In this assignment you will continue to process the dataset $($diabetes$.$csv$)$ using linear regression models and scikit$-$learn libraries. Write a report on your observations.

Download disabetes$\_$df$.$csv $($you created during Assignment$-1)$

Create a Pandas dataframe from diabetes$\_$df$.$csv and call it assignment$2\_$df

Setup the Machine Learning Model:

Divide the data into features $($X$)$ array and target $($y$)$ array.

Split the dataset into $80-20,70-30,$ and $60-40$ ratios. $($Example: $80-20$ means, $80\%$ training data, $20\%$ testing data, and so on$.)$

For each data split, apply logistic regression machine learning model to build confusion matrix and accuracy estimates.

Which data split is providing you the best accuracy?

For the selected data split in step $4,$ run the bootstrap analysis and calculate p$-$value, and confidence intervals.

Write a short report documenting your observations such as accuracy, threshold $($for receiver operator curve, p$-$value for model acceptance, and a histogram showing the confidence intervals.