COVID-19 Statistics

----------------------------------------

An Analytical and Interactive Approach
View Demo · Report Bug · Request Feature

About The Project

The recent surge in cases of covid-19 due to the second wave of the pandemic has created a crisis within the country. This calls for an analysis of how we've been handling the initial wave, how we are doing currently and what we can potentially do in the future. It is also important to make this information accessible to the people and that is what we aim to achieve with this project.

Note :

The frontend has been recently refactored to ReactJS. We are having difficulty deploying the Rasa Chatbot to servers. We have also exhausted the trial period of Elastic services. We apologise for the same and are working on resolving it as soon as possible

Tech Stack

• ReactJS
• Elasticsearch and Kibana
• Flask
• RASA-NLU Chatbot
• Firebase Hosting

Project Design :

Getting Started

To get a local copy up and running follow these simple steps.

Installation

• Setting up the RASA chatbot server:

  1. cd to the RASA folder

     cd
     cd ChatBotRasa EW

  2. Install prerequisite packages

     pip install rasa-x -i https://pypi.rasa.com/simple

  3. Run RASA server at a deployable localhost endpoint

     rasa run -m models --enable-api --cors “*” --debug

• Setting up the web application :

  1. Clone the repo

     git clone https://github.com/rwishavg/COVID-19-and-India.git

  2. cd to the Flask folder

     cd backend

  3. Create a virtual environment and activate it

       conda create -n venv python=3.6
       activate venv

  4. Install prerequisite packages

     pip install flask

Application in Use

Salient Features

1. Implementing the Elastic stack in particular Elasticsearch and Kibana in order to perform data analysis and present impactful visualizations through the Kibana dashboard.
2. Displaying Covid statistics that update in real time by reading from API's.
3. Building a RASA chatbot by training it on custom interaction and also enabling it to update the user with location specific pandemic statistics.

What it Looks Like

Screenshot 1

Screenshot 2

Roadmap

1. Data preprocessing and sending the data to Elasticsearch using Bulk API.
2. Analyzing the data using Kibana, and creating a dashboard of visualizations using it.
3. Created an embeddable link of the dashboard.
4. At this time the front-end of the website had been completed.
5. Implemented live data update of COVID19 by writing scripts to read API's generated by scraping the web. Parsed the API into .JSON files and extracted data from them.
6. Built a chatbot using RASA and Python, trained it on custom interaction, to make it handle general conversation. It is a chatbot that provides the user with the up-to-date pandemic stats which is location specific.
7. All of the individual modules were integrated, and deployed to the localhost using Flask.

License

Distributed under the MIT License. See LICENSE for more information.

Contributors

Rwishav Ghosh [Web Development]

Ved Prakash Dubey [Data Science and Machine Learning]

Acknowledgements

• Kaggle
• Elastic