DeepTime

DeepTime copied to clipboard

Hello, thank you for sharing the code. I have a question. Can this model be predicted based on only one time feature after training? How can it be predicted? Is...

YHU11

How to debug or How to rewrite the code to start through the main function such as Informer or Autoformer

2

I want to debug the code and use my own sql data,I change the "Fire(ForecastExperiment)" into " forcastexp = ForecastExperiment(config_path='storage/experiments/ECL/96M/repeat=0/config.gin') forcastexp.instance(model_type='deeptime')",but it not work.I would be very grateful if you...

linbingkong

- Add function to enable loading of model from experiments config. - Add Makefile steps to extract last log message for all hp_search experiments.

xhoong

How to run your code in Windows

6

hello, My computer system is Windows. There are always errors when I run `make`. Can I write a method to run it directly in `python xx.py` without using `make`. For...

sophia-sxx

Bumps [scipy](https://github.com/scipy/scipy) from 1.7.3 to 1.10.0. Release notes Sourced from scipy's releases. SciPy 1.10.0 Release Notes SciPy 1.10.0 is the culmination of 6 months of hard work. It contains many...

dependabot[bot]

Hello, Thankyou for releasing the code I am trying to plot the trues and preds of the test data, But the values normalized So, I tried to denormalize the preds...

Niharikajo

``` model = DeepTIMe(.... model.fit(X, y) y_pred = model.predict(.. ``` See `XGBoost` as an example. Thanks

diegolovison

def __getitem__(self, idx: int) -> Tuple[np.ndarray, np.ndarray, np.ndarray, np.ndarray]: if self.time_features: dim_idx = idx // self.n_time_samples dim_slice = slice(dim_idx, dim_idx + 1) idx = idx % self.n_time_samples else: dim_slice =...

YHU11