Feat/imputation improvements

[jorgeMFS]

Summary by Sourcery

Introduce a flexible, strategy-agnostic imputation framework with global and per-column settings and mask-and-score tuning; enhance GUI, CLI scripts, and reporting diagnostics; update documentation; bump version to 1.2.0; fix GUI metric defaults and typing compatibility.

New Features:

• Add strategy-agnostic imputation panel supporting global and per-column configuration with optional mask-and-score tuning
• Add clinical_all_features_e2e.py script for comprehensive clinical pipeline runs
• Include categorical PSI and Cramér’s V metrics in bias diagnostics with per-variable trigger reporting

Bug Fixes:

• Fix GUI quality metrics picker defaults for dict-style configuration
• Resolve Python 3.9 typing compatibility issue in the GUI

Enhancements:

• Make minor tuning UI improvements

Build:

• Bump project version to 1.2.0

Documentation:

• Update README and usage docs to reflect new strategy-agnostic imputation and tuning options

[sourcery-ai]

Reviewer's guide (collapsed on small PRs)

Reviewer's Guide

This PR overhauls imputation to be strategy-agnostic with global and per-column tuning, refreshes documentation and reporting (including categorical bias metrics), adds a comprehensive clinical E2E script, bumps version to 1.2.0, and delivers GUI bug fixes and compatibility improvements.

Class diagram for imputation configuration and strategy selection

classDiagram
    class ImputationConfig {
      +strategy: str
      +params: dict
      +per_column: dict
      +tuning: bool
    }
    class Imputer {
      +fit_transform(data)
      +set_strategy(strategy)
      +set_params(params)
      +set_per_column(per_column)
      +run_tuning()
    }
    ImputationConfig <|-- Imputer
    Imputer o-- "1..*" ImputationStrategy
    class ImputationStrategy {
      +name: str
      +apply(data, params)
    }
    ImputationStrategy <|-- MeanImputer
    ImputationStrategy <|-- MedianImputer
    ImputationStrategy <|-- ModeImputer
    ImputationStrategy <|-- KNNImputer
    ImputationStrategy <|-- MICEImputer
    ImputationStrategy <|-- SVDImputer
    ImputationStrategy <|-- NoneImputer

Loading

Class diagram for bias metrics reporting

classDiagram
    class BiasMetrics {
      +numeric_metrics: list
      +categorical_metrics: list
      +report_triggers(variable)
    }
    BiasMetrics <|-- NumericBiasMetrics
    BiasMetrics <|-- CategoricalBiasMetrics
    class NumericBiasMetrics {
      +SMD
      +VarianceRatio
      +KS
    }
    class CategoricalBiasMetrics {
      +PSI
      +CramersV
    }

Loading

File-Level Changes

Change	Details	Files
Implement strategy-agnostic imputation and tuning	Revamped README to support global strategy with optional per-column overrides Extended mask-and-score tuning to all imputation methods Adjusted config YAML examples for new parameters	README.md
Add comprehensive clinical end-to-end script	Documented new scripts/clinical_all_features_e2e.py in README Noted the addition in CHANGELOG	README.md CHANGELOG.md
Enhance bias reporting with categorical metrics	Included PSI and Cramér’s V metrics with per-variable trigger indicators Updated bias description in CLI workflow bullets	README.md CHANGELOG.md
Bump project version to 1.2.0	Updated version in pyproject.toml and src/phenoqc/init.py Added new 1.2.0 section in CHANGELOG	pyproject.toml src/phenoqc/__init__.py CHANGELOG.md
Apply GUI bug fixes and compatibility tweaks	Fixed quality metrics picker defaults for dict-style metrics Resolved Python 3.9 typing issues with minor UI tuning improvements	CHANGELOG.md

---

Tips and commands

Interacting with Sourcery

• Trigger a new review: Comment @sourcery-ai review on the pull request.
• Continue discussions: Reply directly to Sourcery's review comments.
• Generate a GitHub issue from a review comment: Ask Sourcery to create an
  issue from a review comment by replying to it. You can also reply to a
  review comment with @sourcery-ai issue to create an issue from it.
• Generate a pull request title: Write @sourcery-ai anywhere in the pull
  request title to generate a title at any time. You can also comment
  @sourcery-ai title on the pull request to (re-)generate the title at any time.
• Generate a pull request summary: Write @sourcery-ai summary anywhere in
  the pull request body to generate a PR summary at any time exactly where you
  want it. You can also comment @sourcery-ai summary on the pull request to
  (re-)generate the summary at any time.
• Generate reviewer's guide: Comment @sourcery-ai guide on the pull
  request to (re-)generate the reviewer's guide at any time.
• Resolve all Sourcery comments: Comment @sourcery-ai resolve on the
  pull request to resolve all Sourcery comments. Useful if you've already
  addressed all the comments and don't want to see them anymore.
• Dismiss all Sourcery reviews: Comment @sourcery-ai dismiss on the pull
  request to dismiss all existing Sourcery reviews. Especially useful if you
  want to start fresh with a new review - don't forget to comment
  @sourcery-ai review to trigger a new review!

Customizing Your Experience

Access your dashboard to:

• Enable or disable review features such as the Sourcery-generated pull request
  summary, the reviewer's guide, and others.
• Change the review language.
• Add, remove or edit custom review instructions.
• Adjust other review settings.

Getting Help

• Contact our support team for questions or feedback.
• Visit our documentation for detailed guides and information.
• Keep in touch with the Sourcery team by following us on X/Twitter, LinkedIn or GitHub.

[sourcery-ai]

Hey there - I've reviewed your changes and they look great!

---

Sourcery is free for open source - if you like our reviews please consider sharing them ✨

• X
• Mastodon
• LinkedIn
• Facebook

_{Help me be more useful! Please click 👍 or 👎 on each comment and I'll use the feedback to improve your reviews.}

[codecov-commenter]

⚠️ Please install the to ensure uploads and comments are reliably processed by Codecov.

Codecov Report

✅ All modified and coverable lines are covered by tests.
❗ Your organization needs to install the Codecov GitHub app to enable full functionality.

Files with missing lines	Coverage Δ
src/phenoqc/__init__.py	100.00% <100.00%> (ø)

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.