From 9b0d573f0cadc3abd7e4d8bbaff428847df2d8ac Mon Sep 17 00:00:00 2001
From: Dengddd <3149942468@qq.com>
Date: Thu, 31 Oct 2024 14:35:31 +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 | 43 ++++++++++++++++++++++---------------------
 1 file changed, 22 insertions(+), 21 deletions(-)

diff --git a/function.py b/function.py
index 27ecb63..836b618 100644
--- a/function.py
+++ b/function.py
@@ -33,28 +33,13 @@ def sigmoid(z):
     return 1 / (1 + np.exp(-z))
 
 def train_logreg(X, y, learning_rate=0.01, iterations=1000):
-    """
-    对率回归训练函数。
-
-    Args:
-    - X (numpy array): 特征数据。
-    - y (numpy array): 标签数据。
-    - learning_rate (float): 学习率，默认值为0.01。
-    - iterations (int): 迭代次数，默认值为1000。
-    
-    Returns:
-    - weights (numpy array): 训练得到的权重。
-    """
-    # 初始化权重
+    """对率回归训练函数。"""
     weights = np.zeros(X.shape[1])
     
-    # 训练模型
     for _ in range(iterations):
         z = np.dot(X, weights)
         predictions = sigmoid(z)
-        # 计算梯度
         gradient = np.dot(X.T, (predictions - y)) / y.size
-        # 更新权重
         weights -= learning_rate * gradient
     
     return weights
@@ -82,25 +67,41 @@ def load_data(filepath):
     for i in range(len(data)):
         if len(data[i]) < max_columns:
             data[i].extend(['nan'] * (max_columns - len(data[i])))
-    
+
     # 转换成numpy数组，处理缺失值
     data_array = np.array(data, dtype=float)
     data_array[np.isnan(data_array)] = np.nanmean(data_array, axis=0)
-    
+
     return data_array[:, :-1], data_array[:, -1]
 
-# 主逻辑
+def preprocess_data(X, y):
+    """数据预处理，合并特征23的值，并删除特征3和特征24~28。"""
+    # 合并特征23的值：将2（死亡）和3（安乐死）合并为0（死亡）
+    y = np.where(y == 2, 0, y)  # 将值2替换为0
+    y = np.where(y == 3, 0, y)  # 将值3替换为0
+
+    # 删除特征3和特征24~28（假设特征索引从0开始）
+    X = np.delete(X, [2] + list(range(23, 28)), axis=1)
+
+    return X, y
+
 if __name__ == "__main__":
     # 加载数据
     X, y = load_data("./data/horse-colic.data")
 
+    # 数据预处理
+    X, y = preprocess_data(X, y)
+
     # 训练模型
     weights = train_logreg(X, y)
 
-    # 加载测试数据并预测
+    # 加载测试数据并进行预处理
     X_test, y_test = load_data("./data/horse-colic.test")
+    X_test, y_test = preprocess_data(X_test, y_test)
+    
+    # 预测
     predictions = predict_logreg(X_test, weights)
 
     # 打印预测结果和实际结果
-    for i in range(min(10, len(y_test))):  # 打印前10个结果或全部结果，取决于测试数据量
+    for i in range(min(10, len(y_test))):
         print(f"预测结果: {predictions[i]}, 实际结果: {y_test[i]}")