更新 function.py

function.py

@@ -27,7 +27,7 @@ name = "章程鸿"
 
 # 这里写自己的代码实现
 import numpy as np
-from sklearn.model_selection import KFold
+
 def sigmoid(z):
     return 1 / (1 + np.exp(-z))
 
@@ -92,21 +92,20 @@ def load_data(filepath):
     X = data[:, :-1]
     y = data[:, -1]
     return X, y
-def cross_validate(X, y, k=5, learning_rate=0.01, iterations=1000):
-    kf = KFold(n_splits=k)
-    accuracies = []
+def standardize(X):
+    """
+    标准化特征数据，使其均值为0，标准差为1。
     
-    for train_index, test_index in kf.split(X):
-        X_train, X_test = X[train_index], X[test_index]
-        y_train, y_test = y[train_index], y[test_index]
+    Args:
+    - X (numpy array): 特征数据。
     
-        weights = train_logreg(X_train, y_train, learning_rate, iterations)
-        predictions = [predict_logreg(x, weights) for x in X_test]
+    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
 
-        accuracy = np.mean(predictions == y_test)
-        accuracies.append(accuracy)
-
-    return np.mean(accuracies)
 
 if __name__ == "__main__":
     # 加载训练集
@@ -115,11 +114,6 @@ if __name__ == "__main__":
     # 加载测试集
     X_test, y_test = load_data("./data/horse-colic.test")
 
-    # 进行 K 折交叉验证
-    k = 5  # 设置折数
-    cv_accuracy = cross_validate(X_train, y_train, k=k, learning_rate=0.01, iterations=1000)
-    print(f"{k}-折交叉验证的平均准确率: {cv_accuracy:.2f}")
-
     # 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)