TRID Ana 2

1 Explore

1.1 General

library(readxl)
library(DT)
library(dplyr)
library(reshape2)
library(data.table)

setwd("C:/Users/s-das/Syncplicity Folders/MyProjects_IMP/MY_Papers_V2/TRB 2021/00_Topics/XML")

dat1 <- read_excel("Das_032020.xlsx", sheet="fin00")
dat2 <- dat1[,c("title", "abstract", "year", "serial", "publisher")]
dat2a <- dat2[!duplicated(dat2[,c(1:5)]),]

dat2a$non_na <- 3- apply(dat2a, 1, function(x) sum(is.na(x)))

# use aggregate to create new data frame with the maxima
dat2b <- aggregate(non_na ~ title, dat2a, max)
# then simply merge with the original
dat2c  <- merge(dat2b, dat2a)


dat4 <- dat1[,c("title", "term", "subject_area", "author")]
dat4a <- dat4[!duplicated(dat4[,c(1:4)]),]
dat5 = melt(dat4a, id.vars = c("title" ))
dat6 = dat5[complete.cases(dat5), ]
dat7= dat6 %>% group_by(title, variable) %>% mutate(rowind = row_number())
dat2e <- dat1[,c("title", "year")][complete.cases(dat1[,c("title", "year")]), ][!duplicated(dat1[,c("title", "year")][complete.cases(dat1[,c("title", "year")]), ][,c(1:2)]),]
dat8= left_join(dat7, dat2e, by="title")
dat8a= subset(dat8, variable=="term")
datatable(dat8a)

library(tidyr)
dat9 <- dat8a[,c("value", "year")] %>% group_by(value, year) %>% summarise(count = n()) %>%
  spread(year, count)
dat9[is.na(dat9)] <- 0 
dim(dat9)

## [1] 263  10

dat9$WordCount=rowSums(dat9[,c(2:10)])
datatable(dat9, extensions = c('Scroller', 'FixedColumns'), options = list(
  deferRender = TRUE,
  scrollY = TRUE,
  scrollX = TRUE,
  fixedColumns = list(leftColumns = 2, rightColumns = 1)
))

dat8a= subset(dat8, variable=="author")
datatable(dat8a)

dat9 <- dat8a[,c("value", "rowind")] %>% group_by(value, rowind) %>% summarise(count = n()) %>%
  spread(rowind, count)
dat9[is.na(dat9)] <- 0 
datatable(dat9)

datatable(dat2c)