Homework 6

Problem 6.1 (Network data visualization)

• Use the "Les Miserables Links to an external site." dataset (03_les miserablese_GraphData.txt)
• Visualize the network of (novel) characters as an undirected graph
• Summarize the graph and explain the output
• Calculate the degree and the centrality of this graph
• Find some important nodes (corresponding to key novel characters)
• Will the results change if we assume the graph is directed?

Problem 6.2 (Feature Selection):

Use the 06_PPMI_ClassificationValidationData_Short dataset

• Set ResearchGroup as class variable.
• Delete irrelevant columns (e.g. X, FID_IID) and select only the PD and Control cohorts, as the ResearchGroup feature includes PD, Control and SWEDD (which are mild cases of PD)
• Properly convert the variables types, as may be necessary
• Compare alternative feature selection methods - Boruta, Recursive Feature Elimination (RFE), and stepwise feature selection
• Summarize and visualize the results
• Report and compare the variables selected by these methods. How much overlap is there in the selected salient features?