Machine Learning Repository

Interact with this project here:

This repo serves as a playground for all my experimentation with different techniques used in ML. Since I'm quite new to Data Science and have recently gotten work experience with Analytics and the basics of ML, I want to explore the field further.

Structure

1. Knowledge

• NLP - contains all notebooks & datasets related to Natural Language Processing
  • Datasets
  • Notebooks
    • nlp_tfidf_lda.ipynb
    • Paraphrase Classifier - a simple investigation on creating a paraphrase classifier
• AI - contains all content related to Artificial Intelligence
  • Notes can be viewed at Hrithik's Notes

2. Kaggle - contains everything used for Kaggle Competitions

• Titanic - competition to classify whether a passenger would survive the disaster. Overall accuracy of 75%.
  • Titanic-EDA.ipynb

3. Projects - contains all Data Science Projects

• COVID-19 Dashboard - a dashboard created to monitor the Coronavirus Pandemic. Created using Plotly, Dash, and Heroku. View the dashboard at covid19-report.herokuapp.com

  • covid-app

• Spotify Speech - A speech recognizer for Spotify commands source code