Around_the_world_in_80_days

NLP project to plot Fogg's journey in the book 'Around the world in 80 days'

Implementation

This project reads the book 'Around the world in 80 days' and performs the following NLP operations to identify the locations Fogg travelled in his journey.

• Spacy model to perform Named Entity Recognition https://huggingface.co/spacy/en_core_web_sm
• NLTK library is used for processing the location text by perfoming
  • Tokenization
  • Stop words removal
  • Special characters removal using regex

The location data is used to get the latitude and longitude by using the geopy pip package.

Pandas is used to create a CSV file with columns - location, latitude and longitude. This CSV file acts as the source of visualization in tableau public.

Streamlit application

We have a streamlit version of this here. Please follow the Installation guide mentioned in the streamlit_app sub folder to set up streamlit application locally.

Visualization

Tableau Dashboard : https://public.tableau.com/app/profile/antony.prince.j/viz/Around_the_world_in_80_days/Dashboard?publish=yes

Streamlit Application

Steps to run

1. Install the required packages pip3 install -r requirements.txt

2. Run the python script python3 app.py

---

Developed By

Antony Prince J and Hemanth Kumar