Learning Phrases with PyLucene, part1

on March 3, 2026

Lucene is a library that is used to build text search optimised indexes, it is an Apache project and is the core file format sitting under ElasticSearch. The following code uses pylucene which is a JNI wrapper to the Java API.

The algorithm derives from the idea that the terms in search results will have increased frequencies for their search terms and associated concepts. Phrases similarly should have increased frequencies. By using Lucene it is fast, though we have to index first. The code also demonstrates an integration between Lucene and Pandas for analytics. The technique here could be used summarise in aggregate user / player entered text in surveys, reviews etc. That might otherwise get ignored by analytics.

Continue reading

Analytical Problem Solving

on November 23, 2018

Data can tell you much, but only if you know how to use it effectively. After all, if you know how many people have signed up to your service, but not how many are actually using it, you can’t truly understand customer behaviour and prioritise your service improvements. Analytical problem solving can help you gather the right data and use it to solve real problems - if you can build the insights that will reveal the full story of your customers, and help give you the answers you want from your data.

Continue reading

Areas of Expertise

on November 23, 2018

At ACUMED Consulting, we specialise in using data science to drive progress, innovation and success within businesses. We have concentrated experience in Gaming Analytics, but have worked in cybersecurity, fraud detection, marketing, banking, insurance, telecommunications and government sectors too. Our experts are skilled in a range of data science and analytics areas including:

Analytical Methods and Problem Solving

Reducing dimensions Time series analysis Anomaly detection - finding unusual behaviour

Machine Learning

Continue reading

Consultancy

on November 23, 2018

There are a lot of challenges that a business can encounter along their journey, and most of them can be solved by data. For example, encouraging customer purchases. To achieve this, you may want to understand your customer demographic: how much an average customer spends with you, what products or services they look at, how long it takes them to make a purchasing decision, and any factors influencing that decision. If you have that data, then you can analyse it, and use it to tailor your services.

Continue reading