Dataset / Data Pipeline · Jupyter Notebook

SkinLeisonML

Daffa@DaBabyOx · Atlas 63.4 · #14= builder

What it is

The repository prepares skin lesion datasets (clinical and ISIC 2019) for cross-domain classification through data discovery, validation, label harmonization, duplicate detection, and leakage-aware splitting. It then trains a model on clinical data and evaluates it on clinical and ISIC data to study domain shift.

Scored atc37fd488 Nov 2026Changes since

Merit describes the code at this commit. Later pushes count once the owner rescans. How merit is scored

Where it counts

Data Science50%
Machine Learning40%
Computer Vision40%

How much of the project is about each field, as scoring counts it. It ranks in the field it is most about.

Around it on the Data Science board

Whole board

RankProjectBuilderFieldMerit

04, shared rankc3pa-sentence-label-parserDataset / Data Pipeline · PythonThis repository provides a Python pipeline for processing the C3PA dataset's HTML privacy policies and CSV annotations into sentence-level candidates, extracting readable text, segmenting sentences, and aligning annotator evidence via a three-tier algorithm.58.4/100AdvancedJarad PeckenpaughData Science
04, shared rankhindsightAI Developer Tool · PythonHindsight is an AI tool usage analyzer and workflow optimizer that examines shell history and AI tool interactions (such as McFly, Claude Code, and Claude Desktop) to identify patterns and generate actionable recommendations for improving developer productivity, including MCP…58.4/100AdvancedLindsey CatlettData Science
04, shared rankSkinLeisonMLDataset / Data Pipeline · Jupyter Notebook58.4/100AdvancedDaffaData Science
07bellapyLibrary / Framework · Pythonbellapy is a Python library and CLI toolkit designed for data preparation in machine learning workflows. It provides functions for deduplication, cleaning, format conversion, and other common data processing tasks.54.1/100ImplementationRickData Science
08ProductHunt-TopLLM-Picks-for-2026Dataset / Data PipelineThis repository provides a scraped snapshot of Product Hunt's LLMs category, containing 750 LLM products in CSV and NDJSON formats, along with a detailed README describing the schema, usage, and basic statistics.35.6/100ExplorationPop AlexandruData Science

What it is

Where it counts

Around it on the Data Science board

More from Daffa