From 52643867625d02cf43d34cf56823f60ab67c8eda Mon Sep 17 00:00:00 2001
From: Dengddd <3149942468@qq.com>
Date: Tue, 15 Oct 2024 16:18:15 +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 | 27 ++++++++++++++++++++-------
 1 file changed, 20 insertions(+), 7 deletions(-)

diff --git a/function.py b/function.py
index fd14443..968415e 100644
--- a/function.py
+++ b/function.py
@@ -60,29 +60,38 @@ def classify(input_vector, dataSet, labels, k=3):  # 设置默认值 k=3
 
 def load_dataset(directory):
     """加载数据集中的图像，并将其转换为特征向量和标签。"""
+    # 初始化特征数据列表和标签列表
     feature_list = []
     label_list = []
+    # 遍历目录中的所有文件
     for file in os.listdir(directory):
+        # 获取文件的完整路径
         file_path = os.path.join(directory, file)
+        # 将图像文件转换为向量
         feature_vector = img_to_vector(file_path)
+        # 将特征向量添加到列表中
         feature_list.append(feature_vector)
+        # 获取文件名中的标签并添加到标签列表中
         label_list.append(int(file.split('_')[0]))
+    # 将特征列表和标签列表转换为numpy数组
     feature_matrix = np.array(feature_list)
     label_array = np.array(label_list)
     return feature_matrix, label_array
 
 def img_to_vector(filename):
     """将二值图像转换为向量。"""
+    # 读取文件内容并转换为整数数组
     with open(filename, 'r') as file:
-        lines = file.read().strip()
-    vector = np.array(list(map(int, lines))).reshape(1024,)
+        lines = file.readlines()
+    # 将每行的数字字符转换为整数，并使用 NumPy 的 reshape 方法转换为一维数组
+    vector = np.array([int(char) for line in lines for char in line.strip()]).reshape(1024,)
     return vector
 
 if __name__ == "__main__":
-    # 测试代码
+    # 以下代码可用于测试，可自行随意修改
     train_data, train_labels = load_dataset("trainingDigits")
 
-    test_data_str = (
+    test_data = (
         "00000000000000110000000000000000"
         "00000000000011111000000000000000"
         "00000000000011111100000000000000"
@@ -116,6 +125,10 @@ if __name__ == "__main__":
         "00000000000001111111110000000000"
         "00000000000000000111100000000000"
     )
-    test_data = np.array(list(map(int, test_data_str))).reshape(1, 1024)
-    predicted_label = classify(test_data, train_data, train_labels)
-    print(f"预测的标签: {predicted_label}")
+    predicted_label = classify(
+        np.array([int(char) for char in test_data]).reshape(1, 1024),
+        train_data,
+        train_labels,
+    )
+
+    print(f"预测的标签: {predicted_label}")
\ No newline at end of file