modificando para que el chequeo de variables no sea en datashield, sea en local

.gitignore

+*.xlsx
+harmonized_data/*.csv

valid_variables_script.R

 rm(list=ls())
 
-setwd("C:/Users/Victor/Documents/TFG/r-analytics-master")
+dir_name <- readline("Introduce the name of the directory please: ")
+
+setwd(dir_name)
 
 source("required_folder_checker.R")
 source("argument_hasher.R")
 source("dependency_installer.R")
 
-# install.packages("https://cran.r-project.org/src/contrib/Archive/DSI/DSI_1.2.0.tar.gz", repos=NULL, type="source")
-# install.packages("https://cran.r-project.org/src/contrib/Archive/DSOpal/DSOpal_1.2.0.tar.gz", repos=NULL, type="source")
-# install.packages("https://cran.r-project.org/src/contrib/Archive/DSLite/DSLite_1.2.0.tar.gz", repos=NULL, type="source")
-# install.packages("https://cran.r-project.org/src/contrib/Archive/opalr/opalr_2.1.0.tar.gz", repos=NULL, type="source")
-
 
-dep_list = c("jsonlite", "stringr","DSI","DSOpal","DSLite", "fields", "metafor", "ggplot2", "gridExtra", "data.table", "dsBaseClient")
+dep_list = c("jsonlite", "stringr","DSI","DSOpal","DSLite", "fields", "metafor", "ggplot2", "gridExtra", "data.table", "dsBaseClient", "openxlsx")
 install_dependencies(dep_list)
 
-#,"DSI","DSOpal","DSLite"
 
-setwd("C:/Users/victor/Documents/TFG/r-analytics-master")
-source("connection_parameters.R")
-source("necessary_functions_connection.R")
 
+setwd(dir_name)
 
-setwd("C:/Users/Victor/Documents/TFG/r-analytics-master/harmonised_data")
+#source("connection_parameters.R")
+#source("necessary_functions_connection.R")
 
+codebook <- read.csv("harmon.csv" , sep = ";")
 
-ComAndRF <- data.frame(read.csv("Com&RF.csv", sep=","))[1:64,1:5]
-Complications <- data.frame(read.csv("Complications.csv", sep=";"))[1:20,1:5]
-Dates <-  data.frame(read.csv("Dates.csv", sep=";"))[1:12,1:5]
-Demographics <-  data.frame(read.csv("Demographics.csv", sep=";"))[1:9,1:5]
-Home_med <-  data.frame(read.csv("Home_med.csv", sep=";"))[1:13,1:5]
-Imaging_data <-  data.frame(read.csv("Imaging_data.csv", sep=";"))[1:11,1:5]
-Labo <-  data.frame(read.csv("Labo.csv", sep=";"))[1:143,1:5]
-SiAndSympt <-  data.frame(read.csv("Si&Sympt.csv", sep=";"))[1:50,1:5]
-Treatment <-  data.frame(read.csv("Treatment.csv", sep=";"))[1:32,1:5]
-LifestyleAndDiet <-  data.frame(read.csv("Lifestyle&Diet.csv", sep=";"))[1:165,1:5]
+codebook_col_names <- as.data.frame(codebook$Harmonised.variable.name)
 
+names(codebook_col_names) <- c("col_names")
 
+setwd(paste(dir_name ,"/harmonized_data", sep=""))
 
-harmonised_data <- rbind(SiAndSympt,ComAndRF)
-harmonised_data <- rbind(harmonised_data,Treatment)
-harmonised_data <- rbind(harmonised_data,Dates)
-harmonised_data <- rbind(harmonised_data,Demographics)
-harmonised_data <- rbind(harmonised_data,Home_med)
-harmonised_data <- rbind(harmonised_data,Imaging_data)
-harmonised_data <- rbind(harmonised_data,Complications)
-harmonised_data <- rbind(harmonised_data,Labo)
-harmonised_data <- rbind(harmonised_data,LifestyleAndDiet)
+file_name <- readline("Introduce the name of the file to check the values: ")
+harmonized_data <- ""
+
+if (grepl(".csv" , file_name , fixed = TRUE)){
+  harmonized_data <- read.csv(file_name)
+}else if (grepl(".xlsx" , file_name , fixed = TRUE)){
+  harmonized_data <- read.xlsx(file_name)
+}
 
-rm(list=c("SiAndSympt",
-          "Complications",
-          "ComAndRF",
-          "Dates",
-          "Demographics",
-          "Home_med",
-          "Imaging_data",
-          "Complications",
-          "Labo",
-          "LifestyleAndDiet"))
 
 categoric_vars = c("DMRGENDR", "DMRBORN", "DMRRETH1", "DMROCCU", "DMRHREDU", "DSXOS", "DSXHO", "DSXIC", "TRXAV","TRXRIB","TRXLR","TRXRM","TRXIA","TRXIB","TRXCH","TRXAB","TRXCS","TRXHEP","TRXAF","TRXCP","TRXOT","TRXECM","TRXIV","TRXNIV","TRXNO","TRXOX","TRXRR","TRXTR","TRXVA","TRXPE","TRXPV","TRXIT","TRXNMB","TRXAC","TRXINA","TRXIS","TRXIM","TRXVC","TRXVD","TRXZN",                         "CSXCOT","CSXCTR","SMXASAH","SMXFEA","SMXCOA","SMXSTA","SMXSBA","SMXRNA","SMXMYA","SMXARA","SMXCPA","SMXAPA","SMXINA","SMXNAA","SMXDIA","SMXFAA","SMXHEA","SMXCNA","SMXACA","SMXSLA","SMXTLA","SMXSYA","SMXWHA","SMXLYA","SMXANA","SMXIWA","SMXSRA","SMXBLA","CMXPRG","CMXCVD","CMXCMP","CMXHT","CMXDI","CMXCKD","CMXCLD","CMXCPD","CMXASM","CMXCND","CMXRHE","CMXCCI","CMXCBD","CMXDE","CMXPU","CMXST","CMXLY","CMXAP","RFXSM","RFXFSM","RFXOB","RFXTB","RFXIMD","RFXHIV","RFXAIDS","RFXUI","RFXHC","RFXONC","RFXMN",                         "HMRACI","HMRARB","HMRAHO","HMRNS","HMROS","HMRCS","HMRIS","HMRAV","HMRAB","HMRCOV","IMDXCT","IMDXCTCR","IMDXCTTE","IMDXCTAB","IMDXXR","IMDXPN",                         "COXRD","COXAR","COXPM","COXMOD","COXPT","COXEC","COXSH","COXIO","COXPE","COXST","COXDIC","COXRIO","COXKF","COXHF","COXBC")
 
@@ -65,50 +43,38 @@ categoric_vars = c("DMRGENDR", "DMRBORN", "DMRRETH1", "DMROCCU", "DMRHREDU", "DS
 #----------------------------------------------------------------------------
 
 #Test if column names are valid
-check_column_names <- function(x){
+check_column_names <- function(col_names){
   
   str_res <- "The column names:"
-  
-  for(i in 1:(nrow(data_colnames))){
-    if(!check_valid_name(data_colnames[i,1])){
-      str_res<- paste(str_res, data_colnames[i,1], sep=" ")
+  valid_colnames <- c()
+  for(i in 1:(nrow(col_names))){
+    col_name <- col_names[i,1]
+    if(!check_valid_name(col_name)){
+      str_res<- paste(str_res, col_name, sep=" ")
+    }else{
+      valid_colnames = c(valid_colnames, col_name)
     }
   }
   
   str_res<- paste(str_res,"are not registered in the harmonized data codebook \n", sep=" ")
   
-  return (str_res)
+  new_list <- list("not_colnames" = str_res , "colnames" = valid_colnames)
+  return (new_list)
   
 }
 
 #Test if a single variable name is valid
-check_valid_name <- function(x){
+check_valid_name <- function(col_name){
   
   valid <- FALSE
   
-  aux <- as.data.frame(strsplit(x , split = "_"))
-  
-  if(aux[1,1] %in% harmonised_data$Harmonised.variable.name)
+  if(col_name %in% codebook_col_names$col_names)
     valid <- TRUE
   
   return (valid)
   
 }
 
-valid_data_colnames <- function(x){
-  
-  valid_colnames = c()
-  
-  for(i in  1:(nrow(data_colnames))){
-    if(check_valid_name(data_colnames[i,1])){
-      valid_colnames = c(valid_colnames,data_colnames[i,1])
-    }
-  }
-  
-  
-  return(valid_colnames)
-}
-
 remove_space <- function(x){
   searchString <- ' '
   replacementString <- ''
@@ -219,7 +185,7 @@ possible_values <- function(x){
   
   else{
     
-    possible_value <- subset(harmonised_data,harmonised_data$Harmonised.variable.name==x)[1,5]
+    possible_value <- subset(harmonized_data,harmonized_data$harmonized.variable.name==x)[1,5]
     res <- strsplit(x=possible_value,split="/")
   }
   
@@ -228,7 +194,7 @@ possible_values <- function(x){
 
 possible_values_categoric <- function(x){
   
-  possible_value <- subset(harmonised_data,harmonised_data$Harmonised.variable.name==x)[1,4]
+  possible_value <- subset(harmonized_data,harmonized_data$harmonized.variable.name==x)[1,4]
   res <- strsplit(x=possible_value,split="/")
   
   return(as.data.frame(res))
@@ -254,7 +220,7 @@ check_values_categoric <- function(values, colname){
 
 get_values_from_quantiles <- function(x){
   
-  data_summary <- ds.summary(x)
+  data_summary <- summary(x)
   
   low_quantile <- data_summary[[1]][3][[1]][[1]]
   
@@ -357,7 +323,7 @@ error_message <- function(colname, invalid_values){
   else
     new_colname <- colname
   
-  range <- subset(harmonised_data, harmonised_data$Harmonised.variable.name == new_colname)
+  range <- subset(harmonized_data, harmonized_data$harmonized.variable.name == new_colname)
   range <- range[5]
   range <- as.data.frame(strsplit(range[1,1], '/'))
   
@@ -435,7 +401,7 @@ check_valid_values <- function(){
           print("Unable to analyse data")
           res <- FALSE
         },
-        data_table <- as.data.frame(ds.table(column))
+        data_table <- as.data.frame(table(column))
       )
       
       if(data_table == "empty"){
@@ -475,7 +441,6 @@ check_valid_values <- function(){
             k <- k+1
           }
           
-          # if((!is_numeric & !has_numeric) | is_numeric)
         }else{
           
           if(grepl("numeric", valid_colnames[i,1],fixed=TRUE))
@@ -492,11 +457,7 @@ check_valid_values <- function(){
           }
           
           
-          #print(valid_colnames[i,1])
-          #print(values)
-          
-        }#else
-        # print("This variable has a numeric version")
+        }
       }
       
       
@@ -536,56 +497,32 @@ notify_unable_analyse <- function(x){
   
 }
 
-auxConnections <- connect()
-connections <- auxConnections[[1]]
-inp <- auxConnections[[2]]
-
-#Conexión a la base de datos
-
-ds.dim("data", datasources = connections)
-ds.colnames("data")
-
-#----------------------------------------------------------------------------
-
-#Check valid column names
-datastructure_name <- "data"
-data_colnames <- ds.colnames(x=datastructure_name, datasources= connections)
-
-data_colnames <- as.data.frame(data_colnames)
+data_colnames <- as.data.frame(colnames(harmonized_data))
 
 check_valid_columns <- check_column_names(data_colnames)
 
-valid_colnames <- as.data.frame(valid_data_colnames(data_colnames))
+columns_not_valid <- check_valid_columns$not_colnames
 
+valid_colnames <- as.data.frame(check_valid_columns$colnames)
+names(valid_colnames) = c("valid_colnames")
 
 
-#possible_values("CSXCTR")
 result <- ""
 result<-check_valid_values()
 print(check_valid_columns)
-datashield.logout(connections) 
+#datashield.logout(connections) 
 cat(result)
 
 
 
-# ds.dataFrameSubset(df.name = "data", V1.name = "data$DMXWT", "400" , Boolean.operator = '>', newobj = "columna")
-# # 
-# ds.summary("columna$DMXWT")
-# ds.dim("columna$DMXWT")
-# ds.table("columna$DMXWT")
-
 file_name<- paste(hospital_name,"_invalid_values.txt", sep="")
 
-#ds.heatmapPlot("data$LBDSALSIA", "data$RFXHC_numeric",type="combine", datasources = connections)
-
 
-#setwd("C:/Users/victor/Desktop/TFG/r-analytics-master/invalid_values")
 dir.create("../invalid_values", showWarnings = FALSE)
 setwd("../invalid_values")
 
-
 cat(check_valid_columns,file=file_name,sep="\n")
 cat(result,file=file_name,append=TRUE)
 
-datashield.logout(connections) 
+#datashield.logout(connections)