Creating a Development Environment for SQL

My past few positions have had me using a lot of Python, R, Docker, Airflow etc., and not as much pure SQL for analysis. As a result, my SQL skills are a little rusty. So I decided to create a development environment for SQL in order to practice. In this quick post I’ll outline how I setup a PostgreSQL environment in a docker container. There are plenty of practice environments online, but I want to have certain data tables available to practice analyzing business data specifically (MAU, ARPU, Revenue, etc.).

A/B/N Testing in Python

The following case study will illustrate how to analyze the results for an A/N Test (or multitest). An A/N Test is a type of A/B Test in which multiple variants are tested at the same time.

We’ll compare 2 variants, against a control, to increase purchase rate on a fictional website. Since testing multiple variants at once increases the error rate (known as Family Wise Error Rate–FWER), we’ll use a correction when determining statistical significance.

Along the way, I’ll warn against some common mistakes when designing and interpreting results of experiments. And touch on the sticky subject of P-values and what they mean (and don’t mean). Hope you find it informative.

A/B Testing in R

A stakeholder may ask if a particular change, to an application, will make a user more likely to make a purchase (or more likely to make a larger purchase, etc.). These types of questions are excellent candidates for a controlled experiment–known as A/B Testing. To answer these questions, a data scientist must apply good testing methods; and understand well, certain statistical concepts to evaluate the experiment effectively. A/B testing can be tricky to conduct without bias and difficult to evaluate. And like all hypothesis testing, there is a certain amount of uncertainty inherent. It’s this uncertainty that the Data Scientist attempts to quantify and explain.

Time for a New Chapter

Having spent the last three years as a Data Scientist at Location Labs by Avast and later at Smith Micro Software Inc (following the division’s acquisition from Avast), I am now seeking my next opportunity. In my previous role, I fulfilled multiple responsibilities, including supporting the product development team and spearheading the development of a cutting-edge Data Science Platform and workflow based on open-source tooling, using a microservices/API approach.

Twitter Sentiment Analysis: Part 2

This is the second part of the Twitter Sentiment Analysis. I will create a TFIDF and perform some dimensionality reduction to allow me to use the mighty Random Forrest algorithm.

Twitter Sentiment Analysis: Part 1

The following is an analysis of the Twitter Sentiment Analysis Dataset available at: http://thinknook.com/twitter-sentiment-analysis-training-corpus-dataset-2012-09-22/. I will attempt to use this data to train a model to label unseen tweets into “Positive” or “Negative” sentiment. I will walk through my methodology and include code.

Time Series Analysis of crude oil

In order to illustrate data modeling techniques, and also experiment and learn, the following data analysis will be carried out and discussed. This blog will be an iterative process–meaning it may be incomplete to the viewer at any given time. Nonetheless, it will be public in it’s unfinished state for the purpose of feedback and discussion. All code for this analysis can be found at: https://github.com/kwbonds/crudeoil_products. Please Feel free to clone/fork. And please comment to me at kevin.w.bonds@gmail.com with any helpful suggestions or feedback. I greatly incourage it.

Twitter Sentiment Analysis: Part 1

The following is an analysis of the Twitter Sentiment Analysis Dataset available at: http://thinknook.com/twitter-sentiment-analysis-training-corpus-dataset-2012-09-22/. I will attempt to use this data to train a model to label unseen tweets into “Positive” or “Negative” sentiment. I will walk through my methodology and include code.