Mansfield Sulfidity Predictor

C 61 completed
Web App
web_app / python · small
153
Files
30,446
LOC
6
Frameworks
11
Languages

Pipeline State

completed
Run ID
#370329
Phase
done
Progress
1%
Started
Finished
2026-04-13 01:31:02
LLM tokens
0

Pipeline Metadata

Stage
Cataloged
Decision
proceed
Novelty
68.67
Framework unique
Isolation
Last stage change
2026-05-10 03:35:24
Deduplication group #53805
Member of a group with 9 similar repo(s) — canonical #68505 view group →
Top concepts (1)
Web Backend
Powered by Repobility — scan your code at https://repobility.com

AI Prompt

I want to build a web application that predicts the sulfidity of chemical samples. The system should use a trained regression model for prediction and provide interactive result visualization. I'd like to use FastAPI for the backend, and I plan to use React and Next.js for the frontend. Please ensure the project structure supports this, and include styling using Tailwind CSS. I also need to make sure the application is testable, so please incorporate pytest.
python fastapi react next.js sqlalchemy web-app machine-learning prediction tailwind pytest
Generated by gemma4:latest

Catalog Information

A web application that predicts the sulfidity of chemical samples using a trained regression model and visualizes the results interactively.

Description

The application loads a curated dataset of chemical samples, extracts relevant physicochemical features, and trains a regression model to predict sulfidity. It provides an intuitive interface built with Streamlit, allowing users to upload new data or input feature values manually. Interactive visualizations created with Plotly display predicted values, confidence intervals, and feature importance rankings. The tool is designed for researchers and quality‑control professionals who need rapid, data‑driven estimates of sulfur content without laboratory analysis. By combining machine learning with real‑time graphics, it streamlines decision‑making in formulation and compliance workflows.

الوصف

يحمّل التطبيق مجموعة بيانات مختارة من العينات الكيميائية، ويستخرج الخصائص الفيزيائية والكيميائية ذات الصلة، ثم يدرب نموذج انحدار لتوقع مستوى الكبريت. يقدّم واجهة سهلة الاستخدام مبنية على Streamlit، تسمح للمستخدمين بتحميل بيانات جديدة أو إدخال قيم الخصائص يدويًا. تُعرض النتائج بشكل تفاعلي باستخدام Plotly، مع عرض القيم المتوقعة، وفواصل الثقة، وترتيب أهمية الخصائص. يهدف هذا الأداة إلى الباحثين ومهندسي مراقبة الجودة الذين يحتاجون إلى تقديرات سريعة وموثوقة لمحتوى الكبريت دون الحاجة إلى تحاليل مختبرية. بدمج التعلم الآلي مع الرسوم البيانية اللحظية، يُسهل التطبيق اتخاذ القرارات في عمليات الصياغة والامتثال. يتيح للمستخدمين استكشاف تأثير كل متغير على التنبؤ، مما يعزز الفهم العميق للبيانات. كما يدعم التطبيق عمليات التحقق من الجودة في خطوط الإنتاج الكيميائية، ويقلل من الوقت والموارد المطلوبة للتجارب المختبرية.

Novelty

6/10

Tags

predictive-modeling chemical-analysis sulfur-content-prediction interactive-visualization regression machine-learning data-science quality-control

Technologies

numpy pandas plotly scipy streamlit

Claude Models

claude-opus-4.6

Quality Score

C
61.2/100
Structure
48
Code Quality
85
Documentation
17
Testing
50
Practices
68
Security
100
Dependencies
60

Strengths

  • Code linting configured (ruff (possible))
  • Good security practices \u2014 no major issues detected
  • Containerized deployment (Docker)

Weaknesses

  • Missing README file \u2014 critical for project understanding
  • No LICENSE file \u2014 legal ambiguity for contributors
  • No CI/CD configuration \u2014 manual testing and deployment
  • 3 files with critical complexity need refactoring
  • 1 bare except/catch blocks swallowing errors
  • 1127 duplicate lines detected \u2014 consider DRY refactoring
  • 2 'god files' with >500 LOC need decomposition

Recommendations

  • Add a comprehensive README.md explaining purpose, setup, usage, and architecture
  • Set up CI/CD (GitHub Actions recommended) to automate testing and deployment
  • Add a LICENSE file (MIT recommended for open source)
  • Replace bare except/catch blocks with specific exception types

Security & Health

17.1h
Tech Debt (B)
A
OWASP (100%)
PASS
Quality Gate
A
Risk (1)
Repobility · severity-and-effort ranking · https://repobility.com
Unknown
License
5.1%
Duplication
Full Security Report AI Fix Prompts SARIF SBOM

Languages

python
30.0%
json
28.7%
typescript
20.2%
text
18.3%
markdown
1.2%
html
1.1%
css
0.2%
yaml
0.2%
shell
0.1%
toml
0.1%
javascript
0.1%

Frameworks

FastAPI React Next.js pytest Tailwind CSS SQLAlchemy

Concepts (1)

Analysis by Repobility (https://repobility.com) · MCP-ready
CategoryNameDescriptionConfidence
Want this analysis on your repo? https://repobility.com/scan/
auto_categoryWeb Backendweb-backend70%

Quality Timeline

1 quality score recorded.

View File Metrics

Embed Badge

Add to your README:

![Quality](https://repos.aljefra.com/badge/94534.svg)
Quality BadgeSecurity Badge
Export Quality CSVDownload SBOMExport Findings CSV