Reduce the dimensionality of data and plot it as one or more 2D graphs. You can use a number of tools such as: Matlab, Paraview (open-souce, http://www.paraview.org/), Mathematica, Wolfram (with ListPlot), Meshlab (also open-source, http://meshlab.sourceforge.net/), PCL (free for commercial and research use, http://pointclouds.org/), etc. Even WEKA (http://www.cs.waikato.ac.nz/ml/weka/) will do. Additionaly, if you need to draw decision trees or any sort of network or hierarchical structure Graphviz (http://www.graphviz.org) is a good free choice.

Dear friend

You can use MATLAB. Its very nice.

All the best.

Could you tell us more about the data; how was it generated?

I dont know how the data was generated because yesterday only I joined as Research Associate. My first work is to load that whole data in .dat format to mysql. the .dat file contains data without the delimiter. I am planning to convert it to .csv and use LOAD DATA LOCAL INFILE in MySQL

Okay - do you know what the data represents e.g. is it transformed video, a financial transaction log, genetic sequence data?

it is trade data. so i think it can be transformed into csv file

So basically a time-series? Sounds like you'd access the database natively (as well as needing strong visualization), so I'd go for something well-rounded e.g. R or Matlab during data exploration. Both have libraries allowing database access via JDBC, in addition to Finance libraries. Matlab has significant license costs, particularly if you start scaling algorithms; R was not originally designed for horizontal scaling, but is apparently getting better.

I've not had much experience with Python, perhaps someone else could advise?

I will suggest using Pandas (in Python). You can import the .dat file into a dataframe. This will then allow you to view, analyse and manipulate the data as you wish. There are easy to follow tutorials that can take you through this process. (http://wesmckinney.com/blog/?p=647)

http://www.hiveplot.net/ can be used for big datasets.

We worked with 700 GB OpenStreetMap data to develop new insights into it. The tool we used is head/tail breaks, which enables you to filter out data efficiently and effectively.

Jiang B. (2015), Head/tail breaks for visualization of city structure and dynamics, Cities, 43, 69-77.

Ma D., Sandberg M., and Jiang B. (2005), Characterizing the heterogeneity of the OpenStreetMap data and community, ISPRS International Journal of Geo-Information, xx(x), xx-xx, Preprint: http://arxiv.org/abs/1503.06091

https://www.researchgate.net/publication/273957178_Characterizing_the_Heterogeneity_of_the_OpenStreetMap_Data_and_Community?ev=prf_pub

https://www.researchgate.net/publication/270634544_Headtail_Breaks_for_Visualization_of_City_Structure_and_Dynamics?ev=prf_pub

Article Characterizing the Heterogeneity of the OpenStreetMap Data a...

Article Head/tail Breaks for Visualization of City Structure and Dynamics

Can you reduce the data dimension size using PCA?