README.md

tweet-nlp-text-analyser

Description:

PROJECT RESOURCES directory contains data gathered during project AND powerpoint presentation.

MSc Project.

A natural language data pipeline for Twitter data and conducting sentiment analysis.

Top-level Directory:

.
├── project_resources/
|    ├─ presentation
|    ├─ project_data.zip/
|       ├─ raw
|       ├─ final (labelled datasets)
|
├── analyser/
|    ├─analysis/
|    |     ├─ streamreader (Labelled Datasets)
|    |
|    ├─/extraction
|          ├─ streamreader (NLP preprocessing and Sentiment Analysis)
|
├── api/
|    ├─store/
|       ├─analytical options
|       ├─database configuration
|       ├─data loading
|       ├─processing options
|
├── scripts/
|    ├─twitter api wrapper
|    ├─raw data formatting
|
├── data/
|    ├─raw/
|    |   ├─completed/ (raw data)
|    |   ├─process/   (temp)
|    |   ├─output/    (store ready)
|    ├─stage/
|    |   ├─analysis/ (Labelled Datasets)
|    ├─resource utilities
|
├── archive.py
├── main.py
├── LICENSE
└── README.md