From 095bfc00025de3053c2bab1d9dd7dec149adb6a4 Mon Sep 17 00:00:00 2001
From: Yijuehen <1906265724@qq.com>
Date: Wed, 13 Nov 2024 18:24:06 +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 | 44 +++++++++++++++++++++++++-------------------
 1 file changed, 25 insertions(+), 19 deletions(-)

diff --git a/function.py b/function.py
index a2c2588..0fdf689 100644
--- a/function.py
+++ b/function.py
@@ -5,29 +5,35 @@ id = "202210423230"
 name = "尹家立"
 
 def load_data(filepath):
-    """
-    从文件中加载数据，并处理缺失值。
+    data, labels = [], []
+    with open(filepath, 'r') as f:
+        for line in f:
+            line = line.strip().split()
+            if len(line) >= 1 and line[-1].isdigit():
+                line_data = [0 if x == '?' else float(x) for x in line[:-1]]
+                data.append(line_data)
+                labels.append(int(line[-1]))
 
-    Args:
-    - filepath (str): 数据文件路径。
+    data = np.array(data)
+    labels = np.array(labels)
 
-    Returns:
-    - np.array: 特征数据。
-    - np.array: 标签数据。
-    """
-    # 读取数据，替换缺失值 '?' 为 NaN
-    data = np.genfromtxt(filepath, delimiter=' ', dtype=float, missing_values='?', filling_values=np.nan)
+    # 检查特征数量
+    num_features = data.shape[1]
+
+    # 特征选择：去掉特征3（索引2）和特征24~28（索引23~26），确保索引有效
+    indices_to_delete = [2]  # 特征3
+    if num_features > 24:  # 确保特征数量足够
+        indices_to_delete += list(range(24, 27))  # 特征24到27（索引23到26）
+
+    # 删除特征
+    data = np.delete(data, indices_to_delete, axis=1)
+
+    # 将标签二分类化，特征23（索引22）取值2和3合并为0，其余为1
+    target_variable = np.where((labels == 2) | (labels == 3), 0, 1)
+
+    return data, target_variable
 
-    # 将 NaN 替换为列均值
-    nan_indices = np.isnan(data)
-    col_means = np.nanmean(data, axis=0)
-    data[nan_indices] = np.take(col_means, np.where(nan_indices)[1])
 
-    # 将最后一列作为标签
-    X = data[:, :-1]
-    y = data[:, -1]
-    
-    return X, y