Homework - 4
Due: September 19, 2013
Data Analysis and Summary
In this homework, we will analyze some data collected by mlab. Specifically, we will analyze data collected by NDT (Mobile Client). The purpose of this data analysis is to understand the network performance between mobile clients and mlab servers.
Download network performance data. Each of you will analyze one month worth of data. The following Python code helps you find the year and month for the data you have to analyze:
yourid = 'your id' month = 1 + int(yourid[-2:]) % 12 if month < 9: year = 2013 else: year = 2012
You can read about the data format here: https://code.google.com/p/ndt/wiki/NDTDataFormat
Link to the dataset: https://storage.cloud.google.com/?arg=m-lab/ndt#m-lab%2Fndt
In this assignment, we will be analyzing the meta data file.
Summarize S2C throughput speed and C2S throughput speed. Your summary must include analysis of the distributions, different statistical summaries, and graphs.
Are C2S and S2C throughput speed correlated?
Your submission should also include a few paragraph description of what the data is about and how you obtained the data. This text should read like a description of experiment settings in research papers.
Submission
Please submit your homework on Moodle.