Big Data *

Everyone uniquely perceives texts, regardless of whether this person reads news on the Internet or world-known classic novels. This also applies to a variety of algorithms and machine learning techniques, which understand texts in a more mathematical way, namely, using high-dimensional vector space.

This article is devoted to visualizing high-dimensional Word2Vec word embeddings using t-SNE. The visualization can be useful to understand how Word2Vec works and how to interpret relations between vectors captured from your texts before using them in neural networks or other machine learning algorithms. As training data, we will use articles from Google News and classical literary works by Leo Tolstoy, the Russian writer who is regarded as one of the greatest authors of all time.

We go through the brief overview of t-SNE algorithm, then move to word embeddings calculation using Word2Vec, and finally, proceed to word vectors visualization with t-SNE in 2D and 3D space. We will write our scripts in Python using Jupyter Notebook.

Couple of years ago my team (compliance in one of Swiss banks) and I had an interesting task to implement — we had to generate a huge random graph of financial transactions between clients, companies and ATMs. Moreover, we wanted this graph to contain some money-laundering and other financial crime patterns alongside with nodes description such as names, addresses, currencies etc. Obviously, all data should be randomly generated from scratch as long as we could not use any real data for obvious reasons.

As a solution we wrote a generator that I’d love to share with you. This article explains why we needed it and how this generator is working, but if you don’t want to read and want to try it on your own here is the code: https://github.com/MGrin/transactions-graph-generator. I hope that our experience will be helpful to any of you.

How Tax Service, OpenStreetMap, and InterSystems IRIS
could help developers get clean addresses

Pieter Brueghel the Younger, Paying the Tax (The Tax Collector), 1640

In my previous article, we just skimmed the surface of objects. Let's continue our reconnaissance. Today's topic is a tough one. It's not quite BIG DATA, but it's still the data not easy to work with: we're talking about fairly large amounts of data. It won't all fit into RAM at once, and some of it won't even fit on the drive (not due to lack of space, but because there's a lot of junk). The name of our subject is FIAS DB: the Federal Information Address System database — the databases of addresses in Russia. The archive is 5.5 GB. And it's a compressed XML file. After extraction, it will be a full 53 GB (set aside 110 GB for extraction). And when you start to parse and convert it, that 110 GB won't be enough. There won't be enough RAM either.