Visualising NLP pipelines with Pynorama
summary
A Python visualization system called Pynorama (Panorama) visualizes whole NLP corpora, metadata and model pipelines, not just one chart. It ships as a Flask backend and React/Redux frontend, supports a pandas data-frame backend or a MongoDB backend for scale, and uses lazy node evaluation with optional Spark runs. Demo shows ~10,000 Reuters articles, a confusion-matrix workflow, and an intern-built open-source repo created over a summer.
AI-written summary · about
chapters (10)
- 0:00Introduction
- 1:12What we aim to achieve with Pynorama
- 3:03NLP pipeline challenges
- 8:16Pynorama features
- 11:08Live demo
- 16:58Integrating Pynorama
- 17:19Pynorama API
- 28:22Pynorama open source
- 29:23Contributing to Pynorama
- 31:30Q&A
related talks
35mUsing Scattertext and the Python NLP Ecosystem for Text Visualization
35mUnderstanding the News around the World with Web Scraping and NLP at Scale
28mAdvanced Graph Visualizations in Jupyter Notebooks
15mVisualizing Data Analysis Pipelines with Pandas Tutor and Tidy Data Tutor
35mUntitled12.ipynb
53mApache Deep Learning 302
45mArchitecture of an NLP Deployment
21mFrom 0 to a crowd sourced neural network in a jiffy
