golang How (and why) I built an over-complicated data-driven system to remind me to drink water Data, Golang, Python, Android, Docker, gRPC, Firebase, Cloud, BigQuery. Oh my!
artificial intelligence Sorry, but your cat or dog AI is damaging the world. Summarizing the “Green AI” paper
Fitbit Interpreting 270862 Fitbit footsteps using time series analysis with Prophet Learning how much I walk during my 24 days in Malaysia
puerto rico The importance of social networks in the Puerto Rican protests How a country united under the same hashtag, #RickyRenuncia.
nlp What did Puerto Rico say after its governor resigned? A Twitter data analysis Interpreting tweets containing the hashtag #RickyRenunció using spaCy, Google Cloud, and NLP. The island of Puerto Rico and its people are currently making history. On July 13, the Puerto Rico’s Center for Investigative Journalism published a document consisting of 889 pages of Telegram messages interchanged between the governor, Ricardo
Articles Analyzing tweets from the controversial Pokemon-related #BringBackNationalDex hashtag with spaCy and Google Cloud Discovering the top part-of-speech terms, sentiment, and mentioned Pokemon with the NLP library spaCy and Google Cloud
opinion More focus and desire to finding answers, and less hype My view on why newcomers should focus on the basics and on the true meaning of working with data
Projects Reliving Avengers: Infinity War with spaCy and Natural Language Processing Discovering the top nouns, verbs, entities and text similarity within the spoken lines of Earth’s Mightiest Heroes
Projects Am I going to listen to Potato Salad today? Using data, statistics and machine learning to make sense of my obsession with this song Please bear with me because this will sound crazy. There is this song by Tyler, The Creator, and A$AP Rocky, named Potato Salad, and I like it. My girlfriend says I play a lot,
Articles On how I acknowledge human based bias and how to handle it A word on how we, data practitioners, should be more aware and attentive to our own biases (story originally posted on Medium) In the world of data science, we define bias as the phenomenon in which a system overgeneralize from its data and learn the wrong thing. When this happens,
Projects Building a League of Legends team recommender in Go How to build a recommender system from scratch, and deploy it in the cloud Ever since the boom of machine learning started, many aspects of our online lives have become a target of it. In particular, one of its primary use cases — recommender systems — have become so prevalent in our
Spammers vs Data @ PyData Warsaw 2018 On November 19, 2018 I presented a talk regarding Antispam at PyData Warsaw 2018. Unlike last year's presentation, which was about a personal project, this year I decided I talked about spammers, data and about my role I play as a Spammer Fighter or Software Engineer Big Data
Projects What was Puerto Rico Googling during and after Hurricane Maria? Hurricane Maria left most of Puerto Rico dark and nearly uncommunicated. Under such circumstances, I assumed that the country's Google Search patterns would change. In this article, I explore this.
Pikachu Detection System Talk @ PyData Amsterdam 2018 On May 26, 2018 I had the fantastic opportunity of presenting my Pikachu detection project at PyData Amsterdam 2018. The experience was a great one (to be honest it's been my favorite presentation so far), and the lessons learned were even better. I'd like to thanks
Projects Detecting Pikachu in videos using TensorFlow Object Detection The second part of my Pikachu Detection project is about improving the model I previously trained during the first iteration of the project, and making said model able to detect Pikachu from videos. The article explained the experiment is available on Medium: Detecting Pikachu in videos using TensorFlow Object Detection
Spotify Analysis Talk @ MLDD Meetup On March 20 I had the chance of presenting my Spotify experiments at the Machine Learning Dresden Meetup. Even though it was late, cold and dark, the audience was great and very active in the discussion, which made everything way better. Thanks to everyone who assisted, and to the organizing
Welcome My name is Juan, a data and machine learning practitioner and in this blog, I will share my experiments and projects, in addition to other data-related content.
Projects Detecting Pikachu on Android using Tensorflow Object Detection First part of my Pikachu Detection project. Report is available at my Medium page: https://towardsdatascience.com/detecting-pikachu-on-android-using-tensorflow-object-detection-15464c7a60cd
Projects Discovering similarities across my Spotify music using data, clustering and visualization This article, which is the second part of my Spotify series, is about exploring my music taste using unsupervised learning. You can read it here: https://towardsdatascience.com/discovering-similarities-across-my-spotify-music-using-data-clustering-and-visualization-52b58e6f547b
Projects Is my Spotify music boring? An analysis involving music, data, and machine learning In this article I am comparing my music tastes with those of my girlfriend. The analysis include topics such as exploratory data analysis, supervised learning and some fun topics. The article can be found at: https://towardsdatascience.com/is-my-spotify-music-boring-an-analysis-involving-music-data-and-machine-learning-47550ae931de
Projects Doing Machine Learning (K Nearest Neighbors) in a Messenger Chatbot This project is about Facebook Messenger chatbot I built that trains a k-nearest neighbor model. Link to the article: https://chatbotnewsdaily.com/doing-machine-learning-k-nearest-neighbors-in-a-messenger-chatbot-58f0d261a17f
Projects Pokemon, Colors, and Deep Learning This blog post explains how I built a convolutional neural network to predict the type of a given Pokemon. The whole story is available at: https://medium.com/@jdiossantos/pokemon-colors-and-deep-learning-95fb715be46
Projects 9 days of Pokemon Go — a statistical analysis (this story was originally published on Medium: https://medium.com/@jdiossantos/9-days-of-pokemon-go-a-statistical-analysis-3bbad8aaedc2) Pokemon Go is finally out. Like every 90’ kid (and as a huge fan of the series), I have spent a considerable amount time catching our beloved digital creatures. However, besides spending battery life and swiping my screen