From a31bfdeb9f3b79b67588d0ffa63d58f66f2c775b Mon Sep 17 00:00:00 2001
From: Xionghaoran <719929980@qq.com>
Date: Thu, 31 Oct 2024 15:26:24 +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 | 27 +++++++++++++++++++--------
 1 file changed, 19 insertions(+), 8 deletions(-)

diff --git a/function.py b/function.py
index b4be86e..d0a307d 100644
--- a/function.py
+++ b/function.py
@@ -1,5 +1,6 @@
 # function.py
 import numpy as np
+from sklearn.preprocessing import PolynomialFeatures
 
 """
 实验说明:
@@ -20,8 +21,8 @@ import numpy as np
 """
 请在这里填写学号和姓名，不填写即成绩无效。
 """
-id = "202210423213"
-name = "熊浩燃"
+id = "202210423xxx"
+name = "test_name"
 
 def sigmoid(z):
     return 1 / (1 + np.exp(-z))
@@ -30,9 +31,14 @@ def standardize(X):
     """ 数据标准化：均值为0，标准差为1 """
     return (X - np.mean(X, axis=0)) / (np.std(X, axis=0) + 1e-8)  # 避免除零
 
-def train_logreg(X, y, learning_rate=0.0005, iterations=3000, batch_size=32, lambda_=0.05):
+def add_polynomial_features(X, degree=2):
+    """ 增加多项式特征 """
+    poly = PolynomialFeatures(degree)
+    return poly.fit_transform(X)
+
+def train_logreg(X, y, learning_rate=0.0001, iterations=5000, batch_size=32, lambda_=0.1, degree=2):
     """
-    对率回归训练函数，包含批量梯度下降和L2正则化。
+    对率回归训练函数，包含批量梯度下降和L2正则化，并增加多项式特征。
 
     Args:
     - X (numpy array): 特征数据。
@@ -41,11 +47,13 @@ def train_logreg(X, y, learning_rate=0.0005, iterations=3000, batch_size=32, lam
     - iterations (int): 迭代次数。
     - batch_size (int): 每次更新的样本数。
     - lambda_ (float): L2正则化项的系数。
+    - degree (int): 多项式特征的次数。
 
     Returns:
     - numpy array: 训练得到的权重。
     """
-    X = standardize(X)  # 使用标准化数据
+    X = standardize(X)  # 标准化数据
+    X = add_polynomial_features(X, degree=degree)  # 增加多项式特征
     m, n = X.shape
     weights = np.random.rand(n) * 0.01  # 初始化权重为小的随机数
     
@@ -66,17 +74,20 @@ def train_logreg(X, y, learning_rate=0.0005, iterations=3000, batch_size=32, lam
     
     return weights
 
-def predict_logreg(inX, weights):
+def predict_logreg(inX, weights, degree=2):
     """
     对率回归预测函数。
 
     Args:
     - inX (numpy array): 输入待分类的样本。
     - weights (numpy array): 训练得到的权重。
+    - degree (int): 多项式特征的次数。
 
     Returns:
     - int: 预测的分类标签。
     """
+    inX = standardize(inX.reshape(1, -1))  # 标准化输入
+    inX = add_polynomial_features(inX, degree=degree)  # 增加多项式特征
     probability = sigmoid(np.dot(inX, weights))
     return 1 if probability >= 0.5 else 0
 
@@ -107,8 +118,8 @@ if __name__ == "__main__":
     X_test, y_test = load_data("./data/horse-colic.test")
 
     # 训练对率回归模型
-    weights = train_logreg(X_train, y_train, learning_rate=0.0005, iterations=3000, batch_size=32, lambda_=0.05)
+    weights = train_logreg(X_train, y_train, learning_rate=0.0001, iterations=5000, batch_size=32, lambda_=0.1, degree=2)
 
     # 测试单个数据
-    y_pred = predict_logreg(X_test[11], weights)
+    y_pred = predict_logreg(X_test[11], weights, degree=2)
     print(f"预测结果: {y_pred}, 实际结果: {y_test[11]}")