Here is the repo for our paper ``Maat: Performance Metric Anomaly Anticipation for Cloud Services with Conditional Diffusion'', accepted by ASE 2023.
The data should be stored in csv files with the first column being timestamp'' and the last column being label''. If labels are not avaliable, it can be all zeros.
We put an example dataset (part of the AIOps18 dataset due to the space limit) in the ``data'' director.
.
├── dataload.py
├── detect.py
├── extract_feat.py
├── model
│ ├── PixelCNN.py
│ ├── detection.py
│ ├── diffusion.py
│ ├── network.py
│ ├── prediction.py
│ └── util.py
├── predict.py
├── requirements.txt
└── util.py
We support python3.x $ pip install -r requirements.txt
For the prediction phase, run:
$ cd src && python predict.py
For the detection phase, you should first extract features and then run:
$ cd src && python detect.py