Waffles are for Breakfast It’s been a long time since my last update and I’ve decided to start with Tableau, of all topics! Although open source advocates do not look kindly upon Tableau, I find myself using it frequently and relearning all the... [Read more...]

Milwaukee Beer - Inspired by my Job Hunt I’m excited to launch my latest Shiny app - “Milwaukee Beer” - which I made to learn shinydashboard. Due to my decision to return to the USA and hunt for a career in data, I decided to add another project to ... [Read more...]

Today I want to predict churn using data from a hypothetical telecom company. Although it isn’t real life data, it is based on real life data. The data are spread across 19 columns — 14 continuous, 4 categorical, and the outcome variable for prediction - “churn”. The dataset is small, with 3333 rows for ... [Read more...]

This post is following exercise 1 in Chapter 12 of Applied Predicative Modeling. Here I use the machine learning package CARET in R to make classification models; in particular, the linear classification models discussed in Chapter 12. The dataset in question is about hepatic injury (liver damage). It includes a dataframe of biological ... [Read more...]

“Halo 5 Stats” is my first ever Shiny app, which is themed around the the popular sci-fi shooter Halo 5. It combines beatiful data with Halo’s beautiful graphics - something that Halo fans and data enthusiasts undoubtedly love. You can use my app... [Read more...]

This is a continuation in my series of exploratory text analysis of 3 Chinese classic works. In the previous post, I calculated word counts for each book, and visualized common words using bar charts. This time, I’d like to examine word use across the texts with network visualization. The goal ... [Read more...]

In the last post, we saw frequencies of the most common words in the Analects, Zhuangzi, and Mozi texts. The faceted plot did an excellent job of capturing a generic “theme” of each text. However, I wondered how the results might change when plotting bigrams (2 word combinations of adjacent words) ... [Read more...]

For a long time I’ve admired the tidytext package and its wonderful companion book Text Mining with R. After reading it I thought, “Why not undertake a project of Chinese text analysis?” I am deeply interested in Chinese philosophy but I decided to keep the analysis narrow by selecting ... [Read more...]

My latest update is a milestone! I have authored my first ever R package which is an API caller for ctext.org. Ctext hosts numerous pre-modern Chinese texts and my package makes them available to you. The scope is broad, but think philosophical works in Confucianism, Daoism, Legalism, military doctrines, ... [Read more...]

Last week I was considering a project that would be interesting and unique. I decided I would like to do a text analysis on classical Chinese texts, but wasn’t sure what kind of analysis regarding which texts. I decided to keep it small - and use five of the “... [Read more...]

Deep, labored breathing Hello everyone, this is the opening post on my new blog, which I’m relocating from Wordpress to GitHub Pages and Netlify. It’s so nice I’ve given it a name - because nice things have names! But, why was I panting? The relocation effort wasn’... [Read more...]

I suddenly got bit by a bug to learn about network analysis. So I recalled the Correlates of War Project having a dataset about alliances. I decided to revisit them and download the data for this new project, which you can do too. To start small, I decided to visualize ... [Read more...]

Today I’d like to work a little on geospatial mapping in R, so I’ve chosen a small dataset (only 256 kb) that can be plotted on a map. It the location information of Fortune 500 company headquarters in the US. You can download it from here. R has several choices ... [Read more...]

Somebody once asked me for reccomendations on MBA programs based on rank and tuition. I didn’t have any information on hand, but knew how toget it. Webscraping. Webscraping is an immensly useful tool for gathering data from webpages, when it isn’t hosted on an API or stored in ... [Read more...]