ploomber VS statsforecast

- One-click sharing powered by Ploomber Cloud: https://ploomber.io

Documentation: https://jupysql.ploomber.io

Note that JupySQL is a fork of ipython-sql; which is no longer actively developed. Catherine, ipython-sql's creator, was kind enough to pass the project to us (check out ipython-sql's README).

We'd love to learn what you think and what features we can ship for JupySQL to be the best SQL client! Please let us know in the comments!

For those who don't know, Jupyter has a bash kernel: https://github.com/takluyver/bash_kernel

And you can run Jupyter notebooks from the CLI with Ploomber: https://github.com/ploomber/ploomber

Develop notebook-based pipelines

Fair point. MLflow has a lot of features to cover the end-to-end dev cycle. This SQLite tracker only covers the experiment tracking part.

We have another project to cover the orchestration/pipelines aspect: https://github.com/ploomber/ploomber and we have plans to work on the rest of features. For now, we're focusing on those two.

We started with an open-source framework to help data practitioners make their work reproducible. However, after months of building and learning from our community, we realized that many needed help with the setup: getting Python installed, getting dependencies, running experiments locally, etc.

It really depends on your use cases, I've seen a lot of those tools that lock you into a certain syntax, framework or weird language (for instance Groovy). If you'd like to use core python or Jupyter notebooks I'd recommend Ploomber, the community support is really strong, there's an emphasis on observability and you can deploy it on any executor like Slurm, AWS Batch or Airflow. In addition, there's a free managed compute (cloud edition) where you can run certain bioinformatics flows like Alphafold or Cripresso2

btw, you can export Ploomber to Argo and Airflow!

As a second option, we will use Ploomber with serial execution, which also has a Python API that allows us to execute different notebooks using the NotebookRunner function:

I also recommend checking ploomber out, this open source can help you build code as templates, parallelize it and parameterize it. There are also some reporting and debugging tools in there!

I can't find the TimeGPT-1 model.

LICENSE Apache-2

https://github.com/Nixtla/statsforecast/blob/main/LICENSE

Mentions ARIMA, ETS, CES, and Theta modeling

Model development on Prophet stopped this year: https://medium.com/@cuongduong_35162/facebook-prophet-in-202...

They recommend checking out these for cutting-edge time series forecasting:

https://neuralprophet.com/

https://nixtla.github.io/statsforecast/

If you only have historical data: StatsForecast

I also recommend you check Nixtla's libraries, in particular StatsForecast and HierarchicalForecast. They offer a wide selection of forecasting models, and can work with multiple time series. Given that you're working with many products in a warehouse, I think the hierarchical forecast can be very useful, especially for the short time series (the ones that don't seem to have enough time stamps).

If you are mostly worried about time and use python you could try out Nixtla's statsforecast as it is very snappy. https://github.com/Nixtla/statsforecast

- https://nixtla.github.io/statsforecast/

Leaving these two repos here for anyone interested in trying decision tree regression or statistical forecasting baselines: - https://nixtla.github.io/mlforecast/ - https://github.com/Nixtla/statsforecast

In other experiments, we have shown that: - AutoETS is 32% more accurate and 104x faster than NeuralProphet: https://github.com/Nixtla/statsforecast/tree/main/experiments/neuralprophet - AutoARIMA is 17% more accurate and 37x faster than Prophet: https://github.com/Nixtla/statsforecast/tree/main/experiments/arima_prophet_adapter -  MSTL is 26% more accurate than Prophet and 2 times faster. - MSTL is 24% more accurate than NeuralProphet and 11 times faster: https://github.com/Nixtla/statsforecast/tree/main/experiments/mstl - In the M5 competition, AutoETS is 11% more accurate and 2 times faster than Prophet: https://nixtla.github.io/statsforecast/examples/prophet_spark_m5.html