The first thing to do before running any models is to simply understand what the data is about and visualisation is a very good way.
so one Important thing is before plotting always remember
- Numerical+Numerical=Scatter Plot
- Numerical+Categorical=Bar Chart or Heat plots or Line Plots
- Categorical+Categorical=Filled maps
I have used tableau . Its an amazing product and i have a license for tableau as a student.
You can read more about tableau and other amazing dashboards created by tableau here http://www.tableau.com/
So lets get started ,I have made a dash board below , but will explain each component in great detail below
The first column shows total number of records and present and how many people earn above and below 50K. Sorry for the wrong placement for the legend but had no option as I could not fit it in one picture.
The next column specifies the Average hours per week people work , followed by the average age in this data set.
The next 3 are pretty simplistic and could be understood
This scatter plot explains the relationship between age and hours per week .
In The next post i will try to explain all the variables of the UCI adult data set