Download diabetes.csv file from modules in canvas.

Write a function that will print patient records where BMI is in the interval $[27,37],$ and outcome is $1(1$: diabetic, $0$: not diabetic$)$

Create a heat map using seaborn library and list features that are of high importance.

This is a subjective question. You will define $$high importance$$ and you get a chance cross validate them when we do Principal Component Analysis.

High importance is defined as the value being close to $1\mathrm{.}0$ but not equal to $1\mathrm{.}0.$ Sometimes $0\mathrm{.}2$ is of high importance, and other times $0\mathrm{.}02$ is important.

Remember to list both features in the matrix that meet $$high importance$$ criteria.

Using Pandas DataFrames, prepare the data for machine learning. For this you will do the following:

Create diabetes$\_$df $($a dataframe for entire data$)$

Drop records with missing data $(0,$ empty column values, NaN, etc.$).$

For each command, print $$# of records removed$.$

Print $$zero records removed$$ if the condition is not met.

Replace column values where Insulin is $0$ with $150$

Print $$# of records were updated with new data for insulin$$

Rename column $$Outcome$$ with $$Target$$

Write the updated dataframe $($after addressing requirements $($b$)$ and $($c$))$ into a new file: diabetes$\_$df$.$csv $($we will use this for machine learning$)$

Instructions:

Include comments for each step in the assignment to help us grading your work.

Submit a ipynb and pdf file both files. Don't submit zip file and zip files will not be accepted

diabetes.csv file link.

$$https:$//$unt$.$instructure.com$/$courses$/106574/$files$/27000226/$download$?$download$\_$frd$=1$