From 61b3b782c70b28aa5b433f98dcf6c873f98fbe64 Mon Sep 17 00:00:00 2001
From: wzy <675163717@qq.com>
Date: Thu, 31 Oct 2024 15:38:27 +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 | 29 +++++++++++++++++++++--------
 1 file changed, 21 insertions(+), 8 deletions(-)

diff --git a/function.py b/function.py
index 60c49ac..be4bf3f 100644
--- a/function.py
+++ b/function.py
@@ -31,6 +31,7 @@ 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):
+    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:
@@ -68,7 +69,7 @@ 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
@@ -116,15 +117,26 @@ def load_data(filepath):
     data = [line.strip().split() for line in lines]
     data = [list(map(lambda x: float(x) if x != '?' else np.nan, row)) for row in data]
     
-    # 处理缺失值，这里简单用平均值填充
-    for i in range(len(data[0])):
-        mean_val = np.nanmean([row[i] for row in data if not np.isnan(row[i])])
-        for row in data:
+    # 移除类别标签缺失的样本
+    data = [row for row in data if row[-1] != np.nan]
+
+    # 使用“0”填充缺失值
+    for row in data:
+        for i in range(len(row)):
             if np.isnan(row[i]):
-                row[i] = mean_val
+                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 == 3:  # 假设特征23是第23个元素
+            row[22] = 0
+    
+    # 移除不需要的特征
+    # 假设特征从0开始编号，那么我们需要移除特征3和特征24~28
+    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]
+    X = [row[:-1] for row in data]  # 特征现在是从0到21，然后是23到27
     y = [row[-1] for row in data]
     
     return np.array(X), np.array(y)
@@ -140,6 +152,7 @@ def load_data(filepath):
     """
 
 if __name__ == "__main__":
+    # 以下代码可用于测试，可自行随意修改
     # 加载训练集
     X_train, y_train = load_data("./data/horse-colic.data")
 
@@ -151,4 +164,4 @@ if __name__ == "__main__":
 
     # 测试单个数据
     y_pred = predict_logreg(X_test[11], weights)
-    print(f"预测结果: {y_pred}, 实际结果: {y_test[11]}")
\ No newline at end of file
+    print(f"预测结果: {y_pred}, 实际结果: {y_test[11]}")