The dataset used can be found in the repository, along with the source code. Training and testing have been done using Support Vector Machines, and K-Nearest Neighbours.
Alternately, the dataset used can be found in the following link: https://archive.ics.uci.edu/ml/machine-learning-databases/breast-cancer-wisconsin/ , and the dataset is titled 'breast-cancer-wisconsin.data'.
NOTE: The dataset used is the Wisconsin Standard Dataset. There is another dataset available for Breast Cancer Detection, but we're not making use of that.
git clone https://github.com/AnindKiran/Breast-Cancer-Detection-Using-ML
cd Breast-Cancer-Detection-Using-ML
It is presumed that you have at least Python 3.7. The prerequisites include: sklearn, Pandas, Matplotlib, and numpy. Although using conda would be preferable, the following commands use pip to install libraries considering most people have the 'pip' utility. Use the following commands to install them:
pip install -U scikit-learn
pip install pandas
pip install matplotlib
pip install numpy
Open Jupyter Notebook using the following command on the cmd / terminal (depending on your platform):
jupyter notebook
The notebook will be visible for you to use.