concept_miner_elastic
An Elastic-backed wrapper around Prodigy, Kibana and spaCy. Designed to allow a small group to quickly annotate data and iterate on a text classification machine learning model.
Science Score: 44.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
✓CITATION.cff file
Found CITATION.cff file -
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
○DOI references
-
○Academic publication links
-
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (8.1%) to scientific vocabulary
Repository
An Elastic-backed wrapper around Prodigy, Kibana and spaCy. Designed to allow a small group to quickly annotate data and iterate on a text classification machine learning model.
Basic Info
Statistics
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 2
- Releases: 1
Metadata Files
README.md
Concept Miner Elastic
A framework around prodigy to let end users start and stop the interface, trigger training, etc. - for small group collab.
Installation
- Make sure you have an active prodigy license
Create a .env file in the build directory (or edit docker-compose.yml in that location), containing:
shell COMPOSE_PROJECT_NAME=concept_miner_elastic KIBANA_SERVER_PUBLICBASEURL=https://<your_base_url>/kibana TZ=<your_timezone> DEBUG=false PRODIGY_KEY=<your_prodigy_key>Run
docker compose upThe server should now be running on http://127.0.0.1:8000/ (you can change this port in ./conf/nginx.conf)
Usage
- Visit http://
:8000/ - From the Home tab, upload your PDF or TXT documents for training
- Navigate to the Annotating tab, and perform your prodigy annotations
- Once you have completed a number of annotations, return to 'Home' and click 'Go' next to 'Stop annotating (Start training)'
- Results will be on the 'Training Log' tab, and your model and annotations will be in the ./output folder (or as configured in app.conf)
Owner
- Login: BobWatson
- Kind: user
- Location: Canberra, Aus
- Repositories: 7
- Profile: https://github.com/BobWatson
Citation (CITATION.cff)
# YAML 1.2
---
abstract: "An Elastic-backed wrapper around Prodigy, Kibana and spaCy. Designed to allow a small group to quickly annotate data and iterate on a text classification machine learning model."
authors:
-
family-names: Watson
given-names: "Robert John"
cff-version: "1.1.0"
date-released: 2021-09-07
license: MIT
message: "If you use this software, please cite it using these metadata."
repository-code: "https://github.com/BobWatson/concept_miner_elastic"
title: "Concept Miner"
...
GitHub Events
Total
Last Year
Dependencies
- black * development
- pre-commit * development
- Flask ==2.0.1
- Flask-RESTful ==0.3.9
- Jinja2 ==3.0.1
- MarkupSafe ==2.0.1
- PyYAML ==5.4.1
- ansi2html ==1.6.0
- blis ==0.7.4
- catalogue ==2.0.6
- certifi ==2021.5.30
- chardet ==4.0.0
- charset-normalizer ==2.0.4
- click ==7.1.2
- cymem ==2.0.5
- elasticsearch ==7.14.1
- idna ==3.2
- murmurhash ==1.0.5
- numpy ==1.21.2
- packaging ==21.0
- pathy ==0.6.0
- pdftotext ==2.2.0
- preshed ==3.0.5
- prodigy >=1.11.0,<2.0.0
- psutil ==5.8.0
- psycopg2 ==2.9.1
- pydantic ==1.8.2
- pymitter ==0.3.1
- pyparsing ==2.4.7
- requests ==2.26.0
- smart-open ==5.2.1
- spacy ==3.1.2
- spacy-legacy ==3.0.8
- srsly ==2.4.1
- thinc ==8.0.9
- tqdm ==4.62.2
- typer ==0.3.2
- typing-extensions ==3.10.0.2
- urllib3 ==1.26.6
- wasabi ==0.8.2
- actions/checkout v2 composite
- github/codeql-action/analyze v1 composite
- github/codeql-action/autobuild v1 composite
- github/codeql-action/init v1 composite
- mcr.microsoft.com/vscode/devcontainers/python 0-${VARIANT} build
- docker.elastic.co/elasticsearch/elasticsearch 7.14.1
- docker.elastic.co/kibana/kibana 7.14.1
- nginx 1.21
- postgres 13