From 331080580651ab876dd874db3e347aabd5e92b3a Mon Sep 17 00:00:00 2001
From: zhangchenghong <1598349064@qq.com>
Date: Fri, 1 Nov 2024 20:59:51 +0800
Subject: [PATCH] =?UTF-8?q?=E6=9B=B4=E6=96=B0=20function.py?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 function.py | 26 +++++++++++++-------------
 1 file changed, 13 insertions(+), 13 deletions(-)

diff --git a/function.py b/function.py
index 2b3b073..5573371 100644
--- a/function.py
+++ b/function.py
@@ -32,15 +32,17 @@ from sklearn.preprocessing import StandardScaler
 def sigmoid(z):
     return 1.0 / (1 + np.exp(-z))
 
-
-def train_logreg(X, y, learning_rate=0.05, iterations=1500, batch_size=64):
+def train_logreg(X, y, learning_rate=0.05, iterations=1500, batch_size=64, regularization_strength=0.1):
     """
     对率回归训练函数。
 
     Args:
     - X (numpy array): 特征数据。
     - y (numpy array): 标签数据。
-    - other_params (str): 其它参数，可选设置。若需设置其它参数，必须设置其默认值，否则将**无法通过**自动评测，**成绩为零**。
+    - learning_rate (float): 学习率。
+    - iterations (int): 迭代次数。
+    - batch_size (int): 批量大小。
+    - regularization_strength (float): L2正则化强度。
 
     Returns:
     - numpy array: 训练得到的权重。
@@ -61,8 +63,7 @@ def train_logreg(X, y, learning_rate=0.05, iterations=1500, batch_size=64):
             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)) / len(y_batch)
-
+            gradient = np.dot(X_batch.T, (h - y_batch)) / len(y_batch) + regularization_strength * weights
             weights -= learning_rate * gradient
 
         # 计算训练集准确率
@@ -75,34 +76,34 @@ def train_logreg(X, y, learning_rate=0.05, iterations=1500, batch_size=64):
             wait += 1
 
     return best_weights
+
 def predict_logreg(X, weights):
     """
     对率回归预测函数。
 
     Args:
-    - inX (numpy array): 输入待分类的样本。
+    - X (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。
+    - numpy array: 预测的分类标签。
     """
     z = np.dot(X, weights)
     h = sigmoid(z)
     return np.where(h > 0.5, 1, 0)
-# 这里也写自己的代码实现
+
 def load_data(filepath):
     """
     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**。
 
     Args:
-    - directory (str): 数据文件路径。
+    - filepath (str): 数据文件路径。
 
     Returns:
     - np.array: 特征数据。
     - np.array: 标签数据。
     """
     data = []
-    data = []
     labels = []
     with open(filepath, 'r') as f:
         for line in f:
@@ -114,7 +115,6 @@ def load_data(filepath):
 
     data = np.array(data)
     labels = np.array(labels)
-
     target_variable = np.where((labels == 2) | (labels == 3), 0, labels)
 
     return data, target_variable
@@ -132,7 +132,7 @@ if __name__ == "__main__":
     X_train = scaler.fit_transform(X_train)
     X_test = scaler.transform(X_test)
 
-    final_weights = train_logreg(X_train, y_train, learning_rate=0.001, iterations=1500, batch_size=64)
+    final_weights = train_logreg(X_train, y_train, learning_rate=0.001, iterations=5000, batch_size=64)
 
     final_accuracy = accuracy(X_test, y_test, final_weights)
-    print(f"最终测试集的准确率: {final_accuracy:.4f}")
\ No newline at end of file
+    print(f"最终测试集的准确率: {final_accuracy:.4f}")