paso is a set of function and class method operations for data wrangling for Machine Learning and Deep Learning models. paso is Spanish for the English word step. A paso class or function is a step in your analysis pipeline. Because paso follows a protocol, the set of all operations in paso can be called a framework.
Data engineers and Machine Learning Scientists appreciate the value of having their tools span across the data science workflow. The framework paso has been designed to fit in such all encompassing frameworks, as mlflow and Berkeley Data Analytics Stack(BDAS). It has been designed for pre-processing and post-processing data wrangling to and from learning packages such as PyTorch, Tensorflow, XGBoost and scikit-learn. It has been designed to work with a large number of evolving visialization tools such as facet, matplotlib, seaborn, Tensorboard, and plotly, to name just a few.
You can contribute to the paso Project in many ways. Below are listed some of the areas:
- Fix a typo(s) in documentation.
- Improve some of the documentation.
- Fix typo or/and improve a docstring(s).
- Report a documentation bug.
- Improve existing test or/and code more tests.
- Execute test suite for a distribution candidate and report any test failures.
- Post a new issue.
- Fix a bug in a issue.
- Re-factor some code to add functionality or improve performance.
- Suggest a new feature.
- Implement a new feature.
- Improve or/and add a lesson.
Remember to post in issues the proposed change and if accepted it will be closed. See issues or projects for open issues for the paso project.
You can find a issue , or you can post a new issue, to work on. Next, or your alternative first step, you need to set-up your local paso development environment. Code, Documentation and Test can have separate or shared environments. Each one is discussed in the documentation..
Installation
paso requires python3.5 or above.
pip install paso