john-thuo1's repositories
popular_movies_etl
Airflow ETL with AWS, Docker and Postgres consuming TMDb API
john-thuo1
Config files for my GitHub profile.
sentiment
The Opinion Mining Tool is designed to help Small and Medium Enterprises(S.M.Es) gain valuable insights from their Product Customer Reviews. By analyzing review scores and providing actionable recommendations using OpenAI GPT model & BERT, this tool empowers S.M.Es to make data-driven decisions.
ml_ops-Assignment2
Mlops Assignment 2 Github link
chatWithPDF
This project allows you to upload a PDF document and ask questions about its content. It uses langchain, openai api model and Facebook Ai Similarity Search(FAISS) library to process the text in the PDF and provide answers to questions pertaining the document.
Clustering_DataMining
Clustering via KMeans for Text & Image Data
airflow-v
Begineer Apache-Airflow DAGS implemented to explore Apache-Airflow Operators.
hospitalappointmentmanagementsystem
The repository contains code for a hospital appointment management system that interacts with Africa's Talking API to allow for seamless booking of Doctor-Patient Appointments with a given Hospital. The project utilizes Django framework for both front(Uses html templates, Bootstrap and CSS) and Back-end
seamless_communication
Foundational Models for State-of-the-Art Speech and Text Translation
capitalhack_movierecommendation
Repository contains code for implementation of a simple collaborative filtering(u2u) movie recommendation algorithm.
deep_learning_diagnostic_tool
The repo contains an implementation of a diagnostic tool used to classify chest related x -ray images of diseases such as Tuberculosis and Pneumonia. To develop the tool, VGG-19 pretrained model from imagenet was used.
RecordLinkage
Brief Overview of record linkage implementation
exam-schedular-system
The repository contains code for an Exam Scheduling Application that interacts with Africa's Talking USSD & SMS APIs to allow for seamless Exam Registration For College Students. The project utilizes Django framework for both front(Uses html templates, Bootstrap and CSS) and Back-end.
skills-connect-the-dots
My clone repository
skills-release-based-workflow
My clone repository
skills-resolve-merge-conflicts
My clone repository
skills-review-pull-requests
My clone repository
belebele
Repo for the Belebele dataset, a massively multilingual reading comprehension dataset.
stopes
A library for preparing data for machine translation research (monolingual preprocessing, bitext mining, etc.) built by the FAIR NLLB team.
fairseq
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
orientation-project-python-23.SUM.B
Orientation Project (Python) for 23.SUM.B
first-contributions
🚀✨ Help beginners to contribute to open source projects
breastCancerDiagnosticTool_G1
The repository contains code implementation of a Breast Cancer Diagnostic Tool that determines whether a given Patient's Mammogram Image is Benign or Malignant. VGG16 model, which is 16 layers deep was used.