Task $3$ Data Modelling $(28\%)$

In this task, you are asked to choose TWO classification models, and carry out the following steps:

$3\mathrm{.}1$ Splitting the data into a training set and a test set. Specifically, you need to split the data at the following

ratios, respectively, to form three different suites of training and test sets:

$$ Suite$1$: $50\%$ for training and $50\%$ for testing

$$ Suite$2$: $60\%$ for training and $40\%$ for testing

$$ Suite$3$: $80\%$ for training and $20\%$ for testing

You must describe the way you have used for splitting the data to ensure the reproducibility of your

work in the report required in Task $4.$

$3\mathrm{.}2$ Performing the following steps for each of the two chosen models on each of the above three suites:

$$ Identifying the method in the $$scikit$-$learn$$ package which implements the chosen model.

$$ Selecting appropriate model parameters and use them to train the model via the above$-$identified

method. You must elaborate and justify the way you have used for parameter selection in the report

required in Task $4.$

$$ Evaluating the performances of the model on the training and test sets, respectively, in terms of

o Confusion matrix

o Classification accuracy

o Precision

o Recall

o F$1$ score

and report them in the required Task $4$ Report.

$3\mathrm{.}3$ Comparing the two chosen models via appropriate graphical visualisations based upon the above

evaluation results. You must describe key observations, analyses and conclusions from comparison and

accordingly recommend which model should better be used in the report required in Task $4.$

You must also describe your workflow $($including the involved key components$)$ for completing this task,

provide justifications of any choices you have made and discuss any issues if encountered $($including the ways

you$$ve used to address them$)$ in the report required in Task $4.$