etna
etna copied to clipboard
tinkoff-ai
ETNA – Time-Series Library
### 🚀 Feature Request Add transform to encode time series change point intervals. ### Proposal Encode time series change point intervals . ### Test cases _No response_ ### Additional context...
### 🚀 Feature Request In a lot of places we use `df.loc[:, pd.IndexSlice[segments, column]]` to select `column` from all the segments. It appears to be very slow on a lot...
### 🚀 Feature Request We need to teach our transforms work with dataset instead of dataframe ### Proposal 1. In `Transform`: - Add method `get_regressors_info() -> `List[str]` - Return the...
**IMPORTANT: Please do not create a Pull Request without creating an issue first.** ## Before submitting (must do checklist) - [x] Did you read the [contribution guide](https://github.com/tinkoff-ai/etna/blob/master/CONTRIBUTING.md)? - [x] Did...
### 🚀 Feature Request Add `in_column` attribute to all the transforms, if there is no such attribute yet. This attribute will be used by the transform to get only the...
### 🐛 Bug Report Currently, `DeepARModel` during each forecast predicts different values. It seems like it is not a general problem for neural nets: `TFTModel` predicts the same values each...
### 🚀 Feature Request Currently we can't make in-sample predictions with `BATS`/`TBATS`, we are throwing exception because [underlying library](https://github.com/intive-DataScience/tbats) doesn't support it. However, according to mathematical formulation this possibility exist...
### 🚀 Feature Request Currently we can't make with `nn` models * in-sample predictions * out-sample predictions there `ts` isn't going straight after the train and only on `horizon` steps...
### 🚀 Feature Request Create data access methods in TSDataset to be used by the transforms in the future ### Proposal Create methods: 1. `update_columns_from_pandas(df: pd.DataFrame, regressors: Optional[List[str]]=None)`: - `df`...
### 🐛 Bug Report There are few cases where we create a new `TSDataset` from the old one and assign the same attributes instead of copying them: * [TSDataset.make_future](https://github.com/tinkoff-ai/etna/blob/master/etna/datasets/tsdataset.py#L237) *...