KL-CPD is an algorithm for change point and anomaly detection in time series.
More information can be found in the 2019 paper Kernel Change-point Detection with Auxiliary Deep Generative Models.
from klcpd import KL_CPD
dim, seq_length = 1, 100
ts = np.random.randn(seq_length,dim)
device = torch.device('cuda')
model = KL_CPD(dim).to(device)
model.fit(ts)
preds = model.predict(ts)
print(preds)pip install git+https://github.com/HolyBayes/klcpd
@article{chang2019kernel,
title={Kernel change-point detection with auxiliary deep generative models},
author={Chang, Wei-Cheng and Li, Chun-Liang and Yang, Yiming and P{\'o}czos, Barnab{\'a}s},
journal={arXiv preprint arXiv:1901.06077},
year={2019}
}
Artem Ryzhikov, LAMBDA laboratory, Higher School of Economics, Yandex School of Data Analysis
E-mail: artemryzhikoff@yandex.ru
Linkedin: https://www.linkedin.com/in/artem-ryzhikov-2b6308103/