Modify Tutorial$\_4\_$Data$\_$Preprocessing.ipynb to do a few steps with the attached university salary and faculty size data set $($aaup$.$csv$).$

Here is a description of the variables in the dataset.

Univ$\_$id: id number

Univ$\_$name: Name of institution

State: $2$ letter state code

Type: $($I$,$ IIA, or IIB$)$

fp$\_$sal: Average salary $-$ full professors

ac$\_$sal: Average salary $-$ associate professors

at$\_$sal: Average salary $-$ assistant professors

to$\_$sal: Average salary $-$ all ranks

fp$\_$com: Average compensation $-$ full professors

ac$\_$com: Average compensation $-$ associate professors

at$\_$com: Average compensation $-$ assistant professors

to$\_$com: Average compensation $-$ all ranks

fp$\_$#: Number of full professors

ac$\_$#: Number of associate professors

at$\_$#: Number of assistant professors

in$\_$#: Number of instructors

to$\_$#: Number of faculty $-$ all ranks

Tasks

Replicate the preprocessing steps applied to the breast cancer example as guided below:

Input the data into a Pandas dataframe; create the data columns of your choice; print the number of observations and attributes.

Recode the missing values to NaN. This dataset uses $*.$ Print the counts of missing values across the attributes.

How do you handle missing values in this dataset? Explain your selection. $($put your answer in the box below$)$

Explore for outliers. Apply the boxplot display. Are there any outliers? $($put responses in the box below$)$

Are there any duplicate records?

Can you aggregate the institutions within each state using the grouping operation from Pandas? So you should end up with $50$ observations. Which statistics are you aggregating on$?($describe in the box below$)$

Explore some sampling from the original data set, not the aggregate. What did you find to be the best? Why? $($put answer in the box below$)$