Skip to content

feat: Add CodeFeatureExtractor for 8-dim commit features #77

@noahgift

Description

@noahgift

Summary

Add feature extraction for commit-level defect prediction matching org-intel's 8-dimensional feature vector.

Feature Vector

pub struct CommitFeatures {
    pub defect_category: u8,
    pub files_changed: f32,
    pub lines_added: f32,
    pub lines_deleted: f32,
    pub complexity_delta: f32,
    pub timestamp: f64,
    pub hour_of_day: u8,
    pub day_of_week: u8,
}

Requirements

  • Extract features from git diff/commit metadata
  • Normalize features for ML pipeline
  • Support batch extraction

References

  • D'Ambros et al. (2012) defect prediction benchmark
  • org-intel CommitFeatures struct

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type
    No fields configured for issues without a type.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions