For each of the two case-studies below, load the data, generate summary statistics for all features, plot some of the features using plot_ly() histograms, box plots, density plots, etc., as appropriate, and save the summaries locally as tab-delimited text files.

• Traumatic Brain Injury (TBI) Demographics and Clinical Data Links to an external site..
• Acute TBI Neuroimaging Data. Links to an external site.

• Use the above TBI data Links to an external site. to explore some bivariate relations (e.g. bivariate plot, correlation, table, crosstable etc.)
• Use DSPA Case-Study 7, 07_UMich_AnnArbor_MI_TempPrecipitation_HistData_1900_2015 data, to show the relations between temperature and time. [Hint: use plot_ly()].

Problem 2.3 (Missing Data)

Introduce (artificially) some missing data in the Knee Pain dataset Links to an external site., impute the missing values and examine the differences between the original incomplete and the imputed datasets.

Problem 2.4 (Surface Plots)

Generate a surface plot for the (RF) Knee Pain data illustrating the 2D distribution of locations of the patient reported knee pain (use plot_ly and kernel density estimation).

Problem 2.5 (Sample-Size Rebalancing)

Rebalance the groups of ALS (training data) patients according  $ALSFRS_-Total_-max>37$  vs. $ALSFRS_-Total_-max\le37$ using synthetic minority oversampling (SMOTE) Links to an external site. and confirm approximately equal cohort sizes. [Hint: table(ALS.train$ALSFRS_Total_max <= 37) # FALSE  TRUE  # 257  1966]