diff --git a/.gitlab-ci.yml b/.gitlab-ci.yml new file mode 100644 index 0000000000000000000000000000000000000000..548da28c2710ff01ee39f03485d5425e65c0da27 --- /dev/null +++ b/.gitlab-ci.yml @@ -0,0 +1,23 @@ +default: + image: docker:26.0.1-dind + +stages: + - build + +variables: + PACKAGE_NAME: "pandas" + DOCKER_IMAGE: "$CI_REGISTRY_IMAGE/$PACKAGE_NAME" + DOCKER_TLS_CERTDIR: "/certs" + +before_script: + - unset DOCKER_HOST + - docker login -u "$CI_REGISTRY_USER" -p "$CI_REGISTRY_PASSWORD" $CI_REGISTRY + +push_docker_image: + stage: build + image: docker:26.0.1-dind + script: + - docker build -t $DOCKER_IMAGE:$CI_COMMIT_SHORT_SHA -f docker/Dockerfile . + - docker push $DOCKER_IMAGE:$CI_COMMIT_SHORT_SHA + only: + - main # Only run on the main branch diff --git a/README.md b/README.md index 1a273fdb896c5c1e3699268029d282e811ceaf51..860d1dad60d02bac10cd53e5f29edc2ed0d7d527 100644 --- a/README.md +++ b/README.md @@ -1,190 +1,93 @@ -<picture align="center"> - <source media="(prefers-color-scheme: dark)" srcset="https://pandas.pydata.org/static/img/pandas_white.svg"> - <img alt="Pandas Logo" src="https://pandas.pydata.org/static/img/pandas.svg"> -</picture> - ------------------ - -# pandas: powerful Python data analysis toolkit - -| | | -| --- | --- | -| Testing | [](https://github.com/pandas-dev/pandas/actions/workflows/unit-tests.yml) [](https://codecov.io/gh/pandas-dev/pandas) | -| Package | [](https://pypi.org/project/pandas/) [](https://pypi.org/project/pandas/) [](https://anaconda.org/conda-forge/pandas) [](https://anaconda.org/conda-forge/pandas) | -| Meta | [](https://numfocus.org) [](https://doi.org/10.5281/zenodo.3509134) [](https://github.com/pandas-dev/pandas/blob/main/LICENSE) [](https://pandas.pydata.org/docs/dev/development/community.html?highlight=slack#community-slack) | - - -## What is it? - -**pandas** is a Python package that provides fast, flexible, and expressive data -structures designed to make working with "relational" or "labeled" data both -easy and intuitive. It aims to be the fundamental high-level building block for -doing practical, **real world** data analysis in Python. Additionally, it has -the broader goal of becoming **the most powerful and flexible open source data -analysis / manipulation tool available in any language**. It is already well on -its way towards this goal. - -## Table of Contents - -- [Main Features](#main-features) -- [Where to get it](#where-to-get-it) -- [Dependencies](#dependencies) -- [Installation from sources](#installation-from-sources) -- [License](#license) -- [Documentation](#documentation) -- [Background](#background) -- [Getting Help](#getting-help) -- [Discussion and Development](#discussion-and-development) -- [Contributing to pandas](#contributing-to-pandas) - -## Main Features -Here are just a few of the things that pandas does well: - - - Easy handling of [**missing data**][missing-data] (represented as - `NaN`, `NA`, or `NaT`) in floating point as well as non-floating point data - - Size mutability: columns can be [**inserted and - deleted**][insertion-deletion] from DataFrame and higher dimensional - objects - - Automatic and explicit [**data alignment**][alignment]: objects can - be explicitly aligned to a set of labels, or the user can simply - ignore the labels and let `Series`, `DataFrame`, etc. automatically - align the data for you in computations - - Powerful, flexible [**group by**][groupby] functionality to perform - split-apply-combine operations on data sets, for both aggregating - and transforming data - - Make it [**easy to convert**][conversion] ragged, - differently-indexed data in other Python and NumPy data structures - into DataFrame objects - - Intelligent label-based [**slicing**][slicing], [**fancy - indexing**][fancy-indexing], and [**subsetting**][subsetting] of - large data sets - - Intuitive [**merging**][merging] and [**joining**][joining] data - sets - - Flexible [**reshaping**][reshape] and [**pivoting**][pivot-table] of - data sets - - [**Hierarchical**][mi] labeling of axes (possible to have multiple - labels per tick) - - Robust IO tools for loading data from [**flat files**][flat-files] - (CSV and delimited), [**Excel files**][excel], [**databases**][db], - and saving/loading data from the ultrafast [**HDF5 format**][hdfstore] - - [**Time series**][timeseries]-specific functionality: date range - generation and frequency conversion, moving window statistics, - date shifting and lagging - - - [missing-data]: https://pandas.pydata.org/pandas-docs/stable/user_guide/missing_data.html - [insertion-deletion]: https://pandas.pydata.org/pandas-docs/stable/user_guide/dsintro.html#column-selection-addition-deletion - [alignment]: https://pandas.pydata.org/pandas-docs/stable/user_guide/dsintro.html?highlight=alignment#intro-to-data-structures - [groupby]: https://pandas.pydata.org/pandas-docs/stable/user_guide/groupby.html#group-by-split-apply-combine - [conversion]: https://pandas.pydata.org/pandas-docs/stable/user_guide/dsintro.html#dataframe - [slicing]: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#slicing-ranges - [fancy-indexing]: https://pandas.pydata.org/pandas-docs/stable/user_guide/advanced.html#advanced - [subsetting]: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#boolean-indexing - [merging]: https://pandas.pydata.org/pandas-docs/stable/user_guide/merging.html#database-style-dataframe-or-named-series-joining-merging - [joining]: https://pandas.pydata.org/pandas-docs/stable/user_guide/merging.html#joining-on-index - [reshape]: https://pandas.pydata.org/pandas-docs/stable/user_guide/reshaping.html - [pivot-table]: https://pandas.pydata.org/pandas-docs/stable/user_guide/reshaping.html - [mi]: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#hierarchical-indexing-multiindex - [flat-files]: https://pandas.pydata.org/pandas-docs/stable/user_guide/io.html#csv-text-files - [excel]: https://pandas.pydata.org/pandas-docs/stable/user_guide/io.html#excel-files - [db]: https://pandas.pydata.org/pandas-docs/stable/user_guide/io.html#sql-queries - [hdfstore]: https://pandas.pydata.org/pandas-docs/stable/user_guide/io.html#hdf5-pytables - [timeseries]: https://pandas.pydata.org/pandas-docs/stable/user_guide/timeseries.html#time-series-date-functionality - -## Where to get it -The source code is currently hosted on GitHub at: -https://github.com/pandas-dev/pandas - -Binary installers for the latest released version are available at the [Python -Package Index (PyPI)](https://pypi.org/project/pandas) and on [Conda](https://anaconda.org/conda-forge/pandas). - -```sh -# conda -conda install -c conda-forge pandas -``` +# pandas -```sh -# or PyPI -pip install pandas -``` -The list of changes to pandas between each release can be found -[here](https://pandas.pydata.org/pandas-docs/stable/whatsnew/index.html). For full -details, see the commit logs at https://github.com/pandas-dev/pandas. -## Dependencies -- [NumPy - Adds support for large, multi-dimensional arrays, matrices and high-level mathematical functions to operate on these arrays](https://www.numpy.org) -- [python-dateutil - Provides powerful extensions to the standard datetime module](https://dateutil.readthedocs.io/en/stable/index.html) -- [pytz - Brings the Olson tz database into Python which allows accurate and cross platform timezone calculations](https://github.com/stub42/pytz) +## Getting started -See the [full installation instructions](https://pandas.pydata.org/pandas-docs/stable/install.html#dependencies) for minimum supported versions of required, recommended and optional dependencies. +To make it easy for you to get started with GitLab, here's a list of recommended next steps. -## Installation from sources -To install pandas from source you need [Cython](https://cython.org/) in addition to the normal -dependencies above. Cython can be installed from PyPI: +Already a pro? Just edit this README.md and make it your own. Want to make it easy? [Use the template at the bottom](#editing-this-readme)! -```sh -pip install cython -``` +## Add your files -In the `pandas` directory (same one where you found this file after -cloning the git repo), execute: +- [ ] [Create](https://docs.gitlab.com/ee/user/project/repository/web_editor.html#create-a-file) or [upload](https://docs.gitlab.com/ee/user/project/repository/web_editor.html#upload-a-file) files +- [ ] [Add files using the command line](https://docs.gitlab.com/ee/gitlab-basics/add-file.html#add-a-file-using-the-command-line) or push an existing Git repository with the following command: -```sh -pip install . +``` +cd existing_repo +git remote add origin https://gitlab.rc.uab.edu/bhbelay/pandas.git +git branch -M main +git push -uf origin main ``` -or for installing in [development mode](https://pip.pypa.io/en/latest/cli/pip_install/#install-editable): +## Integrate with your tools +- [ ] [Set up project integrations](https://gitlab.rc.uab.edu/bhbelay/pandas/-/settings/integrations) -```sh -python -m pip install -ve . --no-build-isolation -Ceditable-verbose=true -``` +## Collaborate with your team -See the full instructions for [installing from source](https://pandas.pydata.org/docs/dev/development/contributing_environment.html). +- [ ] [Invite team members and collaborators](https://docs.gitlab.com/ee/user/project/members/) +- [ ] [Create a new merge request](https://docs.gitlab.com/ee/user/project/merge_requests/creating_merge_requests.html) +- [ ] [Automatically close issues from merge requests](https://docs.gitlab.com/ee/user/project/issues/managing_issues.html#closing-issues-automatically) +- [ ] [Enable merge request approvals](https://docs.gitlab.com/ee/user/project/merge_requests/approvals/) +- [ ] [Set auto-merge](https://docs.gitlab.com/ee/user/project/merge_requests/merge_when_pipeline_succeeds.html) -## License -[BSD 3](LICENSE) +## Test and Deploy + +Use the built-in continuous integration in GitLab. -## Documentation -The official documentation is hosted on [PyData.org](https://pandas.pydata.org/pandas-docs/stable/). +- [ ] [Get started with GitLab CI/CD](https://docs.gitlab.com/ee/ci/quick_start/index.html) +- [ ] [Analyze your code for known vulnerabilities with Static Application Security Testing (SAST)](https://docs.gitlab.com/ee/user/application_security/sast/) +- [ ] [Deploy to Kubernetes, Amazon EC2, or Amazon ECS using Auto Deploy](https://docs.gitlab.com/ee/topics/autodevops/requirements.html) +- [ ] [Use pull-based deployments for improved Kubernetes management](https://docs.gitlab.com/ee/user/clusters/agent/) +- [ ] [Set up protected environments](https://docs.gitlab.com/ee/ci/environments/protected_environments.html) -## Background -Work on ``pandas`` started at [AQR](https://www.aqr.com/) (a quantitative hedge fund) in 2008 and -has been under active development since then. +*** -## Getting Help +# Editing this README -For usage questions, the best place to go to is [StackOverflow](https://stackoverflow.com/questions/tagged/pandas). -Further, general questions and discussions can also take place on the [pydata mailing list](https://groups.google.com/forum/?fromgroups#!forum/pydata). +When you're ready to make this README your own, just edit this file and use the handy template below (or feel free to structure it however you want - this is just a starting point!). Thanks to [makeareadme.com](https://www.makeareadme.com/) for this template. -## Discussion and Development -Most development discussions take place on GitHub in this repo, via the [GitHub issue tracker](https://github.com/pandas-dev/pandas/issues). +## Suggestions for a good README -Further, the [pandas-dev mailing list](https://mail.python.org/mailman/listinfo/pandas-dev) can also be used for specialized discussions or design issues, and a [Slack channel](https://pandas.pydata.org/docs/dev/development/community.html?highlight=slack#community-slack) is available for quick development related questions. +Every project is different, so consider which of these sections apply to yours. The sections used in the template are suggestions for most open source projects. Also keep in mind that while a README can be too long and detailed, too long is better than too short. If you think your README is too long, consider utilizing another form of documentation rather than cutting out information. -There are also frequent [community meetings](https://pandas.pydata.org/docs/dev/development/community.html#community-meeting) for project maintainers open to the community as well as monthly [new contributor meetings](https://pandas.pydata.org/docs/dev/development/community.html#new-contributor-meeting) to help support new contributors. +## Name +Choose a self-explaining name for your project. -Additional information on the communication channels can be found on the [contributor community](https://pandas.pydata.org/docs/development/community.html) page. +## Description +Let people know what your project can do specifically. Provide context and add a link to any reference visitors might be unfamiliar with. A list of Features or a Background subsection can also be added here. If there are alternatives to your project, this is a good place to list differentiating factors. -## Contributing to pandas +## Badges +On some READMEs, you may see small images that convey metadata, such as whether or not all the tests are passing for the project. You can use Shields to add some to your README. Many services also have instructions for adding a badge. -[](https://www.codetriage.com/pandas-dev/pandas) +## Visuals +Depending on what you are making, it can be a good idea to include screenshots or even a video (you'll frequently see GIFs rather than actual videos). Tools like ttygif can help, but check out Asciinema for a more sophisticated method. -All contributions, bug reports, bug fixes, documentation improvements, enhancements, and ideas are welcome. +## Installation +Within a particular ecosystem, there may be a common way of installing things, such as using Yarn, NuGet, or Homebrew. However, consider the possibility that whoever is reading your README is a novice and would like more guidance. Listing specific steps helps remove ambiguity and gets people to using your project as quickly as possible. If it only runs in a specific context like a particular programming language version or operating system or has dependencies that have to be installed manually, also add a Requirements subsection. -A detailed overview on how to contribute can be found in the **[contributing guide](https://pandas.pydata.org/docs/dev/development/contributing.html)**. +## Usage +Use examples liberally, and show the expected output if you can. It's helpful to have inline the smallest example of usage that you can demonstrate, while providing links to more sophisticated examples if they are too long to reasonably include in the README. -If you are simply looking to start working with the pandas codebase, navigate to the [GitHub "issues" tab](https://github.com/pandas-dev/pandas/issues) and start looking through interesting issues. There are a number of issues listed under [Docs](https://github.com/pandas-dev/pandas/issues?labels=Docs&sort=updated&state=open) and [good first issue](https://github.com/pandas-dev/pandas/issues?labels=good+first+issue&sort=updated&state=open) where you could start out. +## Support +Tell people where they can go to for help. It can be any combination of an issue tracker, a chat room, an email address, etc. -You can also triage issues which may include reproducing bug reports, or asking for vital information such as version numbers or reproduction instructions. If you would like to start triaging issues, one easy way to get started is to [subscribe to pandas on CodeTriage](https://www.codetriage.com/pandas-dev/pandas). +## Roadmap +If you have ideas for releases in the future, it is a good idea to list them in the README. -Or maybe through using pandas you have an idea of your own or are looking for something in the documentation and thinking ‘this can be improved’...you can do something about it! +## Contributing +State if you are open to contributions and what your requirements are for accepting them. -Feel free to ask questions on the [mailing list](https://groups.google.com/forum/?fromgroups#!forum/pydata) or on [Slack](https://pandas.pydata.org/docs/dev/development/community.html?highlight=slack#community-slack). +For people who want to make changes to your project, it's helpful to have some documentation on how to get started. Perhaps there is a script that they should run or some environment variables that they need to set. Make these steps explicit. These instructions could also be useful to your future self. -As contributors and maintainers to this project, you are expected to abide by pandas' code of conduct. More information can be found at: [Contributor Code of Conduct](https://github.com/pandas-dev/.github/blob/master/CODE_OF_CONDUCT.md) +You can also document commands to lint the code or run tests. These steps help to ensure high code quality and reduce the likelihood that the changes inadvertently break something. Having instructions for running tests is especially helpful if it requires external setup, such as starting a Selenium server for testing in a browser. -<hr> +## Authors and acknowledgment +Show your appreciation to those who have contributed to the project. + +## License +For open source projects, say how it is licensed. -[Go to Top](#table-of-contents) +## Project status +If you have run out of energy or time for your project, put a note at the top of the README saying that development has slowed down or stopped completely. Someone may choose to fork your project or volunteer to step in as a maintainer or owner, allowing your project to keep going. You can also make an explicit request for maintainers. diff --git a/docker/.gitkeep b/docker/.gitkeep new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/docker/Dockerfile b/docker/Dockerfile new file mode 100644 index 0000000000000000000000000000000000000000..3e6b8c591eff7e15c8058a9760b2b9b6c42be5f1 --- /dev/null +++ b/docker/Dockerfile @@ -0,0 +1,17 @@ +FROM python:3.10.8 +WORKDIR /home/pandas + +RUN apt-get update && apt-get -y upgrade +RUN apt-get install -y build-essential bash-completion + +# hdf5 needed for pytables installation +# libgles2-mesa needed for pytest-qt +RUN apt-get install -y libhdf5-dev libgles2-mesa-dev + +RUN python -m pip install --upgrade pip +COPY requirements-dev.txt /tmp +RUN python -m pip install -r /tmp/requirements-dev.txt +RUN git config --global --add safe.directory /home/pandas + +ENV SHELL "/bin/bash" +CMD ["/bin/bash"] \ No newline at end of file