GDP vs other key indicators analysis
Contributed by Amit Sahoo. He is currently in the NYC Data Science Academy 12 week full time Data Science Bootcamp program taking place between January 7th to April 1st, 2017. This post is based on his 1st class project - Exploratory Data Analysis and Visualization with Shiny (due on the 4th week of the program).
Coming from a analytics background i wanted to challenge myself to see how can i visually represent something by more than 2 dimension. So I was inspired by Hans Rosling TED talk where he provides stats based on some cool visualizations. So I started on a quest to come up with some visualization similar to his with the knowledge i had gained so far using R and Shiny. Then came the process of data gathering and data cleaning.
Getting the Data
I wanted to have a data set which has all the data for almost all the countries for last 15 years to be able to able to provide some meaningful visualization and to be able to figure out some correlation among the data. So i gathered some data from world bank like GDP, Population, Employment Ratio, CO2 emission. Since i had CO2 emission data was curious to see how the world temperature has changed over last 15 years. So was able obtain earth surface temperature data from Kaggle.
SHINY APP walkthrough
The app contains 4 sections as below in the screenshot
Gives a brief intro to how to navigate through the app.
Correlation By Region:
This will give you a correlation plot at the Region level and lets you choose a Region what interest you and its a multi-select field which lets you choose multiple regions. You can select the type of icon you want for your corrplot.
Correlation By Country:
This will give you a correlation plot at the Country level and lets you choose a Country what interest you and its a multi-select field which lets you choose multiple Country. You can select the type of icon you want for your corrplot.
Time Series Dashboard :
This give you a plot and you can choose the X and Y variable. The bubble in the graph is set to "Population" by default but can be changed. The bar below lets you control the year you what interests you or you can press the arrow button to Autoplay.
SHINY Code walkthrough
The below code was defined for ui.R
server.R code as below
All the data processing steps like cleansing and merging files were done in the global.R as below
With additional time it would be interesting to make use of other key indicators to be included in the above dataset.
The link to the app can be found here.