Posts in 'machine-learning'

Playing around with the breast cancer dataset

The Breast Cancer Dataset is a dataset of features computed from breast mass of candidate patients. Each instance of features corresponds to a malignant or benign tumour. The motivation behind studying this dataset is the develop an algorithm, which would be able to predict whether a patient has a malignant or benign tumour, based on the features computed from her breast mass. I decided to use this dataset for my first blog post on machine learning, since its a very straightforward dataset with no missing values and all variables being real valued (no categorical variables).