- Since I started using it back in 2013, Python has become an
essential part of my technology stack and my go-to language. ❤️
- I use Django and Flask for web development.
- I use NumPy, Pandas and Matplotlib
extensively for my data science and visualization tasks.
- And lastly, Scikit-learn and TensorFlow for my machine learning and deep learning projects.
- I also used PHP, Java, C++ and C# in the past. And I am glad they are in the past... (you know I am
talking about you, PHP 🙄 🔗)
- I have occasional experience with with HTML, CSS, JavaScript, DOM and jQuery.
- I use R when I have to, which doesn't happen often, hence
my knowledge is rather limited.
- Regarding databases, I only used MySQL and SQLite so far.
- I have some knowledge on Docker from projects that
required containerization but I am nowhere near familiar with it. (#humbleguy)
Currently learning: MongoDB, PostgreSQL, Amazon RDS, Apache
Kafka and Apache Cassandra
- Flower Image Classifier - A Deep Learning Project:
Testing out several pre-trained deep learning models for image classification from PyTorch such as
AlexNet, VGG-19, ResNet-18 and Densenet-121
to create a flower species classifier using the 102 Category Flower Dataset from the Visual Geometry
Group of the
University of Oxford. Then, creating a command line application that can be used to classify any flower
images with more than 91% accuracy.
Skills: Python, PyTorch, Image Classification, GPU Programming, NumPy, Matplotlib
Links: GitHub Repo, Jupyter Notebook
- Identifying Customer Segments - An Unsupervised Learning
Project:
Applying several unsupervised learning techniques and algorithms to identify segments of the population
that form the core customer base for
a mail-order sales company in Germany. These segments can then be used to direct marketing campaigns
towards audiences that will have the
highest expected rate of returns. The dataset for this project has been provided by Bertelsmann Arvato
Analytics, and represents a real-life data
science task.
Skills: Python, Scikit-learn, Principal Component Analysis, K-Means Clustering, NumPy
Links: GitHub Repo, Jupyter Notebook
- Finding Donors for CharityML - A Supervised Learning Project:
Testing out and training several supervised learning algorithms such as decision trees, support vector
machines (SVMs) and AdaBoost to build a
model that accurately predicts whether an individual makes more than $50,000 a year, and to identify
likely donors for a non-profit organization.
Skills: Python, Scikit-learn, Decision Trees, AdaBoost, SVMs, NumPy, Pandas, Matplotlib
Links: GitHub Repo, Jupyter
Notebook
- 🏢 Started working as a software developer at Okulistik in September
2019.
- 👔 Did an internship at Teknolist A.Ş. in Istanbul, Turkey in the summer of 2019.
- 🧮 Started studying mathematics at Bilkent University in 2014.
- 💻 Entered the world of programming in 2013.
- 🐣 Born in August 1995.