theaidentv / cs-4403-lab-2

CS-4403-Lab-2

The task

From the last lab, it appears that you are all using Python. Great! I have thus made this lab Python specific.

For your project you will need to either create your own data, or access data otherwise publicly available. Getting this data from source to your code is made a great deal easier with the Python pandas package. Have a look at the pandas website, and explore the capabilities of this library: https://pandas.pydata.org/docs/getting_started/index.html

Then go explore the public data available at the links set out on the Term Project page.

Find a dataset that interests you, and provided it is not too large, download it.

Examine how the data is organized and locate a data attribute which you anticipate will have a normal distribution. Finding a dataset available in CSV format makes this the easiest.

Using pandas and whatever other Python functionality you may need, write some code to extract a representative sample of this attribute data from the dataset, not to exceed 10,000 instances, and import it into a dataframe.

Once you have the sample in a dataframe, represent the distribution of the attribute data in a histogram with buckets that make sense (again using our friend matplotlib: https://datatofish.com/plot-histogram-python/ ), and confirm whether your suspicion of a normal distribution holds true.