为 numpy 数组
+    data = np.array(data)
+    labels = np.array(labels)
 
-    col_means = np.nanmean(data, axis=0)
-    indices = np.where(np.isnan(data))
-    data[indices] = np.take(col_means, indices[1])
+    # 使用SimpleImputer填充NaN
+    imputer = SimpleImputer(strategy='mean')
+    data = imputer.fit_transform(data)
+
+    # 特征标准化，避免除零错误
+    mean = data.mean(axis=0)
+    std_dev = data.std(axis=0)
+    std_dev[std_dev == 0] = 1  # 如果标准差为0，将其设为1，避免除以零
+    data = (data - mean) / std_dev
+
+    # 特征选择
+    selector = SelectKBest(f_classif, k=k_features)
+    data = selector.fit_transform(data, labels)
 
     return data, labels
 
-# 暴力搜索函数
-def brute_force_search(X, y, X_test, y_test, learning_rates, iterations_list, regularizations, class_weights_list, thresholds):
-    best_params = {}
-    best_weights = None
-    best_accuracy = 0
+def sigmoid(z):
+    """
+    Sigmoid激活函数，用于对率回归模型。
 
-    for lr in learning_rates:
-        for iters in iterations_list:
-            for reg in regularizations:
-                for cw in class_weights_list:
-                    for threshold in thresholds:
-                        print(f"参数组合: 学习率={lr}, 迭代次数={iters}, 正则化={reg}, 类别权重={cw}, 阈值={threshold}")
-                        weights = train_logreg(X, y, learning_rate=lr, iterations=iters, regularization=reg, class_weights=cw)
-                        y_pred = [predict_logreg(x, weights, threshold=threshold) for x in X_test]
-                        accuracy = np.mean(y_pred == y_test)
-                        print(f"当前组合的测试集准确率: {accuracy}")
+    Args:
+    - z (numpy array): 输入数据。
 
-                        if accuracy > best_accuracy:
-                            best_accuracy = accuracy
-                            best_weights = weights
-                            best_params = {'learning_rate': lr, 'iterations': iters, 'regularization': reg, 'class_weights': cw, 'threshold': threshold}
+    Returns:
+    - numpy array: Sigmoid函数输出值。
+    """
+    return 1 / (1 + np.exp(-z))
 
-    print("最佳参数组合:", best_params)
-    print("最佳准确率:", best_accuracy)
-    return best_weights, best_params
+def train_logreg(X, y, initial_lr=0.005, iterations=5000, regularization=0.01, decay=0.0001):
+    """
+    对率回归训练函数，包含学习率衰减策略。
 
+    Args:
+    - X (numpy array): 特征数据。
+    - y (numpy array): 标签数据。
+    - initial_lr (float): 初始学习率。
+    - iterations (int): 迭代次数。
+    - regularization (float): 正则化强度。
+    - decay (float): 学习率衰减系数。
+
+    Returns:
+    - numpy array: 训练得到的权重。
+    """
+    m, n = X.shape
+    weights = np.zeros(n)
+    learning_rate = initial_lr
+
+    for i in range(iterations):
+        z = np.dot(X, weights)
+        predictions = sigmoid(z)
+        errors = y - predictions
+        gradient = np.dot(X.T, errors) / m - regularization * weights / m
+        weights += learning_rate * gradient
+
+        # 学习率衰减
+        learning_rate = initial_lr / (1 + decay * i)
+
+    return weights
+
+def predict_logreg(inX, weights, threshold=0.5):
+    """
+    对率回归预测函数，包含可调阈值。
+
+    Args:
+    - inX (numpy array): 输入待分类的样本。
+    - weights (numpy array): 训练得到的权重。
+    - threshold (float): 判定阈值，默认为0.5。
+
+    Returns:
+    - int: 预测的分类标签。
+    """
+    probability = sigmoid(np.dot(inX, weights))
+    return 1 if probability >= threshold else 2
+
+# 测试代码
 if __name__ == "__main__":
-    # 加载训练集
-    X_train, y_train = load_data("./data/horse-colic.data")
-    X_test, y_test = load_data("./data/horse-colic.test")
+    # 加载数据并选择前20个最重要的特征
+    X_train, y_train = load_data("./data/horse-colic.data", k_features=20)
+    X_test, y_test = load_data("./data/horse-colic.test", k_features=20)
 
-    # 调整后的超参数组合
-    learning_rates = [0.0001, 0.001, 0.01, 0.05, 0.1]
-    iterations_list = [1000, 2000, 5000, 10000]
-    regularizations = [0.01, 0.1, 1.0, 10.0]
-    class_weights_list = [{0: 1, 1: 2}, {0: 1, 1: 3}, {0: 1, 1: 4}, {0: 1, 1: 5}]
-    thresholds = [0.5, 0.55, 0.6, 0.65, 0.7]
+    # 训练模型
+    weights = train_logreg(X_train, y_train, initial_lr=0.005, iterations=5000, regularization=0.01, decay=0.0001)
 
-    # 进行暴力搜索找到最佳参数组合
-    best_weights, best_params = brute_force_search(X_train, y_train, X_test, y_test, learning_rates, iterations_list, regularizations, class_weights_list, thresholds)
-    print("最佳权重:", best_weights)
+    # 模型评估
+    correct_predictions = 0
+    for i in range(len(X_test)):
+        y_pred = predict_logreg(X_test[i], weights, threshold=0.5)
+        if y_pred == y_test[i]:
+            correct_predictions += 1
+        print(f"预测结果: {y_pred}, 实际结果: {y_test[i]}")
 
-    # 使用最佳权重和阈值在测试集上评估
-    y_pred = [predict_logreg(x, best_weights, threshold=best_params['threshold']) for x in X_test]
-    accuracy = np.mean(y_pred == y_test)
-    print(f"最终测试集准确率: {accuracy}")
+    accuracy = correct_predictions / len(X_test)
+    print(f"测试集准确率: {accuracy:.2f}")