Goto

Collaborating Authors

All the Datasets You Need to Practice Data Science Skills and Make a Great Portfolio

#artificialintelligence

Every time I attempt to do a project for learning a new topic or for a project I spend a significant amount of time finding a suitable dataset for that. That way I have quite a lot of datasets that helped me learn and do some cool projects for my portfolio. I am going to share those datasets in this article so that you have a dataset to practice and make your portfolio. This dataset has information on the Olympic results. Each row contains the data of a country. This dataset will give you a taste of data cleaning to start with.


MuseGAN: Using GANs To Generate Original Music - AI Summary

#artificialintelligence

GANs are highly versatile, allowing for the generation of anything that can be synthesized into images. By utilizing this feature of GANs, it is possible to generate very unorthodox content, at least from the perspective of machine learning. This article is sharing my project where I used GANs to generate baroque music, based on midi files of Bach compositions. This is not the first time that I used GANs to generate creative content. I wrote a GAN last time that would generate art, based on famous artworks by famous artists.


Three Tricks to Speed Up and Optimise Your Python

#artificialintelligence

Every data scientists needs to maintain up-to-date: every day they should read, read and again read. One possible strategy to maintain yourself up-to-date is to register to Twitter and follow the top influencer data scientists, as well as to subscribe to newsletters and join groups related to Data Science. In my June discoveries, I have found three interesting Python packages, which permit to speed up operations and reduce memory usage. Often, in fact, we are faced with the management of quite large datasets, which require long computation times. According to the official Numba Web Site, Numba is an open source JIT compiler that translates a subset of Python and NumPy code into fast machine code.


Image recognition app scans paintings to act like Shazam for art

New Scientist

Taking a souvenir home from an art gallery no longer has to mean a trip to the gift shop. A new app lets people scan a work of art with their smartphone camera to find out more about it and save a digital copy. The app, called Smartify, uses image recognition to identify scanned artworks and provide people with additional information about them. Users can then add the works to their own digital collection. Smartify co-founder Thanos Kokkiniotis describes it as a combination of the music discovery service Spotify and music recognition app Shazam – but for visual works.


How to Declutter a Bar Chart in Altair

#artificialintelligence

Recently I have read a very interesting book by Jose Berengueres, entitled Introduction to Data Visualization & Storytelling: A Guide For The Data Scientist. In this book, the author describes many techniques to extract from a dataset a very interesting story. Taking inspiration from this book, in this article I describe a strategy to declutter a bar chart in Altair and to extract a story from the represented data. Altair is a popular Python library for Data Visualization. Many other Python libraries for Data Visualization exist, such as Matplotlib and Seaborn.