更新 function.py

function.py

@@ -1,7 +1,8 @@
 # function.py
 import numpy as np
-import random
+import pandas as pd
 from sklearn.preprocessing import StandardScaler
+from sklearn.model_selection import train_test_split, KFold
 
 """
 实验说明:
@@ -30,30 +31,31 @@ name = "万子玉"
 def sigmoid(z):
     return 1 / (1 + np.exp(-z))
 
-def train_logreg(X, y, learning_rate=0.001, iterations=500, batch_size=16, initial_weights=None):
+def train_logreg(X, y, learning_rate=0.01, iterations=2000, lambda_reg=0.01, batch_size=32):
     X = np.insert(X, 0, 1, axis=1)  # 添加偏置项
-    if initial_weights is None:
-        weights = np.zeros(X.shape[1])
-    else:
-        weights = initial_weights
-    
-    m = X.shape[0]
-    
-    for _ in range(iterations):
+    m, n = X.shape
+    weights = np.random.randn(n) * 0.01  # 随机初始化权重
+
+    for i in range(iterations):
         indices = np.arange(m)
         np.random.shuffle(indices)
         X_shuffled = X[indices]
         y_shuffled = y[indices]
-        
-        for i in range(0, m, batch_size):
-            end = i + batch_size
-            X_batch = X_shuffled[i:end]
-            y_batch = y_shuffled[i:end]
+
+        for j in range(0, m, batch_size):
+            X_batch = X_shuffled[j:j + batch_size]
+            y_batch = y_shuffled[j:j + batch_size]
+
             z = np.dot(X_batch, weights)
-            h = sigmoid(z)
-            gradient = np.dot(X_batch.T, (h - y_batch)) / batch_size
+            predictions = sigmoid(z)
+            gradient = np.dot(X_batch.T, (predictions - y_batch)) / X_batch.shape[0]
+
+            # L2正则化
+            gradient += (lambda_reg / m) * weights
+
+            # 更新权重
             weights -= learning_rate * gradient
-        
+
     return weights
 
     """
@@ -72,8 +74,8 @@ def train_logreg(X, y, learning_rate=0.001, iterations=500, batch_size=16, initi
 def predict_logreg(inX, weights):
     inX = np.insert(inX, 0, 1)  # 添加偏置项
     z = np.dot(inX, weights)
-    h = sigmoid(z)
-    return 1 if h >= 0.5 else 0
+    prediction_prob = sigmoid(z)
+    return 1 if prediction_prob >= 0.5 else 0
 
 
     """
@@ -112,10 +114,10 @@ def split_train_val(X, y, val_size=0.2):
 def load_data(filepath):
     with open(filepath, 'r') as file:
         lines = file.readlines()
-    
+
     data = [line.strip().split() for line in lines if line.strip().split()[-1].isdigit()]
     data = [list(map(lambda x: float(x) if x != '?' else np.nan, row)) for row in data]
-    
+
     # 移除类别标签缺失的样本
     data = [row for row in data if not np.isnan(row[-1])]
 
@@ -124,22 +126,22 @@ def load_data(filepath):
         for i in range(len(row)):
             if np.isnan(row[i]):
                 row[i] = 0.0
-    
+
     # 合并特征23的值2和3为0
     for row in data:
         if row[22] == 2 or row[22] == 3:  # 假设特征23是第23个元素
             row[22] = 0
-    
+
     # 移除不需要的特征
     data = [row[:2] + row[3:23] + row[28:] for row in data]
-    
+
     # 分离特征和标签
     X = [row[:-1] for row in data]
     y = [row[-1] for row in data]
-    
+
     scaler = StandardScaler()
     X = scaler.fit_transform(X)
-    
+
     return np.array(X), np.array(y)
     """
     从文件中加载数据，若不自行正确实现，则无法通过评测，**不记录成绩**。
@@ -156,7 +158,7 @@ if __name__ == "__main__":
     X_train, y_train = load_data("./data/horse-colic.data")
     X_test, y_test = load_data("./data/horse-colic.test")
     
-    weights = train_logreg(X_train, y_train, learning_rate=0.01, iterations=1000)
+    weights = train_logreg(X_train, y_train, learning_rate=0.01, iterations=2000)
     
     y_pred = predict_logreg(X_test[11], weights)
     print(f"预测结果: {y_pred}, 实际结果: {y_test[11]}")