generated from LufsX/Experiment-kNN
This commit is contained in:
+57
-74
@@ -41,81 +41,64 @@ name = "李劲"
|
||||
|
||||
|
||||
# 这里写自己的代码实现
|
||||
def classify(input_vector, dataSet, labels, k=3):
|
||||
"""
|
||||
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,请**自行设置默认值**,评测时仅会使用其默认值,不修改默认值将**无法通过**评测,**成绩为零**。
|
||||
|
||||
Returns:
|
||||
- int: 预测的分类标签。
|
||||
"""
|
||||
# 计算欧式距离
|
||||
distances = np.linalg.norm(dataSet - input_vector, axis=1)
|
||||
|
||||
# 获取距离最近的 k 个样本的索引
|
||||
k_indices = np.argsort(distances)[:k]
|
||||
|
||||
# 获取最近邻样本的标签
|
||||
k_nearest_labels = [labels[i] for i in k_indices]
|
||||
|
||||
# 找出出现次数最多的标签
|
||||
most_common = max(set(k_nearest_labels), key=k_nearest_labels.count)
|
||||
|
||||
return most_common
|
||||
|
||||
# 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**。
|
||||
|
||||
Args:
|
||||
- directory (str): 数据文件夹路径。
|
||||
|
||||
Returns:
|
||||
- np.array: 特征数据。
|
||||
- np.array: 标签数据。
|
||||
"""
|
||||
features = []
|
||||
labels = []
|
||||
|
||||
# 遍历文件夹中的所有文件
|
||||
for filename in os.listdir(directory):
|
||||
if filename.endswith(".txt"): # 假设文件是 .txt 格式
|
||||
filepath = os.path.join(directory, filename)
|
||||
|
||||
# 假设文件名格式为 "数字_编号.txt"
|
||||
label = int(filename.split('_')[0])
|
||||
|
||||
# 加载文件中的二进制数据并转换为 1D 向量
|
||||
image_vector = img_to_vector(filepath)
|
||||
|
||||
features.append(image_vector)
|
||||
labels.append(label)
|
||||
|
||||
return np.array(features), np.array(labels)
|
||||
|
||||
# 这里还写自己的代码实现
|
||||
def img_to_vector(filename):
|
||||
"""
|
||||
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。
|
||||
"""
|
||||
def classify(input_vector, dataSet, labels, k=3):
|
||||
"""
|
||||
KNN 分类算法。
|
||||
"""
|
||||
# 计算欧式距离
|
||||
distances = np.linalg.norm(dataSet - input_vector, axis=1)
|
||||
|
||||
# 获取距离最近的 k 个样本的索引
|
||||
k_indices = np.argsort(distances)[:k]
|
||||
|
||||
# 获取最近邻样本的标签
|
||||
k_nearest_labels = [labels[i] for i in k_indices]
|
||||
|
||||
# 找出出现次数最多的标签
|
||||
from collections import Counter
|
||||
most_common = Counter(k_nearest_labels).most_common(1)[0][0]
|
||||
|
||||
return most_common
|
||||
|
||||
with open(filename) as file:
|
||||
lines = file.readlines()
|
||||
image_vector = np.array([int(char) for line in lines for char in line.strip()])
|
||||
|
||||
def load_dataset(directory):
|
||||
"""
|
||||
从文件夹中加载数据。
|
||||
"""
|
||||
features = []
|
||||
labels = []
|
||||
|
||||
# 遍历文件夹中的所有文件
|
||||
for filename in os.listdir(directory):
|
||||
if filename.endswith(".txt"): # 假设文件是 .txt 格式
|
||||
filepath = os.path.join(directory, filename)
|
||||
|
||||
try:
|
||||
# 假设文件名格式为 "数字_编号.txt"
|
||||
label = int(filename.split('_')[0])
|
||||
|
||||
# 加载文件中的二进制数据并转换为 1D 向量
|
||||
image_vector = img_to_vector(filepath)
|
||||
|
||||
features.append(image_vector)
|
||||
labels.append(label)
|
||||
except Exception as e:
|
||||
print(f"Error processing file {filepath}: {e}")
|
||||
|
||||
return np.array(features), np.array(labels)
|
||||
|
||||
def img_to_vector(filename):
|
||||
"""
|
||||
将二值图像转换为向量。
|
||||
"""
|
||||
try:
|
||||
with open(filename) as file:
|
||||
lines = file.readlines()
|
||||
image_vector = np.array([int(char) for line in lines for char in line.strip()])
|
||||
except Exception as e:
|
||||
print(f"Error reading file {filename}: {e}")
|
||||
image_vector = np.zeros(expected_vector_length) # 假设有一个预期的向量长度
|
||||
# 或者可以抛出一个异常,根据需求决定
|
||||
|
||||
return image_vector
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
Reference in New Issue
Block a user