This is a summary of a set of 1 experiments using a LONI pipeline workflow file that performs 3000 independent jobs, each one with the CBDA-SL and the knockoff filter feature mining strategies. Each experiments has a total of 9000 jobs and is uniquely identified by 6 input arguments: # of jobs [M], % of missing values [misValperc], min [Kcol_min] and max [Kcol_max] % for FSR-Feature Sampling Range, min [Nrow_min] and max [Nrow_max] % for SSR-Subject Sampling Range.
This document has the final results, by experiment. See https://drive.google.com/file/d/0B5sz_T_1CNJQWmlsRTZEcjBEOEk/view?ths=true for some general documentation of the CBDA-SL project and github https://github.com/SOCR/CBDA for some of the code.
Features selected by both the knockoff filter and the CBDA-SL algorithms are shown as spikes in the histograms shown below. I list the top features selected, set to 15 here.
## [1] EXPERIMENT 2
## M misValperc Kcol_min Kcol_max Nrow_min Nrow_max
## 9000 0 15 30 60 80
## [1] "TABLE with CBDA-SL & KNOCKOFF FILTER RESULTS"
## [1] "EXPERIMENT" "2"
## CBDA Frequency Density Knockoff Density
## 4 50 6.090134 7 2.481834
## 8 37 4.506699 38 2.350411
## 1 31 3.775883 2 2.346067
## 7 25 3.045067 6 2.325430
## 56 24 2.923264 5 2.314568
## 6 23 2.801462 26 2.293932
## 21 23 2.801462 8 2.288501
## 60 23 2.801462 4 2.287415
## 63 23 2.801462 40 2.271123
## 17 19 2.314251 49 2.213557
## 19 19 2.314251 61 2.136441
## 43 19 2.314251 59 2.079962
## 61 19 2.314251 42 1.973520
## 2 17 2.070646 18 1.920299
## 32 17 2.070646 37 1.904007
## [1] "Top Features Selected across multiple experiments,shared between CBDA-SL and Knockoff filter"
## [1] 4 8 1 7 56 6 21 60 63 17 19 43 61 2 32 38 5 26 40 49 59 42 18
## [24] 37
The features listed above are then used to run a final analysis applying both the CBDA-SL and the knockoff filter. The ONLY features used for analysis are the ones listed above. A final summary of the accuracy of the overall procedure is determined by using the CDBA-SL object on the subset of subjects held off for prediction. The predictions are then used to generate the confusion matrix. We basically combine the CBDA-SL & Knockoff Filter algorithms to first select the top features during the first round. Then, the second stage uses the top features to run a final predictive modeling step that can ultimately be tested for accuracy, sensitivity,…..
## ggplot2 plyr colorspace grid data.table
## TRUE TRUE TRUE TRUE TRUE
## VIM MASS Matrix lme4 arm
## TRUE TRUE TRUE TRUE TRUE
## foreach glmnet class nnet mice
## TRUE TRUE TRUE TRUE TRUE
## missForest calibrate nnls SuperLearner plotrix
## TRUE TRUE TRUE TRUE TRUE
## TeachingDemos plotmo earth parallel splines
## TRUE TRUE TRUE TRUE TRUE
## gam mi BayesTree e1071 randomForest
## TRUE TRUE TRUE TRUE TRUE
## Hmisc dplyr Amelia bartMachine knockoff
## TRUE TRUE TRUE TRUE TRUE
## caret smotefamily FNN
## TRUE TRUE TRUE
## [1] 4 8 1 7 56 6 21 60 63 17
## Levels: 4 8 1 7 56 6 21 60 63 17 19 43 61 2 32
## missForest iteration 1 in progress...done!
## missForest iteration 1 in progress...done!
## missForest iteration 1 in progress...done!
## missForest iteration 1 in progress...done!
## Confusion Matrix and Statistics
##
## Reference
## Prediction AD MCI Normal
## AD 69 17 1
## MCI 12 243 8
## Normal 0 9 140
##
## Overall Statistics
##
## Accuracy : 0.9058
## 95% CI : (0.8767, 0.93)
## No Information Rate : 0.5391
## P-Value [Acc > NIR] : <2e-16
##
## Kappa : 0.8426
## Mcnemar's Test P-Value : 0.589
##
## Statistics by Class:
##
## Class: AD Class: MCI Class: Normal
## Sensitivity 0.8519 0.9033 0.9396
## Specificity 0.9569 0.9130 0.9743
## Pos Pred Value 0.7931 0.9240 0.9396
## Neg Pred Value 0.9709 0.8898 0.9743
## Prevalence 0.1623 0.5391 0.2986
## Detection Rate 0.1383 0.4870 0.2806
## Detection Prevalence 0.1743 0.5271 0.2986
## Balanced Accuracy 0.9044 0.9082 0.9569