All notable changes to this project will be documented in this file.
The format is based on Keep a Changelog, and this project adheres to Semantic Versioning.
- MedianOutliersTransform, DensityOutliersTransform (#30)
- Issues and Pull Request templates
- TSDataset checks (#24, #20)\
- Pytorch-Forecasting models (#29)
- SARIMAX model (#10)
- Logging, including ConsoleLogger (#46)
- WandbLogger (#71)
- Correlation heatmap plotter (#77)
- Backtest is fully parallel
- New default hyperparameters for CatBoost
- Documentation fixes (#55, #53, #52)
- Solved warning in LogTransform and AddConstantTransform (#26)
- Regressors does not have enough history bug (#35)
- make_future(1) and make_future(2) bug
- Fix working with 'cap' and 'floor' features in Prophet model (#62))
- Fix saving init params for SARIMAXModel (#81)
- Imports of nn models, PytorchForecastingTransform and Transform (#80))
- Models
- CatBoost
- Prophet
- Seasonal Moving Average
- Naive
- Linear
- Transforms
- Rolling statistics
- Trend removal
- Segment encoder
- Datetime flags
- Sklearn skalers (MinMax, Robust, MinMaxAbs, Standard, MaxAbs)
- BoxCox, YeoJohnson, LogTransform
- Lag operator
- NaN imputer
- TimeSeriesCrossValidation
- Time Series Dataset (TSDataset)
- Playground datasets generation (AR, constant, periodic, from pattern)
- Matrics (MAE, MAPE, SMAPE, MedAE, MSE, MSLE, R^2)
- EDA mehods
- Outliers detection
- PACF plot
- Cross correlation plot
- Destribution plot
- Anomalies (Outliers) plot
- Backtest (CrossValidation) plot
- Forecast plot