From 4519443c46dbe695b18394e4e149050968e1f28f Mon Sep 17 00:00:00 2001
From: luderby <2339127037@qq.com>
Date: Tue, 5 Nov 2024 11:24:58 +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 | 34 ++++++++++++++++++++--------------
 1 file changed, 20 insertions(+), 14 deletions(-)

diff --git a/function.py b/function.py
index be15b75..4705eee 100644
--- a/function.py
+++ b/function.py
@@ -1,5 +1,6 @@
 # function.py  
 import numpy as np  
+import csv
 
 """  
 实验说明:  
@@ -82,29 +83,34 @@ def load_data(filepath):
     - np.array: 特征数据。  
     - np.array: 标签数据。  
     """  
-    # 加载数据，使用适当的分隔符和设置  
-    data = np.genfromtxt(filepath, delimiter=',', dtype=None, encoding=None, invalid_raise=False, filling_values=np.nan, autostrip=True)  
+    features = []  
+    labels = []  
+    
+    with open(filepath, 'r') as f:  
+        reader = csv.reader(f)  
+        for row in reader:  
+            # 检查每一行是否包含预期数量的列，这里假设每行需要至少一个特征和一个标签  
+            if len(row) > 1:  
+                features.append([float(x) for x in row[:-1]])  # 将特征转换为浮点数  
+                labels.append(row[-1])  # 取最后一列作为标签  
 
-    print("Loaded data shape:", data.shape)  # 打印数据的形状  
+    # 转换成NumPy数组  
+    X = np.array(features)  
+    y = np.array(labels)  
 
-    # 检查是否成功加载了二维数据  
-    if data.ndim == 1:  
-        raise ValueError("Loaded data is one-dimensional, please check the file format.")  
+    # 确保 y 只包含 0 和 1  
+    y = np.where(y == '1', 1, 0)  
 
-    X = data[:, :-1].astype(float)  # 假设最后一列为标签  
-    y = data[:, -1]                 # 最后一列为标签  
-
-    # 检查有效索引  
-    valid_indices = ~np.isnan(X).any(axis=1) & ~np.isnan(y)  
+    # 过滤掉包含 NaN 的行  
+    valid_indices = ~np.isnan(X).any(axis=1) & ~np.isnan(y.astype(float))  
     X = X[valid_indices]  
     y = y[valid_indices]  
 
-    y = np.where(y == 1, 1, 0)  
-    return X, y  
+    return X, y
 
 
 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")
-    
\ No newline at end of file
+    print(f"预测结果: {y_pred[sample_index]}, 实际结果: {y_test[sample_index]}")
\ No newline at end of file