path.lib <- "none" # absolute path of the library folder. Write "none" if not required
path.in <- "Z:/rogge12231/rogge_12231_1550514780/" # absolute path of the data folder
path.in <- "Z:/rogge12231/attempt_using_v3/rogge_12231_1550913367/" # absolute path of the data folder
path.out <- "C:/Users/Gael/Desktop/" # absolute path of the output folder
path.function1 <- "C:/Users/Gael/Documents/Git_versions_to_use/cute_little_R_functions-v4.5.0/cute_little_R_functions.R" # Define the absolute pathway of the folder containing functions created by Gael Millot
@@ -10,7 +10,7 @@ erase.graphs <- TRUE # write TRUE to erase all the graphic windows in R before s
################################ End Initialization
sink(stdout(),type="message")
sink(stdout(),type="message")# redirect messages to standart output
script<-commandArgs(trailingOnly=FALSE)[4]# recover script name, e.g., r_341_conf $check_lod_gael_conf. 1) .exe R path, 2) --slave, 3) --no-restore, 4) --file and 5) --args
args<-commandArgs(trailingOnly=TRUE)# recover arguments written after the call of the Rscript, ie after r_341_conf $check_lod_gael_conf
tempo.arg.names<-c("path.lib","path.in","path.out","path.function1","file.name1","ml.bootstrap.nb","project.name","label.size","optional.text","slurm.loop.nb","analysis.kind","cross.valid.ratio","random.seed")# objects names exactly in the same order as in the bash code and recovered in args
...
...
@@ -60,7 +60,7 @@ project.name <-"rogge12231"
path.lib <- "/pasteur/homes/gmillot/softwares/R/x86_64-pc-linux-gnu-library/3.5/" # absolute path of the library folder. Write "none" if not required
path.in <- "/pasteur/homes/gmillot/rogge12231/" # absolute path of the data folder
path.out <- "/pasteur/homes/gmillot/rogge12231/" # absolute path of the output folder
path.function1 <- "/pasteur/homes/gmillot/Git_versions_to_use/cute_little_R_functions-v4.4.0/cute_little_R_functions.R" # Define the absolute pathway of the folder containing functions created by Gael Millot
path.function1 <- "/pasteur/homes/gmillot/Git_versions_to_use/cute_little_R_functions-v4.5.0/cute_little_R_functions.R" # Define the absolute pathway of the folder containing functions created by Gael Millot
file.name1 <- "supplementary_data_file_test.csv" # name of the data file to import in path.in
ml.bootstrap.nb <- 3
label.size <- 6
...
...
@@ -84,17 +84,17 @@ path.in <- "C:/Users/Gael/Documents/Hub projects/20190126 Las Rogge 12231/" # ab
path.out <- "C:/Users/Gael/Desktop/" # absolute path of the output folder
# path.function1 <- "C:/Users/Gael/Documents/Git_versions_to_use/cute_little_R_functions-v4.5.0/cute_little_R_functions.R" # Define the absolute pathway of the folder containing functions created by Gael Millot
file.name1 <- "supplementary_data_file_test.csv" # name of the data file to import in path.in
# file.name1 <- "supplementary_data_file.csv" # name of the data file to import in path.in
# * **COMMENT_VR**: Once a method of selecting genes as been defined, it could be interesting to display the variable importance attached to each of these 25 genes once a unique RF model has been trained on the entire training dataset (67 patients). It could help to get a sense of the main drivers (Example Below).
stop(paste0("\n\n============\n\nERROR: LOOP ",slurm.loop.nb," CANNOT FIND THE ",paste0(path.loop1,"loop1_discov_data.RData")," FILE\nDUE TO UNACTIVE BLOCKAGE OF THE LOOP 1 IN THE workflow.sh\n\n============\n\n"))
...
...
@@ -576,7 +583,17 @@ fun_export_data(path = path.out, data = "################################ VALIDA
# Now that the features of interest are selected, we can train the final models on the whole discovery set.
#
# ```{r train, warning=FALSE}
# ```{r train, warning=FALSE} #### 20190313 checked compared to ReproducibleCode_20190109.Rmd
if(random.seed==TRUE){
used.set.seed2<-sample(x=0:(2^31-1),size=1)
}else{
used.set.seed2<-1
cat(paste0("\n\n================\n\nBEWARE: NON RANDOM set.seed(1) FUNCTION ACTIVATED \n\n================\n\n"))