JacobJ215

BERT-QUESTION-ANSWERING-APP

This project demonstrates a user-friendly web application that uses a pre-trained BERT-based model to answer questions based on a given passage. The app is built using Python, the transformers library for BERT, Flask for the web framework, and HTML/CSS for the interactive user interface.

Churn-Analysis-and-Prediction

Telecom Churn Analysis: Predicting customer churn using ML. Best model was XGBoost with 81.92% accuracy. SHAP analysis revealed top features. Results and insights visualized in Tableau

Credit-Card-Default

This project was created to predict credit card defaults based on customer profiles, achieving a high ROC AUC score of 0.7882 The model analyzes borrower information, such as age, income, and financial indicators, to identify customers at risk of defaulting. The model was deployed to streamlit as a web app.

LLM-QnA-CHAT-BOT

This is a Generative AI powered Question and Answering app that responds to questions about your uploaded file. Here we utilize HuggingFaceEmbeddings and OpenAI gpt-3.5-turbo

Optical-Character-Recognition-WebApp

This project is a web application that uses YOLOv5 and InceptionResNetV2 models for license plate detection and Optical Character Recognition (OCR) text extraction. The web applications were built using streamlit and flask

Pneumonia-Classification

Developed and evaluated two models, to detect pneumonia cases from medical images. Our custom resnet18 was evaluated at an 81% accuracy, 66% precision, and 78% recall. Valuable for timely detection of pneumonia patients, improving outcomes, and reducing mortality. CAM visualizations provide provide insights into model decision-making

Real-Time-Image-Classification

Created a small CNN model capable of classifying images

Sentiment-Analysis-with-DistilBERT

Here we leverage a subset of the amazon_polarity dataset to train two machine learning models: an LSTM model with GloVe embeddings and a fine-tuned DistilBERT model. The LSTM model achieved an accuracy of 80.40%, while the DistilBERT model outperformed with an impressive 90.75% accuracy. Predictions can made in real time via our streamlit app

Vehicle-Detection-Tracking-App

This repository contains a Streamlit web application for vehicle tracking using different SOTA object detection models. The app offers two options: YOLO-NAS with SORT tracking and YOLOv8 with ByteTrack and Supervision tracking. It enables users to upload a video file, set confidence levels, and visualize the tracking results in real-time.

YOLO-NAS-OCR-WebApp

This project uses YOLO-NAS and EasyOCR to detect license plates and perform Optical Character Recognition on them. The project includes both image and video processing capabilities, and has been deployed as a Streamlit web application. This is an update to Optical-Character-Recognition-WebApp project. Here we achieved a mAP@0.50': 0.962

JacobJ215/Vehicle-Detection-Tracking-App

This repository contains a Streamlit web application for vehicle tracking using different SOTA object detection models. The app offers two options: YOLO-NAS with SORT tracking and YOLOv8 with ByteTrack and Supervision tracking. It enables users to upload a video file, set confidence levels, and visualize the tracking results in real-time.

JacobJ215/BERT-QUESTION-ANSWERING-APP

This project demonstrates a user-friendly web application that uses a pre-trained BERT-based model to answer questions based on a given passage. The app is built using Python, the transformers library for BERT, Flask for the web framework, and HTML/CSS for the interactive user interface.

JacobJ215/Credit-Card-Default

This project was created to predict credit card defaults based on customer profiles, achieving a high ROC AUC score of 0.7882 The model analyzes borrower information, such as age, income, and financial indicators, to identify customers at risk of defaulting. The model was deployed to streamlit as a web app.

JacobJ215/LLM-QnA-CHAT-BOT

This is a Generative AI powered Question and Answering app that responds to questions about your uploaded file. Here we utilize HuggingFaceEmbeddings and OpenAI gpt-3.5-turbo

JacobJ215/Optical-Character-Recognition-WebApp

This project is a web application that uses YOLOv5 and InceptionResNetV2 models for license plate detection and Optical Character Recognition (OCR) text extraction. The web applications were built using streamlit and flask

JacobJ215/Real-Time-Image-Classification

Created a small CNN model capable of classifying images

JacobJ215/YOLO-NAS-OCR-WebApp

This project uses YOLO-NAS and EasyOCR to detect license plates and perform Optical Character Recognition on them. The project includes both image and video processing capabilities, and has been deployed as a Streamlit web application. This is an update to Optical-Character-Recognition-WebApp project. Here we achieved a mAP@0.50': 0.962

JacobJ215/YOLO-NAS-SAM

This project demonstrates how to perform object detection and image segmentation using YOLO-NAS for object detection and SAM for image segmentation.

JacobJ215/YOLOv7_Face_Mask_Detection

Object Detection project created to detect face mask using YOLOv7 trained on a custom dataset

JacobJ215/Churn-Analysis-and-Prediction

Telecom Churn Analysis: Predicting customer churn using ML. Best model was XGBoost with 81.92% accuracy. SHAP analysis revealed top features. Results and insights visualized in Tableau

JacobJ215/Pneumonia-Classification

Developed and evaluated two models, to detect pneumonia cases from medical images. Our custom resnet18 was evaluated at an 81% accuracy, 66% precision, and 78% recall. Valuable for timely detection of pneumonia patients, improving outcomes, and reducing mortality. CAM visualizations provide provide insights into model decision-making

JacobJ215/Sentiment-Analysis-with-DistilBERT

Here we leverage a subset of the amazon_polarity dataset to train two machine learning models: an LSTM model with GloVe embeddings and a fine-tuned DistilBERT model. The LSTM model achieved an accuracy of 80.40%, while the DistilBERT model outperformed with an impressive 90.75% accuracy. Predictions can made in real time via our streamlit app

JacobJ215/Airline-Sentiment-Analysis

This sentiment analysis project aims to classify US airline tweets as positive or negative. It explores both classical ML and deep learning approaches. The LSTM outperforms XGBoost with an AUC score of 0.9462, despite a slightly lower accuracy. The AUC metric highlights LSTM's efficacy in handling imbalanced datasets.

JacobJ215/Allstate-Claims-Severity

This repository features code for the Allstate Claims Severity Kaggle competition, utilizing Python, primarily XGBoost, and LightGBM for predicting insurance claim losses. Through preprocessing and hyperparameter tuning, LightGBM attains the best validation MAE of 0.4157, selected for test dataset predictions and competition submission.

JacobJ215/Anomaly-Detection-Using-Autoencoders

Autoencoder Neural Network is trained on credit card transaction data to detect anomalous transactions in near real time using flask api

JacobJ215/CV_Mobile_App

JacobJ215/deploying-machine-learning-models

Code for the online course "Deployment of Machine Learning Models"

JacobJ215/JacobJ215

Config files for my GitHub profile.

JacobJ215/JacobJ215Old.github.io

JacobJ215/learnopencv

Learn OpenCV : C++ and Python Examples

JacobJ215/License-Renewal-Status-Using-Neural-Networks

The objective of this project is to assess given various features whether a customer's business license should be issued, renewed or cancelled

JacobJ215/Lung-Cancer-Segmentation

Developed a Lung Cancer Segmentation model using the U-Net architecture and PyTorch Lightning framework. Achieved an unimpressive dice loss of 0.0247 more work is required.

JacobJ215/Machine-Learning-Guide

The idea behind this Intro to Machine Learning Guide was to initially create a list of resources to provide to my students. This eventually morphed into a comprehensive guide that will eventually cover everything from Linear Regression to Neural Networks

JacobJ215/Melbourne-Housing-Price-Prediction

The purpose of this notebook is to display some of the most common, practical and powerful machine leaning techniques and applications used to solve simple data science problems. Here we are using the Melbourne housing clearance data from Kaggle to predict housing prices.

JacobJ215/opencv

Open Source Computer Vision Library

JacobJ215/password-generator

This a password generator created using the django framework

JacobJ215/Pokemon-Stats-Analysis

This is a data analysis and machine learning project that focuses on analyzing the stats of Pokemon from the popular Pokemon game series. The project utilizes Python and various data analysis libraries to explore and visualize the data, as well as perform statistical analysis on the Pokemon stats.

JacobJ215/Portfolio

This repository contains the source code for my Data Scientist Portfolio website. This website showcases a collection of projects and skills in the field of Data Science, with a focus on Machine Learning, Computer Vision, Natural Language Processing (NLP), and more.

JacobJ215/Premier-League-Regression-Analysis

Basic Regression Analysis

JacobJ215/to-do-list

First ReactJS project - Basic To-Do-List