This repository hosts various notebooks out of my recent Data Analysis and Data Science projects.
This notebook deals with a predictive model for bike demands for a bike rental company in Medellin, CO. The preliminary analysis gives a broad insight on the rental logs with over 14m rows.
The notebook was created as part of one of four challenges at the WorldDataLeague
Analysing performances of Facebook ad campaigns. Giving recommendations on how to get the best performance out of the campaigns.
The targeted feature is the conversion of the listed ads. A similar data set can be found here: Kaggle source
This notebook tries to find a model to count the amount of stacked metal sheets on pallets through image recognition. The data set provides ~100 images of metal sheet stacks.
The notebook is currently in progress. Most of the preprocessing is done so far.
A short guide to a simple music artist recommender app. The data set of over 1m rows is accessible on Kaggle.
The recommender was pushed to Heroku and can be accessed here: Artist Recommender. The user can type an artist and get 3 artist recommendations relevant to the given musician. Try it yourself :)