posts

It’s been a long time since I posted as life has been mostly work since I stopped being a student. During this December break, I decided to spend some time to complete the R package which I had been working on but had not complete. Also, it was taken off CRAN for a quite some time as there was some issue with data.table.

Last week, I went over to Brown University for their annual Datathon. Several data sets were provided for data analysis, from reknowed organisatations such as Citizen’s Bank, Fidelity and Dassault System.

The previous plot was not very nice as the heat maps were messy and not very interpretable. I had spend the past few days learning about sf objects in R, as I had not been previously exposed to working with geo-spatial data properly. This gif certainly seems a bit better than the previous one, though it can definitely be improved on more.

Making use of the Rpackage I just created, the taxi_availability function allows us to query taxi locations to the minute. I was interested in finding out how the taxi availability changes throughout the day after the new year countdown. For this post, I queried the taxi availability for the entire day of 2020-01-01 in 10 minute intervals. Subsequently, it was cleaned and several graphs were plotted.

As part of my coursework, I created an R package which serves as an interface to the developer API tools on data.gov.sg/developers. datagovsgR is a R package used to access data-frames returned by Developer API Tools from Data.gov.sg. The package calls upon the real-time APIs, to obtain information such as taxi availability, real time weather readings, weather forecasts and PSI readings.

I chanced upon the HDB resale flat prices data set and noticed that it was one of the few data sets which did not aggregate the data. Naturally, I went to explore the data set as it was quite extensive.

With the development of the new Changi Jewel in Singapore recently, I was curious to find out where the tourists who visit Singapore come from. I turn to the Overseas visitor survey, which contains information about tourists’accomodation, frequency of visit, purpose of visit and number of travelling companions.

The data within contained the data of the five out of six of the autonomous universities in Singapore, of their graduate employment rates and basic monthly mean salary, between the years 2013 to 2017. Employment Rate and Mean Basic Salary