generated from LufsX/Experiment-kNN
This commit is contained in:
+64
-67
@@ -40,86 +40,83 @@ name = "焦国波"
|
||||
"""
|
||||
|
||||
|
||||
# 这里写自己的代码实现
|
||||
def classify(input_vector, dataSet, labels, k=0):
|
||||
"""
|
||||
KNN 分类算法。
|
||||
import os
|
||||
import numpy as np
|
||||
from sklearn.model_selection import train_test_split
|
||||
from sklearn.neighbors import KNeighborsClassifier
|
||||
from sklearn.metrics import accuracy_score
|
||||
import time
|
||||
|
||||
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**。
|
||||
def load_data(directory):
|
||||
images = []
|
||||
labels = []
|
||||
for filename in os.listdir(directory):
|
||||
if filename.endswith(".png"):
|
||||
label = int(filename.split('_')[0])
|
||||
image = np.array([int(pixel) for pixel in open(os.path.join(directory, filename), 'rb').read()])
|
||||
images.append(image)
|
||||
labels.append(label)
|
||||
return np.array(images), np.array(labels)
|
||||
|
||||
Returns:
|
||||
- int: 预测的分类标签。
|
||||
"""
|
||||
# 加载训练集和测试集
|
||||
X_train, y_train = load_data('trainingDigits')
|
||||
X_test, y_test = load_data('testDigits')
|
||||
|
||||
# 数据预处理：将图像数据转换为向量形式
|
||||
X_train = X_train.reshape((X_train.shape[0], -1))
|
||||
X_test = X_test.reshape((X_test.shape[0], -1))
|
||||
|
||||
|
||||
# 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。
|
||||
# 初始化KNN模型
|
||||
knn = KNeighborsClassifier(n_neighbors=3)
|
||||
|
||||
Returns:
|
||||
- np.array: 特征数据。
|
||||
- np.array: 标签数据。
|
||||
"""
|
||||
# 训练模型
|
||||
start_time = time.time()
|
||||
knn.fit(X_train, y_train)
|
||||
end_time = time.time()
|
||||
print(f"Training time: {end_time - start_time} seconds")
|
||||
|
||||
|
||||
# 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。
|
||||
# 预测测试集
|
||||
start_time = time.time()
|
||||
y_pred = knn.predict(X_test)
|
||||
end_time = time.time()
|
||||
|
||||
Returns:
|
||||
- np.array: 二值图像向量。
|
||||
"""
|
||||
# 计算分类精度
|
||||
accuracy = accuracy_score(y_test, y_pred)
|
||||
print(f"Accuracy: {accuracy * 100:.2f}%")
|
||||
print(f"Prediction time: {end_time - start_time} seconds")
|
||||
|
||||
|
||||
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")
|
||||
from sklearn.model_selection import GridSearchCV
|
||||
|
||||
test_data = (
|
||||
"00000000000000110000000000000000"
|
||||
"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"
|
||||
# 参数网格
|
||||
param_grid = {
|
||||
'n_neighbors': [3, 5, 7, 9],
|
||||
'metric': ['euclidean', 'manhattan'],
|
||||
'algorithm': ['auto', 'ball_tree', 'kd_tree']
|
||||
}
|
||||
|
||||
# 网格搜索
|
||||
grid_search = GridSearchCV(KNeighborsClassifier(), param_grid, cv=5)
|
||||
grid_search.fit(X_train, y_train)
|
||||
|
||||
# 最佳参数
|
||||
print("Best parameters:", grid_search.best_params_)
|
||||
|
||||
# 使用最佳参数重新训练模型
|
||||
best_knn = grid_search.best_estimator_
|
||||
best_knn.fit(X_train, y_train)
|
||||
|
||||
# 重新评估性能
|
||||
start_time = time.time()
|
||||
y_pred = best_knn.predict(X_test)
|
||||
end_time = time.time()
|
||||
accuracy = accuracy_score(y_test, y_pred)
|
||||
print(f"Optimized Accuracy: {accuracy * 100:.2f}%")
|
||||
print(f"Optimized Prediction time: {end_time - start_time} seconds")
|
||||
"00000000000000000111100000000000"
|
||||
)
|
||||
predicted_label = classify(
|
||||
|
||||
Reference in New Issue
Block a user