R scripts adapted to new date format

Rscripts/Process_CT_for_Gargantext.Rmd

@@ -13,15 +13,16 @@ First define what is the name of the file to be processed. This file should be i
 ```{r}
 library(lubridate)
 source("coronalib.R") # R libraries 
-name<-"Database060520" # name of the csv to be loaded
+name<-"database_d_chavalarias_2020-05-15" # name of the csv to be loaded
 
 AllData <-read.csv(paste("data/",name,".csv",sep=""),head=TRUE,sep="\t")
 AllData$Inclusion.criteria <- NULL
 AllData$Exclusion.criteria <- NULL
-#AllData <- filter(AllDataTemp,AllDataTemp$First.author!="N/A")
+AllData <- filter(AllData,!is.na(AllData$Registration.date))
 nrow(AllData)
 x <- unique(AllData$Trial.registration.number)
 head(x)[[1]]
+
 ```
 ### Data segmentation
 Several dataframe are generated according to which are the CTs under study.
@@ -75,5 +76,3 @@ TreatmentsCloud(Prevention)
 TreatmentsCloud(Posttreatment)
 
 ```
-
-

Rscripts/coronalib.R

@@ -4,9 +4,9 @@
 
 ### abstract as html file as in template merging treatments and outcome
 garg_export_with_html <- function(df,filename) {
-  x <- data.frame("publication_day"=day(as.Date(df$Registration.date,"%Y-%m-%d")))
-  x$publication_month = month(as.Date(df$Registration.date,"%Y-%m-%d"))
-  x$publication_year = year(as.Date(df$Registration.date,"%Y-%m-%d"))
+  x <- data.frame("publication_day"=day(as.Date(df$Registration.date,"%d/%m/%Y")))
+  x$publication_month = month(as.Date(df$Registration.date,"%d/%m/%Y"))
+  x$publication_year = year(as.Date(df$Registration.date,"%d/%m/%Y"))
   x$authors=df$First.author
   x$title=df$Trial.registration.number
   x$source=df$Funding
@@ -16,61 +16,64 @@ garg_export_with_html <- function(df,filename) {
 }
 
 garg_export_treatments_with_html <- function(df,filename) {
-  x <- data.frame("publication_day"=day(as.Date(df$Registration.date,"%Y-%m-%d")))
-  x$publication_month = month(as.Date(df$Registration.date,"%Y-%m-%d"))
-  x$publication_year = year(as.Date(df$Registration.date,"%Y-%m-%d"))
+  x <- data.frame("publication_day"=day(as.Date(df$Registration.date,"%d/%m/%Y")))
+  x$publication_month = month(as.Date(df$Registration.date,"%d/%m/%Y"))
+  x$publication_year = year(as.Date(df$Registration.date,"%d/%m/%Y"))
   x$authors=df$First.author
   x$title=df$Trial.registration.number
   x$source=df$Funding
   x$abstract=paste("<a href='",df$Full.text.link,"' target='blank'>Link to study</a></br></br><b> ",toupper(df$Pharmacological.treatment),"</b></br><i>Type: </i>",df$Treatment.type,"</br><i> Treatment name: </i>",str_replace_all(tolower(df$Treatment.name),"[[+]]"," + "))
-  write.table(x, file = paste("output/gargCSV_Treatments_html_",filename,".csv",sep = ""), sep = "\t",row.names = FALSE)
+  y <- filter(x,x$publication_year!="NA")  
+  write.table(y, file = paste("output/gargCSV_Treatments_html_",filename,".csv",sep = ""), sep = "\t",row.names = FALSE)
 }
 
 garg_export_raw_treatments<- function(df,filename) {
-  x <- data.frame("publication_day"=day(as.Date(df$Registration.date,"%Y-%m-%d")))
-  x$publication_month = month(as.Date(df$Registration.date,"%Y-%m-%d"))
-  x$publication_year = year(as.Date(df$Registration.date,"%Y-%m-%d"))
+  x <- data.frame("publication_day"=day(as.Date(df$Registration.date,"%d/%m/%Y")))
+  x$publication_month = month(as.Date(df$Registration.date,"%d/%m/%Y"))
+  x$publication_year = year(as.Date(df$Registration.date,"%d/%m/%Y"))
   x$authors=df$First.author
   x$title=df$Trial.registration.number
   x$source=df$Funding
   x$abstract=paste(toupper(df$Pharmacological.treatment)," . ",df$Treatment.type," . ",str_replace_all(tolower(df$Treatment.name),"[[+]]"," ; "))
-  write.table(x, file = paste("output/gargCSV_Treatments_raw_",filename,".csv",sep = ""), sep = "\t",row.names = FALSE)
+  y <- filter(x,x$publication_year!="NA")
+  write.table(y, file = paste("output/gargCSV_Treatments_raw_",filename,".csv",sep = ""), sep = "\t",row.names = FALSE)
 }
 
 
 garg_export_all_plain <- function(df,filename) {
-  x <- data.frame("publication_day"=day(as.Date(df$Registration.date,"%Y-%m-%d")))
-  x$publication_month = month(as.Date(df$Registration.date,"%Y-%m-%d"))
-  x$publication_year = year(as.Date(df$Registration.date,"%Y-%m-%d"))
+  x <- data.frame("publication_day"=day(as.Date(df$Registration.date,"%d/%m/%Y")))
+  x$publication_month = month(as.Date(df$Registration.date,"%d/%m/%Y"))
+  x$publication_year = year(as.Date(df$Registration.date,"%d/%m/%Y"))
   x$authors=df$First.author
   x$title=df$Trial.registration.number
   x$source=df$Funding
   x$abstract=paste("Link to study: ",df$Full.text.link," DESIGN: ",df$Study.design,", RECRUITEMENT STATUS: ",df$Recruitment.status,", TYPE OF PATIENTS: ",df$Type.of.patients," TREATMENT: ",toupper(df$Pharmacological.treatment),", TYPE: ",df$Treatment.type,", TREATMENT NAME: ",str_replace_all(tolower(df$Treatment.name),"[[+]]"," + "),", PRIMARY OUTCOME: ",df$primary.outcome,", CENTER: ",df$Center,", COUNTRY: ",df$Countries,", N in this treatment group: ",df$n.randomized.in.this.arm,", N in the trial: ",df$Total.sample.size)
-  
-  write.table(x, file = paste("output/gargCSV_all_plain_",filename,".csv",sep = ""), sep = "\t",row.names = FALSE)
+  y <- filter(x,x$publication_year!="NA")
+  write.table(y, file = paste("output/gargCSV_all_plain_",filename,".csv",sep = ""), sep = "\t",row.names = FALSE)
 }
 
 garg_export_OnlyTreatments <- function(df,filename) {
-  x <- data.frame("publication_day"=day(as.Date(df$Registration.date,"%Y-%m-%d")))
-  x$publication_month = month(as.Date(df$Registration.date,"%Y-%m-%d"))
-  x$publication_year = year(as.Date(df$Registration.date,"%Y-%m-%d"))
+  x <- data.frame("publication_day"=day(as.Date(df$Registration.date,"%d/%m/%Y")))
+  x$publication_month = month(as.Date(df$Registration.date,"%d/%m/%Y"))
+  x$publication_year = year(as.Date(df$Registration.date,"%d/%m/%Y"))
   x$authors=df$Full.text.link
   x$title=df$Trial.registration.number
   x$source=df$Funding
   x$abstract=paste(" TREATMENT: ",toupper(df$Pharmacological.treatment),", TYPE: ",df$Treatment.type,", TREATMENT NAME: ",str_replace_all(tolower(df$Treatment.name),"[[+]]"," + "))
-  
-  write.table(x, file = paste("output/gargCSV_only_treatment_plain",filename,".csv",sep = ""), sep = "\t",row.names = FALSE)
+  y <- filter(x,x$publication_year!="NA")
+  write.table(y, file = paste("output/gargCSV_only_treatment_plain",filename,".csv",sep = ""), sep = "\t",row.names = FALSE)
 }
 
 garg_export_OnlyOutcomes <- function(df,filename) {
-  x <- data.frame("publication_day"=day(as.Date(df$Registration.date,"%Y-%m-%d")))
-  x$publication_month = month(as.Date(df$Registration.date,"%Y-%m-%d"))
-  x$publication_year = year(as.Date(df$Registration.date,"%Y-%m-%d"))
+  x <- data.frame("publication_day"=day(as.Date(df$Registration.date,"%d/%m/%Y")))
+  x$publication_month = month(as.Date(df$Registration.date,"%d/%m/%Y"))
+  x$publication_year = year(as.Date(df$Registration.date,"%d/%m/%Y"))
   x$authors=df$Full.text.link
   x$title=df$Trial.registration.number
   x$source=df$Funding
   x$abstract=paste("PRIMARY OUTCOME: ",df$primary.outcome)
-  write.table(x, file = paste("output/gargCSV_only_outcomes_plain",filename,".csv",sep = ""), sep = "\t",row.names = FALSE)
+  y <- filter(x,x$publication_year!="NA")
+  write.table(y, file = paste("output/gargCSV_only_outcomes_plain",filename,".csv",sep = ""), sep = "\t",row.names = FALSE)
 }
 
 # Export de listes de termes