Accuracy score = 0.98
Resulting Decision Tree model visualization:
Tech stack: scikit-learn, Matplotlib, Pandas, NumPy. Dataset used: Drug Data, link here. Description: A Decision Tree model from scikit-learn was employed to determine the most suitable drug for a patient based on their biodata, based on historical record. The non-numeric categorical values in the dataset were converted into numeric values with label encoders and then fed to the model for training. The criterion chosen was to minimize entropy and max depth = 4. Resulting accuracy metrics:
Accuracy score = 0.98
Resulting Decision Tree model visualization: