Python Developer | Machine Learning Engineer | Data science Nigeria bootcamp 2021 finalist(top 25%) | Portfolio | LinkedIn | Hugging Face
- Several MOOCs on programming, Machine Learning, Data Science and software engineering.
- Bachelors of Agriculture (Animal Breeding and Genetics), Federal University of Agriculture Abeokuta, 2010-2015
This is a simple CRUD app built with PHP and MySQL. It allows users to login and create, read, update, and delete their profile information, including their position, education, and more.
This is a chatbot application built with Flask, Langchain, and OpenAI's GPT 3.5 turbo(ChatGPT) model. The chatbot can access the internet using DuckDuckGo and Wikipedia APIs, and can also run Python programs using Python REPL.
This is a web application that allows users to ask questions about the content of a PDF file and receive answers. The application is built using the Flask microframework,langchain library was also used to help with processing the PDF file and utilisation of the large language model.
This project is a blog posting webapp where you can log in, write, post and edit your blog posts. I used Django framework for building this webapp, I hosted it on python anywhere.
I created a CRUD website where one can sign in , post a job that will appear on the homepage for everyone to see. For this project I had to use Flask python library, HTML, sqlite, CSS and bootstrap. I also hosted it on a cloud platform.
Photo by Kirill Tonkikh on Unsplash
This project is about hosting a static website. In this project I deployed a static website to AWS by performing the following steps.
- Created a public S3 bucket and uploaded website files to my bucket.
- Next I configured the bucket for website hosting and secured it using IAM policies.
- Then sped up content delivery using content distribution network service (CloudFront)
- Finally accessed my website in a browser.
In this project, I used convolutional neural networks to train a model that can predict if a cassava has a certain disease based on the picture of the cassava plant. I later had to use image augmentation and transfer learning to improve my accuracy.
- Python libraries and Framework used: Docker, Pandas, matplotlib, sklearn, seaborn, Keras, Tensorflow
- Machine learning Algorithms used: Convolutional neural network,
- Input: Photo of the cassava plant
- Output: Disease prediction
Photo by rupixen.com on Unsplash
You get many visitors to your website every day, but you know only a small percentage of them are likely to buy from you, while most will perhaps not even return.Propensity modeling allows you to allocate your resources more wisely, resulting in greater efficiencies, while achieving better results. To give an example, think of this: instead of sending an email advertisement where there’s a 0%-100% chance of a user clicking it, with propensity modeling, you can target users with a 50%+ chance of clicking it. Fewer emails, more conversions! Right now you may be spending money to re-market to everyone, but perhaps we could use machine learning to identify the most valuable prospects. Having this important information can also help the marketing department know the kind of email to sent to a particular visitor.The goal is to build a web service that sends prediction that indicates if a customer has a propensity to buy based on the actions on a website.
- Python libraries and Framework used: Docker, gunicorn, Flask, Pandas, Pipenv, matplotlib, sklearn, seaborn, pickle
- Machine learning Algorithms used: Logistic regression, Decision tree, Random forest, Xgboost
- Input: visitor's action on the website
- Output: Propensity prediction
Created this webapp using streamlit library and I also deployed it in the cloud with the help of streamlit cloud. The web app helps in the visualisation of selected data, you can compare different variables and predict energy consumption using different machine learning models, you can also select predictor variables you want to use.
- Python libraries used: Streamlit, Pandas, sklearn, Numpy, Seaborn, Pillow
Photo by Stephen Phillips - Hostreviews.co.uk on Unsplash
As a Financial institution you want to offer credit card to customers but you need to be sure that high percentage of customers you offer the credit card won't default. This project helps predict customers that have a low chance of defaulting which can help in selecting customers for credit card approval.
- Python libraries used: Numpy, Pandas, matplotlib, sklearn, seaborn
- Input: Customer's information
- Output: suitability for credit card approval
Photo by Jess Bailey on Unsplash
The purpose of Event Recommendation Engine Project, is to predict what events users will be interested in based on events they’ve responded to in the past, user demographic information, and what events they’ve seen and clicked on in an app.
- Python libraries used: os, Pandas, matplotlib, sklearn, seaborn,plotly
- Input: Customer's information
- Output: Whether a customer will be interested in an event or not.
Photo by Andrew Neel on Unsplash
You would find most of my datascience assignments that I have been doing from several online courses.
- Python libraries used: Numpy, Pandas, matplotlib, sklearn, seaborn, keras, Tensorflow, os, Shutil
You can view my LinkedIn profile here, you can also see my medium posts here.