NLP-DATAU

NLP Data Utilities for processing NLP-data and analyzing results.

Notebooks

Pre-processing

ElasticSearch

• XML documents to ElasticSearch link
• ElasticSearch documents to Excel link
• Prepare a dataset for doccano annotation using ElasticSearch link
• Template parsing link

Processing

• Context Extraction using spaCy & pyContextNLP link

Post-processing

Stats

• Calculate NLP statistics over classification results in excel format link

Dependencies

REQUIRED:

• docker https://hub.docker.com/

RECOMMENDED:

• git https://git-scm.com/downloads

Install

1. Clone or download (button) this repository

   git clone https://github.com/putssander/nlp-datau.git

Run

1. Navigate to the cloned or downloaded project using the terminal or cmd

2. Create network (if it does not exists)

    docker network create nlp-datau-network    
   

3. Start docker-compose

    docker-compose up
   

4. Find the Jupyter link in the log file and copy the link in the browser.

    jupyter-nlp-datau             | [I 12:06:45.669 NotebookApp]  or http://127.0.0.1:8888/?token=0c01e853a34a4bb0db3a542ca15c3af036cab7a11fd64bb2
   

5. Navigate to the desired notebook in the browser (directory notebooks)

6. Data can be copied to the resources/data folder (needs to be created)