更新 function.py

function.py

@@ -31,9 +31,17 @@ import numpy as np
 def sigmoid(z):
     return 1 / (1 + np.exp(-z))
 
-def train_logreg(X, y, learning_rate=0.005, iterations=1000):
+def train_logreg(X, y, learning_rate=0.01, iterations=1000):
     """
-    修改处：将学习率从 0.01 调整为 0.005。
+    对率回归训练函数。
+
+    Args:
+    - X (numpy array): 特征数据。
+    - y (numpy array): 标签数据。
+    - other_params (str): 其它参数，可选设置。若需设置其它参数，必须设置其默认值，否则将**无法通过**自动评测，**成绩为零**。
+
+    Returns:
+    - numpy array: 训练得到的权重。
     """
     m, n = X.shape
     weights = np.zeros(n)
@@ -48,16 +56,38 @@ def train_logreg(X, y, learning_rate=0.005, iterations=1000):
     return weights
 
 def predict_logreg(inX, weights):
+    """
+    对率回归预测函数。
+
+    Args:
+    - inX (numpy array): 输入待分类的样本。
+    - weights (numpy array): 训练得到的权重。
+
+    Returns:
+    - int: 预测的分类标签。
+    """
     z = np.dot(inX, weights)
     h = sigmoid(z)
     return 1 if h >= 0.5 else 0
 
 def load_data(filepath):
+    """
+    从文件中加载数据，若不自行正确实现，则无法通过评测，**不记录成绩**。
+
+    Args:
+    - directory (str): 数据文件路径。
+
+    Returns:
+    - np.array: 特征数据。
+    - 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')
             values = [float(x) for x in cleaned_line.split()]
+            # 处理目标变量
             if values[22] in [2, 3]:
                 values[22] = 0
             new_values = values[:2] + values[3:23]
@@ -67,38 +97,16 @@ def load_data(filepath):
     y = data[:, -1]
     return X, y
 
-def calculate_accuracy(X, y, weights):
-    predictions = [predict_logreg(x, weights) for x in X]
-    correct_predictions = sum([1 for pred, actual in zip(predictions, y) if pred == actual])
-    accuracy = correct_predictions / len(y)
-    return accuracy
-
-def find_best_learning_rate(X_train, y_train, X_test, y_test, learning_rates, iterations=1000):
-    best_accuracy = 0
-    best_lr = None
-    best_weights = None
-    
-    for lr in learning_rates:
-        weights = train_logreg(X_train, y_train, learning_rate=lr, iterations=iterations)
-        accuracy = calculate_accuracy(X_test, y_test, weights)
-        print(f"学习率: {lr}, 测试集准确率: {accuracy}")
-        
-        if accuracy > best_accuracy:
-            best_accuracy = accuracy
-            best_lr = lr
-            best_weights = weights
-    
-    return best_lr, best_accuracy, best_weights
-
 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")
-    
-    learning_rates = [0.0001, 0.001, 0.005, 0.01, 0.05, 0.1]  # 不同的学习率
-    best_lr, best_accuracy, best_weights = find_best_learning_rate(X_train, y_train, X_test, y_test, learning_rates)
 
-    print(f"最佳学习率: {best_lr}, 测试集准确率: {best_accuracy}")
-    
-    # 使用最佳学习率训练最终模型
-    y_pred = predict_logreg(X_test[11], best_weights)
+    # 加载测试集
+    X_test, y_test = load_data("./data/horse-colic.test")
+
+    # 训练对率回归模型
+    weights = train_logreg(X_train, y_train, learning_rate=0.001, iterations=1000)  # 修改学习率
+
+    # 测试单个数据
+    y_pred = predict_logreg(X_test[11], weights)
     print(f"预测结果: {y_pred}, 实际结果: {y_test[11]}")