Skip to content

Conversation

@shiweijiezero
Copy link
Contributor

@shiweijiezero shiweijiezero commented Nov 12, 2025

Description

Fix alfworld dataset loading to use correct train/test split
Fix Bug, Process Bar

Checklist

Please check the following items before code is ready to be reviewed.

  • Code has passed all tests
  • Docstrings have been added/updated in Google Style
  • Documentation has been updated
  • Code is ready for review

@gemini-code-assist
Copy link
Contributor

Summary of Changes

Hello @shiweijiezero, 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 resolves an issue in the alfworld dataset loading script by ensuring that the training and testing data splits are sourced from their appropriate directories. Previously, both splits were drawn from the training data, leading to an incorrect evaluation setup. The updated script now correctly distinguishes between training and validation data sources and provides more flexible control over dataset sizing, defaulting to using the entire available dataset for each split.

Highlights

  • Corrected Dataset Splitting: The alfworld dataset loading logic has been updated to correctly separate training data from the train directory and testing data from the valid_seen directory, resolving an issue where both splits were previously drawn from the training data.
  • Flexible Data Sizing: The create_dataset_files function now allows train_size and test_size parameters to be None, which defaults to using all available files from their respective source directories if no specific size is provided.
  • Default Full Dataset Usage: The main execution block has been modified to call create_dataset_files without specifying train_size or test_size arguments, ensuring that the full alfworld dataset is used by default for both training and testing splits.
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 by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

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 pull request 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.

Copy link
Contributor

@gemini-code-assist gemini-code-assist bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Code Review

This pull request correctly addresses a bug in the alfworld dataset creation script. Previously, the test set was incorrectly sampled from the training data. The new implementation properly uses the train and valid_seen splits from the alfworld dataset for creating the training and test sets, respectively. I have provided one suggestion to correct a typo and refactor a part of the code to be more idiomatic, which will improve maintainability.

@pan-x-c pan-x-c merged commit af7f8aa into modelscope:main Nov 14, 2025
1 check passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants