Explore thousands of data science projects and get inspired

Any topic SQL Python R Machine learning Data visualisation

Project photo

Spotify Recommender and Visualizer

By generating global song recommendations towards highlighting global talent and multilingual songs, our project aims to create a more diverse experience to music listeners while also providing a fun user experience by generating live, audio-responsive artistic visuals.

Project photo

Using R Shiny to Inform Community Officials

Using a leaflet interactive map, we created a multilevel, informational dashboard that enables community officials to develop better insights into their population, facilities, and areas in need. This project utilized data from Census reports, facilities information, housing, and abandoned...

Project photo

Goodreads - Web Scraping using Beautiful Soup

A mug of coffee and my favorite novel, an ideal day for me. But deciding which novel to read is a tedious job, I always go for Goodreads for recommendation and reviewing of the novel. Goodreads is one the world’s largest community for reviewing and recommending books. As a voracious reader,...

Project photo

The Effect of Greyscale on Screentime

A high amount of screen time and phone use can have a serious effect on mental health and physical well being. To tackle this issue, our project explores the use of removing colors from mobile phones to reduce overall screen time. This project’s results show that even with a specific treatment...

Project photo

Sartorius Cell Segmentation Competition

In this competition i detected and delineate distinct objects of interest in biological phase contrast microscopy images depicting neuronal cell types commonly used in the study of neurological disorders. At first, i tried with a UNet with transfer learning using the Imagenet weights,then , i...

Alberto Zorzetto

Project photo

Kepler Mission: Celestial Bodies Classification

Classification of the observed objects by Kepler orbital telescope as Exoplanets or not.

Project photo

Domesticated Animal Image Classification with Python

In this use case, my colleagues and I collaborated on creating and optimizing a convolutional neural network in order to identify domesticated animals versus non-domesticated animals to assist in funding suggestions for local animal shelters. Using the CIFAR-10 dataset with over 60,000 images,...

Project photo

Sentiment247

Sentiment247 is an application that detects emotional tone in text data by dictating polarity and determining depression using NLP techniques.

Project photo

US 2020 Elections Analytics

With my team, we used tweets collected with the Twitter API regarding the US elections of 2020. Using the LDA algorithm, we spotted the most talked topics in the months leading up to the election and for a short period after it. We also trained ML models with annotated data for gender...

Angelos Moavinis

Project photo

Formal and informal social networks in learning and education. A case study of experiential learning for social change

Analytically documenting the example of a rapidly growing interdisciplinary knowledge and skills hub, FabLab - Social Fabrics Research Lab at West University of Timisoara, built from the interplay of personal and professional relationships and formal and informal affiliations.

Alexandra Florea

Project photo

Strava Kudos Predictor

Created a tool that predicts kudos, a proxy for user interaction, on Strava activities (RMSE: 9.41) to see if it was random or if different attributes impact kudos in different ways. Attained over 4000 Strava activities using the Strava API and python. Engineered new features using domain...

Project photo

Recipe Recommendation System

Created a tool that recommends recipes based on ingredients inputted to help students eat better food. Scraped over 4000 recipes from All Recipes and Jamie Oliver using python and beautiful soup. Parsed recipe ingredients and created word embeddings using Word2Vec and TF-IDF. Created a recipe...

Project photo

Covid19 Dashboard Netherlands

A Dash Plotly dashboard which visualizes Covid19 data concerning the Netherlands supplied by the RIVM: National Institute for Public Health and the Environment. The data on the dashboard is updated multiple times a day to provide up-to-date visualizations. The web application is hosted in a...

Project photo

Dutch Text Simplification with MUSS

MUSS: Multilingual Unsupervised Sentence Simplification by Mining Paraphrases, as the name suggests, can train a state of the art text simplification model with unlabelled data. This is an implementation of the paper for the Dutch language, which is altered to run on a workstation with 32GB RAM...

Project photo

Review Sentiment Analysis with BERT using TensorFlow and Hugging Face

A simple tutorial on how to use distilBERT or BERT for a NLP classification problem on Google Colab using TensorFlow and Hugging Face pre-trained models. The used data are reviews scraped from the web and pulled through Google Translate to obtain an English review dataset together with the...

Project photo

Streamlit Deployment of Domain Enhanced Arbitrary Image Style Transfer via Contrastive Learning (CAST)

I'm a big fan of vintage posters. In the past I've tried to make vintage posters by scraping a ton of vintage posters, together with landscape pictures, and train a CycleGAN in to apply the style of vintage posters to the pictures. The results were underwhelming and training the networks capable...

Project photo

Identifying Malignant Tumors with Machine Learning

Using data centered around the measurement of a variety of tumors, we created 3 machine learning models and compared the performance of each in classifying tumors as malignant or benign. We catered our approach, explanation, and demo towards medical professionals and explained a variety of model...

Project photo

Glycemic Index vs. Glycemic Load

The data for this project is scraped from mendosa.com which includes over 1700 foods' Glycemic Index (GI) and Glycemic Load (GI) values. These features are diet related (sugar levels) and the formula for them suggests that they should have a moderate to strong correlation. That's why, after some...

Vusal Kamalzada

Project photo

Cost of Renting a House in Lagos State, Nigeria

I scraped, cleaned, and analysed real estate data with R to determine the factors that affect the cost of renting residential properties in the state, using PowerBI to visualise insights generated from the analysis.

Daniel Obi-Enadhuze

Project photo

Analyzing Cyclistic Rides Data

My capstone project for the Google DA Certificate. Taking on the role of a junior data analyst working in the marketing analyst team at Cyclistic, I am tasked with using data on Cyclistic rides from May 2021–May 2022 to determine how the different categories of riders use Cyclistic bikes differently

Daniel Obi-Enadhuze