Choose an open dataset of your choice to complete this assignment:

$1.$Include a basic description of the data.

$2.$ Write your own description of what the classification task is and why a decision tree is a reasonable. model to try for this data.

$3.$ Include one summary visualization of the data.

$4.$ Fit a decision tree with the default parameters on $50\%$ of the data.

$5.$ Test it on $50\%$ held out data and generate a classification report.

$6.$ Inspect the model by visualizing and interpreting the results.

$-$Does this model make sense?

$-$Are there any leaves that are very small?

$-$Is this an interpretable number of levels?

Next do an experiment to see how max$\_$depth, min$\_$values$\_$split, or min$\_$values$\_$leaf impacts the model.

$1.$ Choose one of these and explain why and how you hypothesize it will impact the performance

$2.$ Use the model you fit above and EDA to choose minimum and maximum values for your parameter. Choose a total of $3$ values for the parameter.

$3.$ Retrain the model for each value of the parameter.

$4.$Test and use at least $3$ metrics to describe the performance, compiling your results into a DataFrame.