-
-
Notifications
You must be signed in to change notification settings - Fork 40
Show factor correlations for oblique rotations #1114
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Summary of Changes
Hello @strengejacke, 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 interpretability of Exploratory Factor Analysis (EFA) results by introducing the display of factor correlations. Specifically, when an oblique rotation method is applied, the summary output will now include a dedicated table showing the correlations between the extracted factors, providing crucial insights into their relationships.
Highlights
- Core Feature: Implemented the display of factor correlations in the summary output for Exploratory Factor Analysis (EFA) when oblique rotations are used.
- Data Processing: Enhanced the
summary.parameters_efafunction to extract and attach the factor correlation matrix (Phi) as an attribute to the summary object for oblique rotations. - Output Formatting: Updated the HTML (
print_html.R), Markdown (print_md.R), and text (print.parameters_efa_summaryinutils_pca_efa.R) print methods to correctly render the newly available factor correlation tables alongside the explained variance summary. - Helper Function: Introduced a new internal helper function
.is_oblique_rotationto reliably identify common oblique rotation methods. - Testing: Added new snapshot tests to
test-factor_analysis.Rand a corresponding snapshot file_snaps/factor_analysis.mdto ensure the correct and consistent display of factor correlations in the output.
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.
Footnotes
-
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. ↩
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Code Review
The pull request successfully adds support for displaying factor correlations when oblique rotations are used in factor analysis. Key changes include updating the summary generation to include these correlations and modifying print handlers for console, HTML, and Markdown to display them. Tests with snapshots have been added to cover this new functionality. Feedback includes making the rotation name check case-insensitive in .is_oblique_rotation for robustness, and aligning the HTML output format for factor correlations with the Markdown and console outputs (i.e., using two separate tables instead of merging them into one) for consistency. Overall, the changes are a valuable addition.
|
@gemini-code-assist review |
There was a problem hiding this 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 introduces functionality to show factor correlations for oblique rotations and introduces a new factor_scores() function. The changes are generally well-implemented with updated documentation and tests. I have suggested some minor improvements.
No description provided.