From 49d7b0c7e82a813348742a884a2b949fcf8184d7 Mon Sep 17 00:00:00 2001
From: 43606070 <43606070@qq.com>
Date: Sat, 2 Nov 2024 15:57:27 +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 | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/function.py b/function.py
index 04cfd7d..5c6af88 100644
--- a/function.py
+++ b/function.py
@@ -38,7 +38,7 @@ def load_data(filepath):
             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:
+            if data.ndim < 2 or data.shape[1] < 2:  # 至少需要两列：特征和标签
                 continue  # 尝试下一个分隔符
 
             # Remove rows with NaN values
@@ -52,6 +52,14 @@ def load_data(filepath):
             # Split into features (X) and labels (y)
             X = data[:, :-1]  # Features
             y = data[:, -1]   # Labels
+
+            # Check if shapes of X and y match
+            if X.shape[0] != y.shape[0]:
+                print(f"Error: Feature and label count mismatch in file '{filepath}'")
+                return None, None
+            
+            # 输出数据形状供检查
+            print(f"Loaded data from '{filepath}': {X.shape[0]} samples, {X.shape[1]} features.")
             
             return X, y
         except Exception as e:
@@ -111,3 +119,4 @@ def predict_logreg(X, weights):
     X = np.c_[np.ones(X.shape[0]), X]  # Add intercept term
     probabilities = sigmoid(np.dot(X, weights))
     return (probabilities >= 0.5).astype(int)
+