From 1bf2f4ebd8d904d59b97a573c6a7542f337d25c2 Mon Sep 17 00:00:00 2001
From: 43606070 <43606070@qq.com>
Date: Sat, 2 Nov 2024 15:50:31 +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 | 74 +++++++++++++++++++----------------------------------
 1 file changed, 26 insertions(+), 48 deletions(-)

diff --git a/function.py b/function.py
index f77b360..71ed317 100644
--- a/function.py
+++ b/function.py
@@ -1,28 +1,3 @@
-import numpy as np
-
-"""
-实验说明:
-- 自行编写实现数据加载与预测病马死亡的对率回归算法。 
-
-注意事项:
-- 在 function.py 中实现对率回归算法。
-- 可以自行导入其他库，需要在 requirements.txt 添加依赖，若未在 requirements.txt 中添加使用到的依赖，则无法自动评测，成绩为零。
-- 自动评测脚本仅会加载 train_logreg、predict_logreg 和 load_data 函数，请勿修改函数名。
-
-测评环境:
-- CPU: Intel Xeon(R) CPU E3-1231 v3 @ 3.40GHz
-- OS: Ubuntu 22.04.4 LTS
-- Python: 3.10.12
-- numpy: 2.1.1
-"""
-
-"""
-请在这里填写学号和姓名，不填写即成绩无效。
-"""
-id = "202210423118"
-name = "刘国庆"
-
-
 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。
@@ -34,31 +9,34 @@ def load_data(filepath):
     - np.array: 特征数据。
     - np.array: 标签数据。
     """
-    try:
-        # Load data with genfromtxt, filling missing values with NaN
-        data = np.genfromtxt(filepath, delimiter=',', missing_values='?', filling_values=np.nan)
-        
-        # Check if the data has been loaded correctly with at least two dimensions
-        if data.ndim < 2:
-            print(f"Error: File '{filepath}' may be empty or improperly formatted.")
-            return None, None
+    for delimiter in [',', ' ', '\t']:  # 尝试不同的分隔符：逗号、空格、制表符
+        try:
+            # Load data, filling missing values with NaN
+            data = np.genfromtxt(filepath, delimiter=delimiter, missing_values='?', filling_values=np.nan)
+            
+            # Check if the data has been loaded correctly with at least two dimensions
+            if data.ndim < 2 or data.size == 0:
+                continue  # 尝试下一个分隔符
 
-        # Remove rows with NaN values
-        data = data[~np.isnan(data).any(axis=1)]
-        
-        # Ensure there's still data left after removing rows with NaN
-        if data.size == 0:
-            print(f"Error: No valid data after removing NaN rows in file '{filepath}'.")
-            return None, None
+            # Remove rows with NaN values
+            data = data[~np.isnan(data).any(axis=1)]
+            
+            # Ensure there's still data left after removing NaN
+            if data.size == 0:
+                print(f"Error: No valid data after removing NaN rows in file '{filepath}'.")
+                return None, None
+
+            # Split into features (X) and labels (y)
+            X = data[:, :-1]  # Features
+            y = data[:, -1]   # Labels
+            
+            return X, y
+        except Exception as e:
+            print(f"Error loading data with delimiter '{delimiter}': {e}")
+
+    print(f"Error: File '{filepath}' may be empty or improperly formatted.")
+    return None, None
 
-        # Split into features (X) and labels (y)
-        X = data[:, :-1]  # Features
-        y = data[:, -1]   # Labels
-        
-        return X, y
-    except Exception as e:
-        print(f"Error loading data: {e}")
-        return None, None
 
 
 def sigmoid(z):