更新 function.py

2024-10-17 16:47:09 +08:00
parent 1deeaa7cda
commit 2e25a652c5
1 changed files with 79 additions and 76 deletions
@@ -1,6 +1,8 @@
+陈垣豪:
 # function.py
 import numpy as np
 import os
+from collections import Counter

 """
 实验说明:
@@ -39,87 +41,88 @@ name = "李潼"
 - int: 预测的分类标签。
 """

+
+# 这里写自己的代码实现
 def classify(input_vector, dataSet, labels, k=3):
-    """
-    KNN 分类算法。
+    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

-    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。
-    """
-    dataSet_size = dataSet.shape[0]
-    diff_mat = np.tile(input_vector, (dataSet_size, 1)) - dataSet
-    sq_diff_mat = diff_mat ** 2
-    sq_distances = sq_diff_mat.sum(axis=1)
-    distances = sq_distances ** 0.5
-    sorted_dist_indices = np.argsort(distances)
-    class_count = {}
-    for i in range(k):
-        vote_label = labels[sorted_dist_indices[i]]
-        class_count[vote_label] = class_count.get(vote_label, 0) + 1
-    sorted_class_count = sorted(class_count.items(), key=lambda x: x[1], reverse=True)
-    return sorted_class_count[0][0]

+# 这里也写自己的代码实现
 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**。
+    file_list = os.listdir(directory)
+    num_files = len(file_list)
+    dataSet = np.zeros((num_files, 1024))
+    labels = []

-    Args:
-    - directory (str): 数据文件夹路径。
+    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))

-    Returns:
-    - np.array: 特征数据。
-    - np.array: 标签数据。
-    """
-    training_files = os.listdir(directory)
-    features = []
-    labels = []
-    for file in training_files:
-        label = int(file.split('_')[0])
-        with open(os.path.join(directory, file), 'r') as f:
-            content = f.read().strip()
-            feature = [int(char) for char in content]
-            features.append(feature)
-            labels.append(label)
-    return np.array(features), np.array(labels)
+    return dataSet, np.array(labels)
+
+
+# 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

 if __name__ == "__main__":
-    train_data, train_labels = load_dataset("trainingDigits")
-    test_data = (
-        "00000000000000110000000000000000"
-        "00000000000011111000000000000000"
-        "00000000000011111100000000000000"
-        "00000000001111111110000000000000"
-        "00000000001111111110000000000000"
-        "00000000001111111100000000000000"
-        "00000000011111111000000000000000"
-        "00000000111111111000000000000000"
-        "00000000111111110000000000000000"
-        "00000000111111110000000000000000"
-        "00000000111111110000000000000000"
-        "00000000111111110000000000000000"
-        "00000000111111110000000000000000"
-        "00000001111111110000000000000000"
-        "00000001111111110000000000000000"
-        "00000001111111110000000000000000"
-        "00000001111111111111111111111111"
-        "11111111111111111111111111111111"
-        "11111111111111111111111111111111"
-        "11111111111111111111111111111111"
-        "11111111111111111111111111111111"
-        "11111111111111111111111111111111"
-        "11111111111111111111111111111111"
-        "11111111111111111111111111111111"
-        "1111111111111111111"
-    )
-    predicted_label = classify(
-        np.array([int(char) for char in test_data]).reshape(-1, 64),
-        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"
+     
+
+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}")
+
+