更新 function.py

function.py

@@ -3,6 +3,8 @@ import numpy as np
 import pandas as pd
 from sklearn.impute import SimpleImputer
 from sklearn.preprocessing import StandardScaler
+from sklearn.utils.class_weight import compute_class_weight
+from imblearn.over_sampling import SMOTE
 
 """
 实验说明:
@@ -29,10 +31,12 @@ name = "陈瑞琪祥"
 
 
 # 这里写自己的代码实现
+
+
 def sigmoid(x):
     return 1 / (1 + np.exp(-x))
 
-def train_logreg(X, y, learning_rate=0.01, iterations=1000, regularization=0.01):
+def train_logreg(X, y, learning_rate=0.01, iterations=1000, regularization=0.1):
     m, n = X.shape
     weights = np.zeros(n)
     for _ in range(iterations):
@@ -52,10 +56,6 @@ def preprocess_data(X, y):
     y[y == 2] = 0
     y[y == 3] = 0
 
-    # 删除特征3和特征24~28
-    X = np.delete(X, [3], axis=1)
-    X = X[:, :23]
-
     return X, y
 
 def load_data(filepath):
@@ -96,6 +96,14 @@ def main():
         X_train = scaler.fit_transform(X_train)
         X_test = scaler.transform(X_test)
 
+        # 使用SMOTE处理类别不平衡
+        smote = SMOTE(random_state=42)
+        X_train, y_train = smote.fit_resample(X_train, y_train)
+
+        # 计算类别权重
+        class_weights = compute_class_weight('balanced', classes=np.unique(y_train), y=y_train)
+        class_weights = dict(enumerate(class_weights))
+
         # 训练模型
         weights = train_logreg(X_train, y_train, learning_rate=0.01, iterations=1000, regularization=0.1)
 
@@ -105,7 +113,6 @@ def main():
         # 计算准确率
         accuracy = np.mean(y_pred == y_test)
         print(f"准确率: {accuracy}")
-        
+
 if __name__ == "__main__":
     main()
-