From 8719f435de9f3bd2c5d6685d020c5950b5907a2c Mon Sep 17 00:00:00 2001
From: lzh <202210423221@qq.com>
Date: Wed, 16 Oct 2024 23:55:29 +0800
Subject: [PATCH] 222

---
 function.py | 90 +++++++++++++++++++++++++----------------------------
 1 file changed, 42 insertions(+), 48 deletions(-)

diff --git a/function.py b/function.py
index 7757bb6..333e89a 100644
--- a/function.py
+++ b/function.py
@@ -1,6 +1,5 @@
 # function.py
 import numpy as np
-from collections import Counter
 import os
 
 """
@@ -41,10 +40,6 @@ name = "廖子豪"
 """
 
 
-# 这里写自己的代码实现
-import numpy as np
-import os
-from collections import Counter
 
 def img_to_vector(filename):
     """
@@ -57,9 +52,7 @@ def img_to_vector(filename):
     - np.array: 二值图像向量。
     """
     with open(filename, 'r') as file:
-        lines = file.readlines()
-        vector = [int(pixel) for line in lines for pixel in line.strip()]
-    return np.array(vector)
+        return np.array([int(char) for line in file for char in line.strip()])
 
 def load_dataset(directory):
     """
@@ -72,7 +65,7 @@ def load_dataset(directory):
     - np.array: 特征数据。
     - np.array: 标签数据。
     """
-    images = []
+    features = []
     labels = []
     for label_dir in os.listdir(directory):
         label_dir_path = os.path.join(directory, label_dir)
@@ -80,9 +73,9 @@ def load_dataset(directory):
             for filename in os.listdir(label_dir_path):
                 file_path = os.path.join(label_dir_path, filename)
                 image_vector = img_to_vector(file_path)
-                images.append(image_vector)
+                features.append(image_vector)
                 labels.append(int(label_dir))
-    return np.array(images), np.array(labels)
+    return np.array(features), np.array(labels)
 
 def classify(input_vector, dataSet, labels, k=3):
     """
@@ -107,46 +100,47 @@ if __name__ == "__main__":
     train_dir = "trainingDigits"  # 训练集目录
     test_dir = "testDigits"  # 测试集目录
     
-    train_images, train_labels = load_dataset(train_dir)
-    test_images, test_labels = load_dataset(test_dir)
+    train_data, train_labels = load_dataset(train_dir)
+    test_data, test_labels = load_dataset(test_dir)
     
-    print("训练集特征形状：", train_images.shape)
+    print("训练集特征形状：", train_data.shape)
     print("训练集标签形状：", train_labels.shape)
-    print("测试集特征形状：", test_images.shape)
+    print("测试集特征形状：", test_data.shape)
     print("测试集标签形状：", test_labels.shape)
     
     # 测试 classify 函数
-    test_data = np.array([int(char) for char in "00000000000000110000000000000000000"  # 示例数据
-                          "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"] * 4).reshape(1, 1024)
-    predicted_label = classify(test_data, train_images, train_labels)
+    test_data_vector = np.array([int(char) for char in (
+        "00000000000000110000000000000000"
+        "00000000000011111000000000000000"
+        "00000000000011111100000000000000"
+        "00000000001111111110000000000000"
+        "00000000001111111110000000000000"
+        "00000000001111111100000000000000"
+        "00000000011111111000000000000000"
+        "00000000111111111000000000000000"
+        "00000000111111110000000000000000"
+        "00000000111111110000000000000000"
+        "00000000111111110000000000000000"
+        "00000000111111110000000000000000"
+        "00000000111111100000000000000000"
+        "00000001111111100000000000000000"
+        "00000001111111100000000000000000"
+        "00000001111111100000000000000000"
+        "00000001111111111111000000000000"
+        "00000001111111111111111000000000"
+        "00000011111111111111111100000000"
+        "00000011111111111111111100000000"
+        "00000011111111111111111100000000"
+        "00000001111111111111111110000000"
+        "00000001111111111111111110000000"
+        "00000000111111111100111111100000"
+        "00000000111111111000111111100000"
+        "00000000011111111000111111110000"
+        "00000000011111111111111111000000"
+        "00000000001111111111111111000000"
+        "00000000000111111111111111000000"
+        "00000000000001111111111110000000"
+        "00000000000000000111100000000000"
+    )]).reshape(1, 1024)
+    predicted_label = classify(test_data_vector, train_data, train_labels)
     print(f"预测的标签: {predicted_label}")
\ No newline at end of file