Based on the first visualization implementation, to better visualize the data, our group chose P5, D3 languages, and Leaflet to explore more valuable information.
1.Visualization by using P5
Further format the data
After the first implementation, we find some problems that needed to be solved. Our data set has multiple rows for each city with different information, like company name company rate, and average salary. So that results in we had several points that were overlapped in one position in our first implementation.
To solve this issue, we use R to group the data concerning city and state, then calculate…
Firstly, what need to be mentioned here is the initial data set we used not includes latitude and longitude information. In order to visualize the map, we try to get the longitude-latitude coordinates for a (very long) list of cities by using Python and a free API. …
1. The idea of adding ‘Click’ function in Converge 1,2,4 is very useful, it combines several features in one plot which makes it much more informative.
2. Explore the value of EUI based on year, building type, …, it is a valuable and meaningful analysis.
1. It seems all the figures are almost focus on the direct relationship with EUI which I understand, but what about jumping out of this circle, make further considerations on other aspects like, how the style of building changes based on year and why is that, how that change influence the EUI… .
Till now, our group has already finished the first design session for our project. This blog will briefly introduce the ‘diverge’ and ‘emerge’ procedure of our design session.
Miro link: https://miro.com/app/board/o9J_lOYjlXQ=/
First, let’s have a glance at our miro board to have an overview of the work we currently have done:
Data Scientist is the sexiest Job of the 21st century. There are experts saying ‘Data scientists today are akin to the Wall Street “quants” of the 1980s and 1990s’. Living in a data-driven world create job vacancies for data scientists, and the dataset we are going to analyze contains 12000+ fresh data science job listing, it is quite helpful for job seekers to get an insight into it.
The data science job listings consist of four major types of data science job (business analyst, data analyst, data engineer, data scientist) in different cities in US and other countries . …
Aims to launching an analysis on Data science job market.
The motivation and background
As Statisticians that we exactly are, It is very willing and meaningful for us to dig more deeper information about the situation of our future career. So, we can take some actions to prepare in advance before we become an employee.
The source of the dataset we have chosen is from glassdoor and Kaggle. It contains 12,000+ job listing for four types of data science job (business analyst, data analyst, data engineer, data scientist) in different cities in US and UK. …