更新 function.py

function.py

@@ -1,4 +1,3 @@
-陈垣豪:
 # function.py
 import numpy as np
 import os
@@ -42,87 +41,107 @@ name = "李潼"
 """
 
 
-# 这里写自己的代码实现
 def classify(input_vector, dataSet, labels, k=3):
-    distances = np.linalg.norm(dataSet - input_vector, axis=1)
-    nearest_indices = np.argsort(distances)[:k]
-    nearest_labels = [labels[i] for i in nearest_indices]
-    most_common_label = Counter(nearest_labels).most_common(1)[0][0]
-    return most_common_label
+    """
+    KNN 分类算法。
 
+    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。
+    """
+    dataSetSize = dataSet.shape[0]
+    diffMat = np.tile(input_vector, (dataSetSize, 1)) - dataSet
+    sqDiffMat = diffMat ** 2
+    sqDistances = sqDiffMat.sum(axis=1)
+    distances = sqDistances ** 0.5
+    sortedDistIndices = distances.argsort()
+    classCount = {}
+    for i in range(k):
+        voteIlabel = labels[sortedDistIndices[i]]
+        classCount[voteIlabel] = classCount.get(voteIlabel, 0) + 1
+    sortedClassCount = sorted(classCount.items(), key=lambda x: x[1], reverse=True)
+    return sortedClassCount[0][0]
 
-# 这里也写自己的代码实现
 def load_dataset(directory):
-    file_list = os.listdir(directory)
-    num_files = len(file_list)
-    dataSet = np.zeros((num_files, 1024))
-    labels = []
+    """
+    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**。
 
-    for i, filename in enumerate(file_list):
-        label = int(filename.split('_')[0])
-        labels.append(label)
-        dataSet[i, :] = img_to_vector(os.path.join(directory, filename))
+    Args:
+    - directory (str): 数据文件夹路径。
 
-    return dataSet, np.array(labels)
+    Returns:
+    - np.array: 特征数据。
+    - np.array: 标签数据。
+    """
+    trainingFileList = os.listdir(directory)
+    m = len(trainingFileList)
+    trainingMat = np.zeros((m, 1024))
+    hwLabels = []
+    for i in range(m):
+        fileNameStr = trainingFileList[i]
+        fileStr = fileNameStr.split('.')[0]
+        classNumStr = int(fileStr.split('_')[0])
+        hwLabels.append(classNumStr)
+        trainingMat[i, :] = img_to_vector(os.path.join(directory, fileNameStr))
+    return trainingMat, hwLabels
 
-
-# 这里还写自己的代码实现
 def img_to_vector(filename):
-    return_vector = np.zeros((1, 1024))
-    with open(filename) as f:
-        for i in range(32):
-            line_str = f.readline()
-            for j in range(32):
-                return_vector[0, i * 32 + j] = int(line_str[j])
-    return return_vector
+    """
+    将二值图像转换为向量。
+    该部分应为 load_dataset 函数的辅助子函数，可单独在这里实现，也可直接集成至 load_dataset 函数中。
+
+    Args:
+    - filename (str): 图像文件路径。
+
+    Returns:
+    - np.array: 二值图像向量。
+    """
+    returnVect = np.zeros((1, 1024))
+    fr = open(filename)
+    for i in range(32):
+        lineStr = fr.readline()
+        for j in range(32):
+            returnVect[0, 32 * i + j] = int(lineStr[j])
+    return returnVect
 
 if __name__ == "__main__":
-    # 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 = (
-        "00000000000000110000000000000000"
-        "00000000000011111000000000000000"
-     
-
-陈垣豪:
-"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),
-        train_data,
-        train_labels,
-    )
-
-    print(f"预测的标签: {predicted_label}")
-
+    # 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 = (
+        "00000000000000110000000000000000"
+        "00000000000011111000000000000000"
+        "00000000000011111100000000000000"
+        "00000000001111111110000000000000"
+        "00000000001111111110000000000000"
+        "00000000001111111100000000000000"
+        "00000000011111111000000000000000"
+        "00000000111111111000000000000000"
+        "00000000111111110000000000000000"
+        "00000000111111110000000000000000"
+        "00000000111111110000000000000000"
+        "00000000111111110000000000000000"
+        "00000000111111110000000000000000"
+        "00000001111111111111111111111111"
+        "11111111111111111111111111111111"
+        "11111111111111111111111111111111"
+        "11111111111111111111111111111111"
+        "11111111111111111111111111111111"
+        "11111111111111111111111111111111"
+        "11111111111111111111111111111111"
+        "11111111111111111111111111111111"
+        "11111111111111111111111111111111"
+        "11111111111111111111111111111111"
+        "11111111111111111111111111111"
+    )
+    predicted_label = classify(
+        np.array([int(char) for char in test_data]).reshape(-1, 32),
+        train_data,
+        train_labels,
+    )
+    print(f"预测的标签： {predicted_label}")