fix(datasets): fix dtype backend

[fmind]

Fixes #39

[gemini-code-assist]

Hello @fmind, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

Summary of Changes

This pull request addresses an issue related to the dtype_backend in the ParquetReader class within the bikes project. The primary change involves modifying the read method of the ParquetReader to utilize the self.backend attribute instead of hardcoding pyarrow as the dtype_backend when reading a parquet file. Additionally, the pull request includes updates to the python_env.yaml and requirements.txt files, which seem to be related to dependency management and environment configuration.

Highlights

• Bug Fix: The dtype_backend in ParquetReader was hardcoded to pyarrow. This PR fixes it to use self.backend.
• Dependency Updates: The python_env.yaml and requirements.txt files have been updated, likely to reflect changes in project dependencies.

Changelog

• python_env.yaml
  • Added/updated dependencies in the python environment.
• requirements.txt
  • Added/updated dependencies in the requirements file.
• src/bikes/io/datasets.py
  • Modified the read method in ParquetReader to use self.backend for dtype_backend when reading parquet files. Line 77 was changed.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point in your pull request via creating an issue comment (i.e. comment on the pull request page) using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in issue comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist is currently in preview and may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments to provide feedback.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

---

Trivia time!

What is Apache Parquet's primary design goal?

Click here for the answer

Apache Parquet is designed for efficient data storage and retrieval. It excels at columnar storage, which allows for optimized query performance, especially when dealing with large datasets.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

The pull request updates the project to use Python 3.13, uv for package management, and just for task automation. It also updates various dependencies and configurations to align with these changes. The removal of invoke and transition to just is a significant change.

Summary of Findings

• Dependency Updates: The pull request updates several dependencies, including mlflow, numpy, pandas, and others. It's important to ensure that these updates are compatible with the existing codebase and that no regressions are introduced.
• Migration from Invoke to Just: The project migrates from PyInvoke to Just for task automation. This involves removing the invoke.yaml file and replacing it with a justfile. The tasks defined in tasks/ are also updated to use Just syntax.
• Python Version Update: The project is updated to use Python 3.13. This requires updating the .python-version, Dockerfile, .pre-commit-config.yaml, and pyproject.toml files to reflect the new Python version.

Merge Readiness

The pull request introduces significant changes to the project, including updating the Python version, migrating from Invoke to Just, and updating dependencies. While the changes seem well-organized, it's crucial to thoroughly test the updated codebase to ensure compatibility and prevent regressions. Given the scope of the changes, I recommend that the pull request not be merged until sufficient testing has been performed. I am unable to approve this pull request, and users should have others review and approve this code before merging.