Feat/imputation improvements

.devcontainer/devcontainer.json

@@ -0,0 +1,33 @@
+{
+  "name": "Python 3",
+  // Or use a Dockerfile or Docker Compose file. More info: https://containers.dev/guide/dockerfile
+  "image": "mcr.microsoft.com/devcontainers/python:1-3.11-bullseye",
+  "customizations": {
+    "codespaces": {
+      "openFiles": [
+        "README.md",
+        "streamlit_app.py"
+      ]
+    },
+    "vscode": {
+      "settings": {},
+      "extensions": [
+        "ms-python.python",
+        "ms-python.vscode-pylance"
+      ]
+    }
+  },
+  "updateContentCommand": "[ -f packages.txt ] && sudo apt update && sudo apt upgrade -y && sudo xargs apt install -y <packages.txt; [ -f requirements.txt ] && pip3 install --user -r requirements.txt; pip3 install --user streamlit; echo '✅ Packages installed and Requirements met'",
+  "postAttachCommand": {
+    "server": "streamlit run streamlit_app.py --server.enableCORS false --server.enableXsrfProtection false"
+  },
+  "portsAttributes": {
+    "8501": {
+      "label": "Application",
+      "onAutoForward": "openPreview"
+    }
+  },
+  "forwardPorts": [
+    8501
+  ]
+}

CHANGELOG.md

@@ -1,17 +1,23 @@
+## [1.2.1] - 2025-08-14
+- Packaging: enrich pyproject metadata (authors, classifiers, dependencies, URLs) and set README content-type for PyPI
+
 ## [1.2.0] - 2025-08-14
+
 - GUI: strategy-agnostic imputation panel (config-driven; per-column overrides; generic tuning)
 - GUI: fix quality metrics picker defaults when config uses dict-style metrics
 - Reporting: include categorical PSI/Cramér's V in bias warning header and per-row triggers
 - Scripts: add clinical_all_features_e2e.py (full dataset/schema/config/custom mappings; online+offline runs)
 - Fix: Python 3.9 compatibility in GUI typing; minor tuning UI improvements
 
 ## [1.1.1] - 2025-01-13
+
 - feat: add class distribution bar chart to PDF and Markdown reports
 - feat: persist per-file *_qc_summary.json with quality_scores, imputation, class_distribution
 - fix: Python 3.9 typing compatibility in ImputationEngine (avoid PEP 604 unions)
 - chore: docs and scripts updated to assert and document new artifact
 
 ## [1.1.0] - 2025-01-13
+
 - feat: Optional class-distribution summary (label-aware)
   - CLI: `--label-column`, `--imbalance-threshold`
   - GUI: label column selector and threshold input
@@ -23,6 +29,7 @@
   - PDF/MD: Imputation Settings and Tuning Summary sections
 - fix: Redundancy metric deduplication (prefer identical over correlation)
 - test: Added unit tests for class distribution, imputation params, tuning skeleton, and config load
+
 # Changelog
 
 All notable changes to PhenoQC will be documented in this file.

README.md

@@ -210,7 +210,11 @@ imputation:
 Launch the Streamlit interface:
 
 ```bash
+# Local
 python run_gui.py
+
+# Streamlit Community Cloud
+# In the deploy UI, set the entrypoint to `streamlit_app.py`
 ```
 
 Workflow:

pyproject.toml

@@ -4,10 +4,51 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "phenoqc"
-version = "1.2.0"
+version = "1.2.1"
 requires-python = ">=3.9"
 description = "Phenotypic Data Quality Control Toolkit for Genomic Data Infrastructure (GDI)"
-readme = "README.md"
+readme = { file = "README.md", content-type = "text/markdown" }
+license = { file = "LICENSE" }
+authors = [
+  { name = "Jorge Miguel Ferreira da Silva" }
+]
+classifiers = [
+  "Programming Language :: Python :: 3",
+  "Programming Language :: Python :: 3.9",
+  "License :: OSI Approved :: MIT License",
+  "Operating System :: OS Independent",
+  "Intended Audience :: Science/Research",
+  "Topic :: Scientific/Engineering :: Bio-Informatics",
+]
+dependencies = [
+  "pandas",
+  "jsonschema",
+  "requests",
+  "plotly",
+  "reportlab",
+  "streamlit",
+  "pyyaml",
+  "kaleido>=0.1.0",
+  "tqdm",
+  "Pillow",
+  "scikit-learn",
+  "fancyimpute",
+  "fastjsonschema",
+  "pronto",
+  "psutil",
+  "rapidfuzz",
+  "streamlit-aggrid",
+  "ucimlrepo",
+]
+
+[project.optional-dependencies]
+test = ["pytest"]
+
+[project.urls]
+Homepage = "https://github.com/jorgeMFS/PhenoQC"
+Repository = "https://github.com/jorgeMFS/PhenoQC.git"
+Documentation = "https://phenoqc.readthedocs.io/en/latest/"
+Issues = "https://github.com/jorgeMFS/PhenoQC/issues"
 
 [project.scripts]
 phenoqc = "phenoqc.cli:main"

requirements.txt

@@ -17,3 +17,4 @@ psutil
 rapidfuzz
 streamlit-aggrid
 ucimlrepo
+watchdog

src/phenoqc/__init__.py

@@ -1,2 +1,2 @@
-__version__ = "1.2.0"
+__version__ = "1.2.1"
 

src/phenoqc/gui/gui.py

@@ -942,8 +942,15 @@ def _render_params(spec: dict, initial: Optional[dict] = None) -> dict:
         # Protected columns
         st.subheader("Protected columns (excluded from imputation/tuning)")
         protected_defaults = st.session_state['config'].get('protected_columns', []) or []
-        protected_selected = st.multiselect("Select protected columns", options=all_columns, default=protected_defaults,
-                                            help="These columns are excluded from the imputation feature matrix and tuning.")
+        # Streamlit requires defaults to be a subset of options; sanitize to avoid errors when
+        # config contains columns not present in the current dataset (e.g., on first load).
+        safe_protected_defaults = [c for c in protected_defaults if c in (all_columns or [])]
+        protected_selected = st.multiselect(
+            "Select protected columns",
+            options=all_columns,
+            default=safe_protected_defaults,
+            help="These columns are excluded from the imputation feature matrix and tuning.",
+        )
         st.session_state['config']['protected_columns'] = protected_selected
 
         # Redundancy metric settings

streamlit_app.py

@@ -0,0 +1,30 @@
+#!/usr/bin/env python3
+
+"""
+Streamlit entrypoint for Streamlit Community Cloud.
+
+This module imports and runs the PhenoQC GUI without spawning a subprocess.
+It adjusts sys.path so that `src/` is importable when deployed.
+"""
+
+import os
+import sys
+
+
+def main() -> None:
+    # Ensure `src/` is importable when running on Streamlit Cloud
+    project_root = os.path.dirname(os.path.abspath(__file__))
+    src_path = os.path.join(project_root, "src")
+    if src_path not in sys.path:
+        sys.path.insert(0, src_path)
+
+    # Import and run the GUI main
+    from phenoqc.gui import main as gui_main
+
+    gui_main()
+
+
+if __name__ == "__main__":
+    main()
+
+