From 7c359f4a6ba6d36d83b91668be6643e678118f42 Mon Sep 17 00:00:00 2001
From: lzh <2233673261@qq.com>
Date: Thu, 17 Oct 2024 00:18:17 +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 | 104 ++++++++++++++++++++++++++++++++++++++++++----------
 1 file changed, 85 insertions(+), 19 deletions(-)

diff --git a/function.py b/function.py
index 7cd9f4e..d74dac3 100644
--- a/function.py
+++ b/function.py
@@ -41,38 +41,101 @@ name = "廖子豪"
 
 
 # 这里写自己的代码实现
+import numpy as np
+import os
 
+def classify(input_vector, dataSet, labels, k=3):
+    """
+    KNN 分类算法。
 
-def classify(input_vector, dataSet, labels, k_values=[1, 31]):
-    # ... 你的代码 ...
+    Args:
+    - input_vector (numpy array): 输入待分类的样本。
+    - dataSet (numpy array): 训练数据集。
+    - labels (list or numpy array): 训练集对应的标签。
+    - k (int): kNN 算法参数，默认值为3。
+
+    Returns:
+    - int: 预测的分类标签。
+    """
+    distances = np.sqrt(np.sum((dataSet - input_vector) ** 2, axis=1))
+    sorted_indices = np.argsort(distances)
+    class_counts = {}
+    for i in range(k):
+        vote_label = labels[sorted_indices[i]]
+        class_counts[vote_label] = class_counts.get(vote_label, 0) + 1
+    sorted_class_counts = sorted(class_counts.items(), key=lambda x: x[1], reverse=True)
+    return sorted_class_counts[0][0]
 
 def load_dataset(directory):
+    """
+    从文件夹中加载数据，若不自行正确实现，则无法通过评测，**不记录成绩**。
+
+    Args:
+    - directory (str): 数据文件夹路径。
+
+    Returns:
+    - np.array: 特征数据。
+    - np.array: 标签数据。
+    """
     labels = []
+    dataset = []
     file_list = os.listdir(directory)
-    num_samples = len(file_list)
-    dataset = np.zeros((num_samples, 1024))
-
-    for i, filename in enumerate(file_list):
-        label = int(filename.split("_")[0])  # 从文件名中提取标签
-        labels.append(label)
-        dataset[i, :] = img_to_vector(os.path.join(directory, filename))
-
-    return dataset, np.array(labels)
+    for file_name in file_list:
+        file_path = os.path.join(directory, file_name)
+        labels.append(int(file_name.split('_')[0]))
+        dataset.append(img_to_vector(file_path))
+    return np.array(dataset), np.array(labels)
 
 def img_to_vector(filename):
-    with open(filename, 'r') as file_in:
-        img_vector = np.zeros((1, 1024))
-        for idx, line in enumerate(file_in):
-            for col_idx, char in enumerate(line.strip()):
-                img_vector[0, idx * 32 + col_idx] = int(char)
-    return img_vector
+    """
+    将二值图像转换为向量。
+
+    Args:
+    - filename (str): 图像文件路径。
+
+    Returns:
+    - np.array: 二值图像向量。
+    """
+    with open(filename, 'r') as file:
+        return np.array([int(bit) for line in file for bit in line.strip()])
 
 if __name__ == "__main__":
     # 请确保trainingDigits文件夹在你的工作目录中，或者提供完整的路径
     train_data, train_labels = load_dataset("trainingDigits")
 
     test_data = (
-        # ... 你的测试数据 ...
+        "00000000000000110000000000000000"
+        "00000000000011111000000000000000"
+        "00000000000011111100000000000000"
+        "00000000001111111110000000000000"
+        "00000000001111111110000000000000"
+        "00000000001111111100000000000000"
+        "00000000011111111000000000000000"
+        "00000000111111111000000000000000"
+        "00000000111111110000000000000000"
+        "00000000111111110000000000000000"
+        "00000000111111110000000000000000"
+        "00000000111111110000000000000000"
+        "00000000111111100000000000000000"
+        "00000001111111100000000000000000"
+        "00000001111111100000000000000000"
+        "00000001111111100000000000000000"
+        "00000001111111111111000000000000"
+        "00000001111111111111111000000000"
+        "00000001111111111111111100000000"
+        "00000011111111111111111110000000"
+        "00000011111111111111111110000000"
+        "00000001111111111111111110000000"
+        "00000001111111111111111110000000"
+        "00000000111111111100111111100000"
+        "00000000111111111000111111100000"
+        "00000000011111111001111111100000"
+        "00000000011111111111111111000000"
+        "00000000001111111111111111000000"
+        "00000000000111111111111111000000"
+        "00000000000011111111111100000000"
+        "00000000000001111111110000000000"
+        "00000000000000000111100000000000"
     )
     predicted_label = classify(
         np.array([int(char) for char in test_data]).reshape(1, 1024),
@@ -80,4 +143,7 @@ if __name__ == "__main__":
         train_labels,
     )
 
-    print(f"预测的标签: {predicted_label}")
\ No newline at end of file
+    print(f"预测的标签: {predicted_label}")
+
+
+