更新 function.py

function.py

@@ -27,14 +27,14 @@ name = "章程鸿"
 
 # 这里写自己的代码实现
 import numpy as np
-from sklearn.metrics import accuracy_score
 
-# 定义sigmoid函数
 def sigmoid(z):
     return 1 / (1 + np.exp(-z))
 
-# 训练逻辑回归模型
-def train_logreg(X, y, learning_rate, iterations=1000):
+def train_logreg(X, y, learning_rate=0.005, iterations=1000):
+    """
+    修改处：将学习率从 0.01 调整为 0.005。
+    """
     m, n = X.shape
     weights = np.zeros(n)
     bias = 0
@@ -45,15 +45,13 @@ def train_logreg(X, y, learning_rate, iterations=1000):
         db = (1/m) * np.sum(h - y)
         weights -= learning_rate * dw
         bias -= learning_rate * db
-    return weights, bias
+    return weights
 
-# 使用逻辑回归模型进行预测
-def predict_logreg(inX, weights, bias):
-    z = np.dot(inX, weights) + bias
+def predict_logreg(inX, weights):
+    z = np.dot(inX, weights)
     h = sigmoid(z)
     return 1 if h >= 0.5 else 0
 
-# 加载数据
 def load_data(filepath):
     data = []
     with open(filepath, 'r') as file:
@@ -69,36 +67,38 @@ def load_data(filepath):
     y = data[:, -1]
     return X, y
 
-# 寻找最佳学习率
-def find_best_learning_rate(X, y, learning_rates, iterations=1000):
+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_learning_rate = None
+    best_lr = None
     best_weights = None
-    best_bias = None
-    for rate in learning_rates:
-        weights, bias = train_logreg(X, y, rate, iterations)
-        y_pred = np.array([predict_logreg(x, weights, bias) for x in X])
-        accuracy = accuracy_score(y, y_pred)
+    
+    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_learning_rate = rate
+            best_lr = lr
             best_weights = weights
-            best_bias = bias
-    return best_learning_rate, best_accuracy, best_weights, best_bias
+    
+    return best_lr, best_accuracy, best_weights
 
 if __name__ == "__main__":
     X_train, y_train = load_data("./data/horse-colic.data")
     X_test, y_test = load_data("./data/horse-colic.test")
     
-    # 定义要尝试的学习率列表
-    learning_rates = np.linspace(0.001, 0.1, 50)
+    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}")
     
-    # 寻找最佳学习率
-    best_learning_rate, best_accuracy, best_weights, best_bias = find_best_learning_rate(X_train, y_train, learning_rates)
-    
-    print(f"最佳学习率: {best_learning_rate}")
-    print(f"最佳准确率: {best_accuracy}")
-    
-    # 使用最佳权重和偏置进行预测
-    y_pred = predict_logreg(X_test[11], best_weights, best_bias)
+    # 使用最佳学习率训练最终模型
+    y_pred = predict_logreg(X_test[11], best_weights)
     print(f"预测结果: {y_pred}, 实际结果: {y_test[11]}")