|
0
|
1 args <- commandArgs(T)
|
|
|
2
|
|
|
3 arg1 <- args[1]
|
|
|
4 arg2 <- args[2]
|
|
|
5 arg3 <- args[3]
|
|
|
6 arg4 <- args[4]
|
|
|
7 arg5 <- args[5]
|
|
|
8 arg6 <- args[6]
|
|
|
9 arg7 <- args[7]
|
|
|
10
|
|
|
11 library(caret)
|
|
|
12 load(arg1)
|
|
|
13 RAWDATA <- dataX
|
|
|
14 RAWDATA$outcome <- dataY
|
|
|
15 rawData <- dataX
|
|
|
16 predictorNames <- names(rawData)
|
|
|
17
|
|
|
18 isNum <- apply(rawData[,predictorNames, drop = FALSE], 2, is.numeric)
|
|
|
19 if(any(!isNum)) stop("all predictors in rawData should be numeric")
|
|
|
20
|
|
|
21 colRate <- apply(rawData[, predictorNames, drop = FALSE],
|
|
|
22 2, function(x) mean(is.na(x)))
|
|
|
23 colExclude <- colRate > 0.001
|
|
|
24 if(any(colExclude)){
|
|
|
25 predictorNames <- predictorNames[!colExclude]
|
|
|
26 rawData <- rawData[, predictorNames]
|
|
|
27 rowRate <- apply(rawData[, predictorNames, drop = FALSE],
|
|
|
28 1, function(x) mean(is.na(x)))
|
|
|
29 }
|
|
|
30
|
|
|
31 rowExclude <- rowRate > 0.001
|
|
|
32 if(any(rowExclude)){
|
|
|
33 rawData <- rawData[!rowExclude, ]
|
|
|
34 hasMissing <- apply(rawData[, predictorNames, drop = FALSE],
|
|
|
35 1, function(x) mean(is.na(x)))
|
|
|
36
|
|
|
37 } else { hasMissing <- apply(rawData[, predictorNames, drop = FALSE],
|
|
|
38 1, function(x) any(is.na(x)))
|
|
|
39
|
|
|
40 rawData <- rawData[complete.cases(rawData),]
|
|
|
41 }
|
|
|
42
|
|
|
43 set.seed(2)
|
|
|
44
|
|
|
45 nzv <- nearZeroVar(rawData)
|
|
|
46 if(length(nzv) > 0) {
|
|
|
47 nzvVars <- names(rawData)[nzv]
|
|
|
48 rawData <- rawData[,-nzv]
|
|
|
49 rawData$outcome <- dataY
|
|
|
50 } else {
|
|
|
51 rawData <- rawData
|
|
|
52 rawData$outcome <- dataY
|
|
|
53 }
|
|
|
54
|
|
|
55 predictorNames <- names(rawData)[names(rawData) != "outcome"]
|
|
|
56
|
|
|
57 dx <- rawData[,1:length(rawData)-1]
|
|
|
58 dy <- rawData[,length(rawData)]
|
|
|
59 corrThresh <- 0.90
|
|
|
60 highCorr <- findCorrelation(cor(dx, use = "pairwise.complete.obs"),corrThresh)
|
|
|
61 dx <- dx[, -highCorr]
|
|
|
62 subsets <- seq(1,length(dx),by=2)
|
|
|
63 normalization <- preProcess(dx)
|
|
|
64 dx <- predict(normalization, dx)
|
|
|
65 dx <- as.data.frame(dx)
|
|
|
66
|
|
|
67 if (arg4 == "lmFuncs"){
|
|
|
68 ctrl1 <- rfeControl(functions = lmFuncs,
|
|
|
69 method = arg5 ,
|
|
|
70 repeats = as.numeric(arg6),
|
|
|
71 number = as.numeric(arg7),
|
|
|
72 verbose = FALSE)
|
|
|
73 } else if(arg4 == "rfFuncs"){
|
|
|
74 ctrl1 <- rfeControl(functions = rfFuncs,
|
|
|
75 method = arg5 ,
|
|
|
76 repeats = as.numeric(arg6),
|
|
|
77 number = as.numeric(arg7),
|
|
|
78 verbose = FALSE)
|
|
|
79 }else if (arg4 == "treebagFuncs"){
|
|
|
80 ctrl1 <- rfeControl(functions = treebagFuncs,
|
|
|
81 method = arg5 ,
|
|
|
82 repeats = as.numeric(arg6),
|
|
|
83 number = as.numeric(arg7),
|
|
|
84 verbose = FALSE)
|
|
|
85 }else {
|
|
|
86
|
|
|
87 ctrl1 <- rfeControl(functions = nbFuncs,
|
|
|
88 method = arg5 ,
|
|
|
89 repeats = as.numeric(arg6),
|
|
|
90 number = as.numeric(arg7),
|
|
|
91 verbose = FALSE)
|
|
|
92 }
|
|
|
93
|
|
|
94
|
|
|
95
|
|
|
96
|
|
|
97 Profile <- rfe(dx, dy,
|
|
|
98 sizes = subsets,
|
|
|
99 rfeControl = ctrl1)
|
|
|
100
|
|
|
101 pred11 <- predictors(Profile)
|
|
|
102 save(Profile,file=arg2)
|
|
|
103 rawData <- RAWDATA[,pred11]
|
|
|
104 rawData$outcome <- RAWDATA$outcome
|
|
|
105 dataX <- rawData[,1:length(rawData)-1]
|
|
|
106 dataY <- rawData[,length(rawData)]
|
|
|
107 save(dataX,dataY,file=arg3)
|
|
|
108 rm(dataX)
|
|
|
109 rm(dataY)
|
|
|
110
|
