Having trouble with this, can you help me complete this project

In this project you will implement classification for two data sets. Note that this is a

project and as such, it is somewhat open ended. You can present additional results to what is

asked for here. In writing your report you need to examine and discuss$/$explain your results

and draw conclusions.

I recommend that you use Scikit Learn models. If you prefer to use another coding

language it is OK as long as you finish the work. But make sure that an implementation of

the models is available.

Data Sets:

"load$\_$breast$\_$cancer": This is a binary classification data set. It uses the properties of

sample breast cells as features for cancer detection.

"load$\_$digits": This is a multi$-$class classification for detecting hand written digits.

Explore and print out some information on each set.

Print out the feature names, the target names, the shape of the features and the target

counts $($number of samples in each target class$).$

Print the mean and variance of the first five features.

Plot the distribution of labels as a bar graph and examine if the data set is balanced.

Plot the histogram of the first four features.

The data sets must be split into training and test sets. Set the parameters in the

splitting algorithm appropriately. Make sure you set the "random state$=123"$ so that

the results are reproducible.

Apply standard and Min$-$Max scaling to the data set.

Fit the model $($binary or multi$-$class Logistic regression$)$ to the training set.

Print out the accuracy, the confusion matrix and the F$1$ score for training and test

sets.

Verify whether it makes any difference to scale the data set or not.

NOte: There are a number of methods available for minimizing the loss function besides the

SGD which we have discussed. For LR$,$ "sag" and "saga" are availble on sklearn which are

close to SGD$.$