This project investigates the use of Support Vector Machines (SVM) for predicting homeownership based on demographic and economic data. It explores SVM’s mathematical formulations, kernel functions, and tuning parameters, demonstrating its potential in predicting homeownership.
This project explores the application of neural networks in classifying bird species based on their sounds. Utilizing a dataset from Xeno-Canto with 10 audio clips for each of the 12 selected bird species, the study focuses on binary classification (amecro vs. norfli) and multi-class classification for all 12 species. Various neural network architectures, including convolutional neural networks (CNNs) and transfer learning with VGG16, are employed and evaluated. The report discusses encountered limitations, compares model performances, and emphasizes the potential of neural networks for bird species identification.
This project applies various supervised and unsupervised machine learning algorithms to analyze legal game positions in Connect-4. It explores the efficacy of different techniques such as Logistic Regression, Decision Trees, SVMs, Neural Networks, and K-means clustering, aiming to predict outcomes and provide insights into the Connect-4 dataset.
This project analyzes Healthy Life Expectancy across continents using the World Happiness Report datasets from 2015 to 2019. Through sophisticated data visualizations, it reveals trends and disparities in global well-being, focusing on the impact of factors like GDP, social support, and freedom on health outcomes. This comprehensive analysis provides valuable insights into the varying conditions of happiness and health around the world.
The project involves an analysis of the ‘Global YouTube Statistics 2023’ dataset, where I conducted comprehensive data visualizations to explore trends in YouTube channel growth, content genres, geographic distribution, and monetization aspects. The visualizations aid in understanding subscriber dynamics, viewer engagement, and the platform’s cultural influence.
The goal of this study is to investigate several aspects of youth drug use using data collected by the National Survey on Drug Use and Health.This project employs decision-tree-based analysis to explore factors related to youth drug usage, utilizing machine learning techniques. Three problem types are addressed: binary classification (whether a respondent has ever used alcohol), multi-class classification (predicting the number of days of alcohol use in the past year), and regression (predicting the age of first alcohol use). It identifies key factors that predict drug use in young people and makes suggestions about how to potentially improve preventive strategies.
This project focuses on analyzing departure delays specifically for United Airlines (carrier code UA) using data from the nycflights13 package. The objective is to understand the relationship between departure delays and various factors, including time of day, time of year, temperature, wind speed, precipitation, and visibility, specifically for UA flights.
The primary objective is to explore the relationship between the magnitude of disasters and the prevalence of food insecurity, as defined by the Food and Agriculture Organization (FAO). The research utilizes datasets from the EM-DAT Centre for Research on Epidemiology of Disasters and FAO’s FAOSTAT. This repository contains the code and data for a research project investigating the impacts of natural disasters on food security.
This project utilizes various Python libraries, including Pandas, Altair, Geopandas, OSMnx, Folium, and others, to visualize and explore tourist attractions in New York City. The map includes markers for different types of attractions, public transport locations, and hotels.
This project delves into the analysis of flight gains for United Airlines (UA) using data from the nycflights13 package. The primary focus is on understanding how much quicker flights conclude compared to their planned schedules, measured by the net gain – the difference between departure delay and arrival delay.
The goal of this study is to provide a simple and affordable gui application for boutique gym and health club startups.
This Python program demonstrates the principles of Object-Oriented Programming (OOP) by implementing classes for Human, Hiker, Scientist, Swimmer, and ScientificSwimmer. The classes showcase the concepts of inheritance, encapsulation, and polymorphism.
This Python program is designed to play the classic game of Rock, Paper, Scissors with the user. The game allows the user to specify the number of rounds to be played, and in each round, the player and the computer make their selections. The winner of each round is determined based on the traditional rules: Rock smashes scissors, Paper covers rock, and Scissors cut paper.