Notebooks

Sentiment Analysis in Python

This project aims to perform sentiment analysis on textual data using Python, leveraging the VADER Sentiment Scoring method, the RoBERTa pre-trained model, and the Transformers pipeline. Sentiment analysis is the process of determining the emotional tone behind a series of words, which can be particularly useful for understanding the sentiment in social media posts, customer reviews, and other text data.

Objectives

1. Implement VADER Sentiment Scoring: Use VADER (Valence Aware Dictionary for Sentiment Reasoning) to perform sentiment analysis on text data. VADER is designed for social media texts and provides a simple yet effective method for obtaining sentiment scores.
2. Utilize RoBERTa Pre-trained Model: Implement sentiment analysis using the RoBERTa (Robustly optimized BERT approach) pre-trained model, which is known for its high performance in NLP tasks.
3. Apply the Transformers Pipeline: Use the Transformers pipeline from Hugging Face to streamline the process of loading pre-trained models and performing sentiment analysis.

Web Apps

401K Contribution Calculator

This project involves developing a 401(k) contribution calculator web application using Python and Streamlit. The app will leverage numpy_financial for financial calculations and matplotlib for generating visual graphs based on user input. The primary goal is to help users project their 401(k) savings over time based on their contributions, employer match, expected rate of return, and other factors.

Objectives

1. User-Friendly Interface: Create an intuitive and interactive web application using Streamlit that allows users to input their 401(k) contribution details.
2. Financial Calculations: Utilize numpy_financial to perform complex financial calculations, including future value projections of 401(k) contributions.
3. Data Visualization: Implement matplotlib to generate graphs that visualize the growth of 401(k) savings over time.
4. Projection Analysis: Provide users with detailed projections and insights based on their inputs.

LLM Papers WebApp

The LLM Papers WebApp is a simple, yet powerful, tool developed using Python and Streamlit. It allows users to explore, search, and filter foundational papers in the field of Large Language Models (LLMs). The app provides an intuitive interface for users to find relevant papers by title, author, summary, and publication year.

Objectives

1. Easy Access to Foundational Papers: Provide a centralized platform for accessing key research papers in the field of LLM.
2. User-Friendly Interface: Create an intuitive and responsive web app using Streamlit to enhance user experience.
3. Customizability: Allow users to update the underlying data (CSV file) to customize the app for their own domain-specific papers.
4. Comprehensive Search and Filter: Enable efficient search and filtering capabilities to help users quickly find papers based on multiple criteria.

Arbitrage Betting Calculator

A Streamlit app to calculate potential profits and losses from arbitrage betting. Input American odds and wagers for two teams. The app computes potential profits, bookmaker margins, and checks for arbitrage opportunities. Ideal for optimizing sports betting strategies. Easy-to-use interface.

Features

1. Input American odds and wager amounts for two teams
2. Calculate potential profit/loss for each outcome
3. Determine bookmaker's profit margin
4. Identify arbitrage opportunities
5. User-friendly interface with streamlined input and output sections