更新 function.py

function.py

@@ -29,7 +29,7 @@ name = "章程鸿"
 import numpy as np
 import pandas as pd
 from sklearn.preprocessing import StandardScaler
-from sklearn.model_selection import train_test_split, KFold
+from sklearn.model_selection import KFold
 
 def sigmoid(z):
     """Sigmoid 激活函数。"""
@@ -69,14 +69,14 @@ def train_logreg(X, y, learning_rate=0.01, iterations=5000, lambda_reg=0.01, bat
 
     return weights
 
-def predict_logreg(inX, weights):
+def predict_logreg(inX, weights, threshold=0.5):
     """逻辑回归预测函数。"""
     z = np.dot(inX, weights)
     prediction_prob = sigmoid(z)
-    return 1 if prediction_prob >= 0.5 else 0
+    return 1 if prediction_prob >= threshold else 0
 
 def load_data(filepath):
-    """加载数据并处理缺失值。"""
+    """加载数据并处理缺失值与规划。"""
     data = []
     labels = []
 
@@ -103,12 +103,11 @@ def load_data(filepath):
     data = np.array(data)
     labels = np.array(labels)
 
-    return data, labels
-
-def preprocess_data(X):
-    """特征标准化。"""
+    # 数据标准化
     scaler = StandardScaler()
-    return scaler.fit_transform(X)
+    data = scaler.fit_transform(data)  # 在这里进行标准化处理
+
+    return data, labels
 
 if __name__ == "__main__":
     # 加载训练集
@@ -117,10 +116,6 @@ if __name__ == "__main__":
     # 加载测试集
     X_test, y_test = load_data("./data/horse-colic.test")
 
-    # 归一化数据
-    X_train = preprocess_data(X_train)
-    X_test = preprocess_data(X_test)
-
     # K折交叉验证
     k = 5
     kf = KFold(n_splits=k, shuffle=True, random_state=42)
@@ -135,7 +130,7 @@ if __name__ == "__main__":
         weights = train_logreg(X_train_kf, y_train_kf, learning_rate=0.01, iterations=5000, lambda_reg=0.01, batch_size=batch_size)
 
         # 验证模型
-        val_predictions = [predict_logreg(X_val_kf[i], weights) for i in range(len(X_val_kf))]
+        val_predictions = [predict_logreg(X_val_kf[i], weights, threshold=0.5) for i in range(len(X_val_kf))]
         accuracy = np.mean(val_predictions == y_val_kf)
         accuracies.append(accuracy)
 
@@ -144,13 +139,15 @@ if __name__ == "__main__":
     print(f"平均准确率: {np.mean(accuracies)}")
 
     # 在测试集上测试模型
-    test_predictions = [predict_logreg(X_test[i], weights) for i in range(len(X_test))]
+    test_predictions = [predict_logreg(X_test[i], weights, threshold=0.5) for i in range(len(X_test))]
     test_accuracy = np.mean(test_predictions == y_test)
     print(f"测试集准确率: {test_accuracy}")
 
-    # 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]}")
+    # 测试单个数据，输出错误分类
+    for i in range(len(X_test)):
+        y_pred = predict_logreg(X_test[i], weights, threshold=0.5)
+        if y_pred != y_test[i]:
+            print(f"第 {i} 次测试错误，数据 {X_test[i]} 被分类到 {y_pred} 实际是 {y_test[i]}")