Dataset is from: http://archive.ics.uci.edu/ml/datasets/breast+cancer+wisconsin+%28diagnostic%29
Environment: Google Colab
Languages and libraries used: Python, matplotlib,scikit-learn, seaborn, numpy
Cleaned and analyzed dataset. Then trained and used 4 different machine learning models from scikit learn:
Support Vector Machine, Random Forest, Decision Tree and Logistic Regression
whether a patient would have breast cancer based on the features of the dataset. All models had very good accuarcy
due to the fact that the dataset was so large and was already mostly ready to be used for training.
However it seemed that Support Vector Machines had by far the best accuarcy rate: 98%.
danteshub / breast-cancer-detection Goto Github PK
View Code? Open in Web Editor NEWDataset is from: http://archive.ics.uci.edu/ml/datasets/breast+cancer+wisconsin+%28diagnostic%29