COAP

Installation

1. Create a python environment

   conda create -n coap python=3.12
   conda activate coap

2. Install pytorch

   Following the official website's guidance (https://pytorch.org/get-started/locally/), install the corresponding PyTorch version based on your CUDA version. For our experiments, we use torch 2.6.0+cu116. The installation command is as follows:

   pip install torch==2.6.0+cu116 torchvision==0.21.0+cu116 torchaudio==2.6.0 --extra-index-url https://download.pytorch.org/whl/cu116

3. Install other related dependencies

   pip install -r requirements.txt

Data Preparation

First, you need to specify the data_path and dataset in the /eventlog directory.

• /eventlog/ORI: stores the original files
• /eventlog/csv: stores the event stream (CSV) files

Running

You can run the following code to reproduce the experimental results on different datasets. The experimental logs and the corresponding results are available in the /log and /results directories.

python main.py