Code used for "Machine Learning with Python" workshop at Cambridge Coding Academy: http://cambridgecoding.com/workshop/machine-learning/cambridge
Modules cover:
- Module 2: Visualisation of feature data distribution from Fisher's iris data set
- Module 3: Visualisation of distribution and correlation of feature data from UCI's breast cancer data set
- Module 4: Experimenting with k-nearest neighbours classifier on the breast cancer data set, and looking at validation metrics
- Module 5: Experimenting with a Naive Bayes classifier on the breast cancer data set
- Module 6: Using k-fold cross-validation to evaluate classifier generalisation, and parameter optimisation using grid search
Some interesting plots: