$$ from sklearn.datasets import load$\_$iris

$$ Using bagging method with a decision tree algorithm, predict with voting method and calculate the accuracy using confusion matrix.

$$ Datasets $(150$ records$)$

$$ X: sepal length, sepal width, petal length, petal width

$$ Y: species $($Versicolor$,$ Setosa, Virginica$)$

$10$ bagging datasets $($for training $10$ classifiers$),$ each with $20$ records

$1$ test dataset that is not sampled during the bootstrapping of $10$ training sets.

$$ Training and evaluating classifiers

$$ Generate a decision tree classifier model using the sklearnDecisionTreeClassifier function

$$ Run $10($training$)$ bagging rounds with BaggingClassifier function.

$$ Using the test dataset, predict the labels using majority voting.

$$ Calculate the accuracy using confusion matrix.

$-$ Output

$1.$ Show the $10$ bootstrapped training sets

$2.$ Show the test set that is not sampled during the bootstrapping

$3.$ Show a table $($dataframe$)$ with predictions from the $10$ base learners and the final ensemble learner

$4.$ Show the confusion matrix