Verbose dt pfn

[noahho]

No description provided.

[gemini-code-assist]

Summary of Changes

Hello @noahho, 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!

This pull request significantly enhances the observability of the DecisionTreeTabPFN and TabPFNRegressor models by introducing comprehensive verbose logging. The changes are designed to provide developers and users with more detailed runtime information about the model's operations, including data processing, tree construction, and prediction logic, without altering the core functionality. This will greatly assist in debugging and understanding the model's behavior.

Highlights

• Enhanced Verbosity and Logging: Integrated the logging module and added numerous conditional logging statements throughout the DecisionTreeTabPFN and TabPFNRegressor classes. These logs provide detailed insights into the model's internal processes, such as data shapes, adaptive tree decisions, tree fitting progress, leaf fitting, and pruning outcomes.
• Improved Debuggability: The new logging statements, activated when self.verbose is true, offer a clearer view of the execution flow within the decision tree, aiding in debugging and understanding the model's behavior at various stages of fitting and prediction.
• Configurable Logging: A basic logging configuration has been added to set the default logging level to INFO, ensuring that verbose messages are captured when enabled.

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 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. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

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.

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. ↩

[Copilot]

Pull Request Overview

This PR adds comprehensive logging functionality to the DecisionTreeTabPFN implementation to provide verbose output during training and prediction processes.

• Adds logging configuration and verbose logging statements throughout the decision tree fitting and prediction pipeline
• Enables detailed progress tracking for adaptive tree operations, leaf fitting, and node-level predictions
• Replaces empty verbose placeholder methods with actual logging statements

---

_{Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.}

[gemini-code-assist]

Code Review

This pull request introduces verbose logging to the DecisionTreeTabPFN classes, which is a valuable addition for debugging and understanding the model's behavior. The logging is controlled by the verbose flag, which is good. However, the implementation uses logging.basicConfig() to configure the root logger. This is not a recommended practice for libraries, as it can interfere with the logging setup of applications that use this library. My review focuses on refactoring the logging to follow best practices for libraries, which involves using a named, module-level logger and leaving the configuration to the application.

[gemini-code-assist]

Configuring the root logger with logging.basicConfig() in a library is not recommended as it can interfere with the logging configuration of the application using the library. A library should not configure handlers on the root logger. Instead, it should use a module-level logger and let the application configure the logging.¹

Please remove this basicConfig call. You should define a module-level logger at the top of the file (e.g., after imports) like logger = logging.getLogger(__name__) and then use logger.info() and logger.warning() for logging.

Style Guide References

Footnotes

1. Python's official logging HOWTO for libraries advises against calling basicConfig and instead using logging.getLogger(__name__) to allow the application developer to control logging configuration. ↩