Q1) Using R programming language, perform the following experiments on the Wisconsin Breast Cancer Dataset:

The Wisconsin Breast Cancer Dataset is one of the most popular datasets used to diagnose breast cancer into benign or malignant classes. The dataset has 699 instances and 11 variables that are mostly related to the tumor characteristics. Such as the tumor size and shape.

To learn more about the dataset, please visit the following web page:

http://127.0.0.1:25834/library/mlbench/html/BreastCancer.html

Type the following code to download the Breast Cancer dataset from the mlbench package.

# Load data # install.packages('mlbench') data(BreastCancer, package="mlbench")

Split the data into training and testing using 10-fold cross validation technique. Select one feature selection method and apply it to your data (you can use Weka tool for feature selection). Build two models one that includes all your features and one that includes the selected features. Compare the performance of both models using Accuracy, sensitivity,specificity, F-measure, precision, and recall. Which model performs better? Which performance measure you think works better in measuring the performance of your model and why?