更新 function.py

function.py

@@ -2,21 +2,27 @@ import numpy as np
 import pandas as pd
 from sklearn.preprocessing import StandardScaler
 from sklearn.model_selection import train_test_split
-from imblearn.over_sampling import SMOTE  # 导入SMOTE
 
 id = "202210423130"
 name = "董秋"
 
 
 def sigmoid(z):
+    """
+    Sigmoid 激活函数。
+    """
     return 1 / (1 + np.exp(-z))
 
 
 def train_logreg(X, y, learning_rate=0.01, iterations=1000, lambda_reg=0.01):
+    """
+    逻辑回归训练函数，随机初始化权重，并在每次迭代前打乱数据。
+    """
     m, n = X.shape
-    weights = np.random.randn(n) * 0.01
+    weights = np.random.randn(n) * 0.01  # 随机初始化权重，取较小值
 
     for i in range(iterations):
+        # 每次迭代打乱数据
         indices = np.random.permutation(m)
         X = X[indices]
         y = y[indices]
@@ -25,26 +31,32 @@ def train_logreg(X, y, learning_rate=0.01, iterations=1000, lambda_reg=0.01):
         predictions = sigmoid(z)
         gradient = np.dot(X.T, (predictions - y)) / m
 
+        # L2正则化
         gradient += (lambda_reg / m) * weights
+
+        # 更新权重
         weights -= learning_rate * gradient
+
+        # 动态调整学习率，逐渐减小
         learning_rate *= 0.99
 
     return weights
 
 
 def predict_logreg(inX, weights):
+    """
+    逻辑回归预测函数。
+    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)
     prediction_prob = sigmoid(z)
     return 1 if prediction_prob >= 0.5 else 0
 
 
-def handle_outliers(df, threshold=3):
-    z_scores = np.abs((df - df.mean()) / df.std())
-    df[z_scores > threshold] = np.nan
-    df.fillna(df.mean(), inplace=True)
-    return df
-
-
 def load_data(filepath):
     data = []
     labels = []
@@ -53,36 +65,40 @@ def load_data(filepath):
     with open(filepath, 'r') as f:
         for line in f:
             line_number += 1  # 每读取一行，行号加1
-            # 检查当前行号，跳过特定行
+            # 跳过第三行和第24到28行
             if line_number == 3 or line_number in range(24, 29):
                 continue
 
             values = line.strip().replace('?', '0').split()
             try:
                 values = [float(v) for v in values]
-                if values[22] == 2 or values[22] == 3:
+                
+                # 合并特征23的取值
+                if values[22] == 2 or values[22] == 3:  # 特征23（索引22）
                     labels.append(0)  # 死亡
                 elif values[22] == 1:
                     labels.append(1)  # 生存
                 else:
-                    continue
-
-                values = [np.nan if v == 0 else v for v in values]
-                data.append(values[:2] + values[3:23])
+                    continue  # 无效标签，丢弃
+                
+                # 用0填充缺失值
+                values = [np.nan if v == 0 else v for v in values]  # 先标记为NaN
+                data.append(values[:2] + values[3:23])  # 保留特征1, 2 和特征4-23
             except ValueError:
                 continue
 
     data = np.array(data)
     labels = np.array(labels)
 
+    # 使用均值填充处理缺失值
     df = pd.DataFrame(data)
-    df.fillna(df.mean(), inplace=True)
-    df = handle_outliers(df)
+    df.fillna(df.mean(), inplace=True)  # 均值填充
 
     return df.to_numpy(), labels
 
 
 def preprocess_data(X):
+    # 特征标准化
     scaler = StandardScaler()
     return scaler.fit_transform(X)
 
@@ -95,12 +111,8 @@ if __name__ == "__main__":
     # 使用 train_test_split 打乱并随机抽取数据
     X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
 
-    # 使用 SMOTE 进行数据集平衡
-    smote = SMOTE(random_state=42)
-    X_train_balanced, y_train_balanced = smote.fit_resample(X_train, y_train)
-
     # 训练逻辑回归模型
-    weights = train_logreg(X_train_balanced, y_train_balanced, learning_rate=0.1, iterations=1000, lambda_reg=0.01)
+    weights = train_logreg(X_train, y_train, learning_rate=0.1, iterations=1000, lambda_reg=0.01)
 
     # 测试单个数据
     y_pred = predict_logreg(X_test[11], weights)