MeteSertkan/ranger
Ranger helps you see the forest among the trees - Ranger is an effect-size meta analysis library creating beautiful forest plots!
When evaluating machine learning models for tasks in fields like Natural Language Processing (NLP) or Information Retrieval (IR), it can be hard to compare results across different metrics or scenarios. This tool helps you combine these varied evaluation outcomes into a single, comprehensive statistical view. You input the performance metrics from your different model evaluations, and it generates a "forest plot" — a visual summary that shows the overall effectiveness and reliability of your model across all tasks. Data scientists, researchers, and machine learning engineers who need to robustly assess and present their model's performance on multiple tasks would use this.
No commits in the last 6 months.
Use this if you need to aggregate and visually represent the impact of a model or 'treatment' across multiple, potentially incomparable, evaluation tasks in NLP, IR, or similar fields.
Not ideal if you are looking for a tool to train models, perform single-task evaluations, or visualize basic statistical distributions outside of meta-analysis.
Stars
11
Forks
1
Language
Python
License
Apache-2.0
Category
Last pushed
Jun 12, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/MeteSertkan/ranger"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
ryanjgallagher/shifterator
Interpretable data visualizations for understanding how texts differ at the word level
HLasse/TextDescriptives
A Python library for calculating a large variety of metrics from text
jboynyc/textnets
Text analysis with networks.
DemetersSon83/Quantitative-Discursive-Analysis
A tool for quantitatively measuring discursive similarity between bodies of text.
sciknoworg/tib-sid
TIB-SID: A bilingual (English/German) dataset of library catalog records with GND subject...