generated from LufsX/Experiment-kNN
This commit is contained in:
+30
-39
@@ -28,50 +28,34 @@ import os
|
||||
id = "202210423215"
|
||||
name = "章程鸿·"
|
||||
|
||||
|
||||
import numpy as np
|
||||
import os
|
||||
from collections import Counter
|
||||
|
||||
|
||||
def classify(input_vector, dataSet, labels, k=2):
|
||||
"""
|
||||
使用 KNN 算法对输入样本进行分类。
|
||||
|
||||
参数:
|
||||
- input_vector (numpy array): 输入待分类的样本(1xN)。
|
||||
- dataSet (numpy array): 训练数据集(MxN)。
|
||||
- labels (list or numpy array): 训练集对应的标签。
|
||||
- k (int): kNN 算法参数,默认值为 2。
|
||||
- input_vector (numpy array): 输入待分类的样本(1xN)。
|
||||
- dataSet (numpy array): 训练数据集(MxN)。
|
||||
- labels (list or numpy array): 训练集对应的标签。
|
||||
- k (int): kNN 算法参数,默认值为 2。
|
||||
|
||||
返回:
|
||||
- int: 预测的分类标签。
|
||||
- int: 预测的分类标签。
|
||||
"""
|
||||
# 计算马氏距离
|
||||
centered_dataSet = dataSet - np.mean(dataSet, axis=0)
|
||||
centered_input_vector = input_vector - np.mean(dataSet, axis=0)
|
||||
cov_matrix = np.cov(centered_dataSet.T)
|
||||
if np.linalg.det(cov_matrix) == 0:
|
||||
raise ValueError("协方差矩阵不可逆")
|
||||
inv_cov_matrix = np.linalg.inv(cov_matrix)
|
||||
mahalanobis_distances = np.sqrt(np.sum(centered_input_vector.dot(inv_cov_matrix) * centered_input_vector, axis=1))
|
||||
|
||||
sorted_indices = mahalanobis_distances.argsort()
|
||||
k_nearest_distances = mahalanobis_distances[sorted_indices[:k]]
|
||||
# 计算输入向量与训练集之间的欧氏距离
|
||||
distances = np.sum((input_vector - dataSet) ** 2, axis=1)
|
||||
# 根据距离排序并获取索引
|
||||
sorted_indices = distances.argsort()
|
||||
# 选择距离最近的k个点
|
||||
k_nearest_labels = labels[sorted_indices[:k]]
|
||||
|
||||
# 计算权重(距离的倒数)
|
||||
weights = 1 / k_nearest_distances
|
||||
# 归一化权重
|
||||
weights /= weights.sum()
|
||||
|
||||
# 计算加权投票
|
||||
weighted_votes = np.zeros((10,))
|
||||
for label, weight in zip(k_nearest_labels, weights):
|
||||
weighted_votes[label] += weight
|
||||
|
||||
return np.argmax(weighted_votes)
|
||||
|
||||
# 统计k个点中各类别的数量
|
||||
count = Counter(k_nearest_labels)
|
||||
# 返回数量最多的类别标签
|
||||
return count.most_common(1)[0][0]
|
||||
|
||||
def load_dataset(directory):
|
||||
"""
|
||||
@@ -81,24 +65,29 @@ def load_dataset(directory):
|
||||
- directory (str): 数据文件夹路径。
|
||||
|
||||
返回:
|
||||
- np.array: 特征数据(Mx1024)。
|
||||
- np.array: 标签数据(Mx1)。
|
||||
- np.array: 特征数据(Mx1024)。
|
||||
- np.array: 标签数据(Mx1)。
|
||||
"""
|
||||
# 初始化特征数据列表和标签列表
|
||||
feature_list = []
|
||||
label_list = []
|
||||
# 遍历目录中的所有文件
|
||||
for file in os.listdir(directory):
|
||||
# 获取文件的完整路径
|
||||
file_path = os.path.join(directory, file)
|
||||
# 将图像文件转换为向量
|
||||
feature_vector = img_to_vector(file_path)
|
||||
# 将特征向量添加到列表中
|
||||
feature_list.append(feature_vector)
|
||||
# 获取文件名中的标签并添加到标签列表中
|
||||
label_list.append(int(file.split('_')[0]))
|
||||
# 将特征列表和标签列表转换为numpy数组
|
||||
feature_matrix = np.array(feature_list)
|
||||
label_array = np.array(label_list)
|
||||
|
||||
# 特征缩放
|
||||
# 特征缩放(如果需要)
|
||||
feature_matrix = feature_matrix / 255.0
|
||||
return feature_matrix, label_array
|
||||
|
||||
|
||||
def img_to_vector(filename):
|
||||
"""
|
||||
将二值图像转换为向量。
|
||||
@@ -109,14 +98,17 @@ def img_to_vector(filename):
|
||||
Returns:
|
||||
- np.array: 二值图像向量。
|
||||
"""
|
||||
vector = np.zeros((1024,))
|
||||
# 初始化向量
|
||||
vector = np.zeros((1024,)) # 创建一个一维数组
|
||||
# 打开文件并逐行读取
|
||||
with open(filename) as file:
|
||||
for i, line in enumerate(file):
|
||||
vector[i * 32:i * 32 + 32] = np.array([int(char) for char in line.strip()])
|
||||
# 将每行的数字字符转换为整数并存储到向量中
|
||||
vector[i*32:i*32+32] = np.array([int(char) for char in line.strip()])
|
||||
return vector
|
||||
|
||||
|
||||
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 = (
|
||||
@@ -160,4 +152,3 @@ if __name__ == "__main__":
|
||||
)
|
||||
|
||||
print(f"预测的标签: {predicted_label}")
|
||||
|
||||
|
||||
Reference in New Issue
Block a user