etna
etna copied to clipboard
tinkoff-ai
ETNA – Time-Series Library
## Before submitting (must do checklist) - [x] Did you read the [contribution guide](https://github.com/tinkoff-ai/etna/blob/master/CONTRIBUTING.md)? - [x] Did you update the docs? We use Numpy format for all the methods and...
### 🚀 Feature Request We decided that we want to enable passing context into `forecast` method of the model. It will be done with a new parameter: `prediction_size`. First `n...
### 🚀 Feature Request We should delete untaged docker images because they use extra space. ### Proposal - [ ] Github workflow script on cron. - [Github docker registry api...
## Before submitting (must do checklist) - [x] Did you read the [contribution guide](https://github.com/tinkoff-ai/etna/blob/master/CONTRIBUTING.md)? - [x] Did you update the docs? We use Numpy format for all the methods and...
### 🚀 Feature Request Create runner objects for computing handling. We just pass function `func` and `args` and `kwargs` via `__call__`. - `etna.auto.runner.LocalRunner` would just call passed function with given...
### 🚀 Feature Request Create class `etna.auto.optuna.Optuna` which would handle logic around using optuna: - method `tune` runs `study.optimize` via given `runner` Copy `etna.auto.optuna.sampler.ConfigSampler` as is. ### Proposal `Optuna`: ```python...
N.B. Blocked by #854 , #853 ### 🚀 Feature Request Create `etna.auto.Auto` class which supposed to search optimal solution from defined config pool. - Config pool could be extended -...
## Before submitting (must do checklist) - [ ] Did you read the [contribution guide](https://github.com/tinkoff-ai/etna/blob/master/CONTRIBUTING.md)? - [ ] Did you update the docs? We use Numpy format for all the...
### 🐛 Bug Report I have a Time-Series Regressor model with `timestamp`, `segment`, `target` and other exogenious features. The model runs in the Kaggle notebook. ``` pf_transform = PytorchForecastingTransform( max_encoder_length=HORIZON,...
### 🚀 Feature Request Currenlty, `determine_num_steps` uses linear probing that results in $O(n^2)$ time. We can reduce it to $O(n)$ by making a next step from the last tried point...