Marcus Kalander

There is an `np.int64` used [here](https://github.com/huawei-noah/trustworthyAI/blob/87586265edf5fc842882b46b18dd29a38c2da032/gcastle/castle/algorithms/gradient/rl/torch/rl.py#L410) which could be the reason for the error. You can try to change it to `int` similarly to how the `np.int32` were changed.

Yes, we agree with you. This is something we are trying to push for internally but it concerns the open-source policy of our lab and may be hard to achieve...

Hello, The data generation in the web GUI uses the DAG.erdos_renyi method to simulate a random weighted DAG: https://github.com/huawei-noah/trustworthyAI/blob/2e08a7aab82e7ea6ba340ecbfccb427b67e3be3f/gcastle/castle/datasets/simulator.py#L161-L174 The [Erdős–Rényi](https://en.wikipedia.org/wiki/Erd%C5%91s%E2%80%93R%C3%A9nyi_model) model is built upon the idea that each edge...

Hello, Prior knowledge is something we plan to include in all algorithms in the future (as also mentioned in #72). However, there is no timeline for this as of yet.

@AlxndrMlk Any contributions in this direction are very welcome! Prior knowledge can be a bit more difficult to integrate into some of the algorithms as compared with PC. If you...

Since the model is first fit and then used to predict future values, the prediction of a moving average model would always be the mean of the last `window` number...

Hello, Thank you for your question and sorry for the late reply. Since we are generating data with synthetic anomalies, before running `scale_anomaly` both the predict and real values are...

Hello, Thank you very much for your interest! Regarding the forecast method, I still do not have any good solution when most values are zero. The approach I suggest is...

For RiskLoc, it tries to find as a good explanation for the error as possible so if there is no good plausible root cause first in the first layers it...

I have also encountered this problem. Did you manage to solve this in any way?