更新 function.py

function.py

@@ -1,4 +1,3 @@
-# function.py
 import numpy as np
 import os
 from sklearn.preprocessing import StandardScaler
@@ -19,17 +18,13 @@ from sklearn.preprocessing import StandardScaler
 - numpy: 2.1.1
 """
 
-
 """
 请在这里填写学号和姓名，不填写即成绩无效。
 姓名请直接**填写中文**
 例如: name = "张三"
 """
-id = "202210423211"
+id = "202210423110"
-name = "梅晓东"
+name = "罗浩"
-
-
-import numpy as np
 
 
 def sigmoid(z):
@@ -79,76 +74,71 @@ def load_data(filepath):
 
     data, labels = [], []
     print(f"加载数据中: {filepath}")  
- with open(filepath, 'r') 
+    with open(filepath, 'r') as f:  
- as f:  
+        for line in f:  
- for line in f:  
+            line = line.strip().split()  
- line = line.strip().split()  
+            if len(line) >= 1 and line[-1].isdigit():  
- if len(line) >= 1 and line[-1].isdigit():  
+                line_data = [0 if x == '?' else float(x) for x in line[:-1]]  
- line_data = [0 if x == '?' else float(x) for x in line[:-1]]  
+                data.append(line_data)  
- data.append(line_data)  
+                labels.append(int(line[-1]))  
- labels.append(int(line[-1]))  
+    data = np.array(data)  
-   data = np.array(data)  
+    labels = np.array(labels)  
- labels = np.array(labels)  
+    num_features = data.shape[1]  
-   num_features = data.shape[1]  
+    indices_to_remove = [2]  
- indices_to_remove = [2]  
+    if num_features > 23:  
-   if num_features > 23:  
+        indices_to_remove.extend(range(23, min(28, num_features)))  
- indices_to_remove.extend(range(23, min(28, num_features)))  
+    data = np.delete(data, indices_to_remove, axis=1)  
-   data = np.delete(data, indices_to_remove, axis=1)  
+    target_variable = np.where((labels == 2) | (labels == 3), 0, 1)  
- target_variable = np.where((labels == 2) | (labels == 3), 0, 1)  
+    print(f"数据加载成功，数据形状: {data.shape}, 标签形状: {target_variable.shape}")  
-   print(f"数据加载成功，数据形状: {data.shape}, 标签形状: {target_variable.shape}")  
+    return data, target_variable  
- return data, target_variable  
-   def k_fold_cross_validation(X, y, k=5, learning_rate=0.001, iterations=10000, batch_size=64, lambda_reg=0.1):  
- """K折交叉验证。"""  
- m = X.shape[0]  
- fold_size = m // k  
- accuracies = []  
-   for i in range(k):  
- val_start = i * fold_size  
- val_end = (i + 1) * fold_size if i != k - 1 else m  
-   X_val = X[val_start:val_end]  
- y_val = y[val_start:val_end]  
- X_train = np.concatenate((X[:val_start], X[val_end:]))  
- y_train = np.concatenate((y[:val_start], y[val_end:]))  
-   weights = train_logreg(X_train, y_train, learning_rate, iterations, batch_size, lambda_reg)  
-   val_accuracy = np.mean([predict_logreg(X_val[j], weights) == y_val[j] for j in range(len(y_val))])  
- accuracies.append(val_accuracy)  
-   print(f"Fold {i + 1}/{k} - 验证准确率: {val_accuracy:.4f}")  
-   return np.mean(accuracies)  
-   if __name__ == "__main__":  
- # 加载训练集  
- try:  
- X_train, y_train = load_data("./data/horse-colic.data")  
- except FileNotFoundError as e:  
- print(e)  
- exit()  
-   # 数据归一化处理  
- scaler = StandardScaler()  
- X_train = scaler.fit_transform(X_train) # 使用训练集进行标准化  
-   # k折交叉验证  
- avg_accuracy = k_fold_cross_validation(X_train, y_train, k=5, learning_rate=0.01, iterations=1000)  
- print(f"K折交叉验证的平均准确率: {avg_accuracy:.4f}")  
-   # 加载测试集  
- try:  
- X_test, y_test = load_data("./data/horse-colic.test")  
- except FileNotFoundError
- as e:  
- print(e)  
- exit()  
-   # 测试集也需要进行相同的归一化  
- X_test = scaler.transform(X_test) # 使用相同的Scaler进行测试集的标准化  
-   # 训练逻辑回归模型  
- weights = train_logreg(X_train, y_train, learning_rate=0.01, iterations=1000)  
-   # 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]}") 
 
+def k_fold_cross_validation(X, y, k=5, learning_rate=0.001, iterations=10000, batch_size=64, lambda_reg=0.1):  
+    """K折交叉验证。"""  
+    m = X.shape[0]  
+    fold_size = m // k  
+    accuracies = []  
+    for i in range(k):  
+        val_start = i * fold_size  
+        val_end = (i + 1) * fold_size if i != k - 1 else m  
+        X_val = X[val_start:val_end]  
+        y_val = y[val_start:val_end]  
+        X_train = np.concatenate((X[:val_start], X[val_end:]))  
+        y_train = np.concatenate((y[:val_start], y[val_end:]))  
+        weights = train_logreg(X_train, y_train, learning_rate, iterations, batch_size, lambda_reg)  
+        val_accuracy = np.mean([predict_logreg(X_val[j], weights) == y_val[j] for j in range(len(y_val))])  
+        accuracies.append(val_accuracy)  
+        print(f"Fold {i + 1}/{k} - 验证准确率: {val_accuracy:.4f}")  
+    return np.mean(accuracies)  
 
-    # 加载测试集
+if __name__ == "__main__":  
-    X_test, y_test = load_data("./data/horse-colic.test")
+    # 加载训练集  
-
+    try:  
-    # 训练对率回归模型
+        X_train, y_train = load_data("./data/horse-colic.data")  
-    weights = train_logreg(X_train, y_train, learning_rate=0.01, iterations=1000)
+    except FileNotFoundError as e:  
-
+        print(e)  
-    # 测试单个数据
+        exit()  
-    y_pred = predict_logreg(X_test[11], weights)
+    
+    # 数据归一化处理  
+    scaler = StandardScaler()  
+    X_train = scaler.fit_transform(X_train)  # 使用训练集进行标准化  
+    
+    # k折交叉验证  
+    avg_accuracy = k_fold_cross_validation(X_train, y_train, k=5, learning_rate=0.01, iterations=1000)  
+    print(f"K折交叉验证的平均准确率: {avg_accuracy:.4f}")  
+    
+    # 加载测试集  
+    try:  
+        X_test, y_test = load_data("./data/horse-colic.test")  
+    except FileNotFoundError as e:  
+        print(e)  
+        exit()  
+    
+    # 测试集也需要进行相同的归一化  
+    X_test = scaler.transform(X_test)  # 使用相同的Scaler进行测试集的标准化  
+    
+    # 训练逻辑回归模型  
+    weights = train_logreg(X_train, y_train, learning_rate=0.01, iterations=1000)  
+    
+    # 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]}")