## ----WoSCompare_libs, message=FALSE--------------------------------------
library(data.table)
library(ggplot2)


## ----WoSCompare_read, message=FALSE--------------------------------------
# Read all lines into a vector:
rawData <- readLines("Data/WoS/WoS_DS.txt")
# Remove first line of that vector:
rawData <- rawData[-1]
# Remove last two lines of that vector:
rawData <- head(rawData,-2)
# Use it to create a data frame:
DSData <- read.table(textConnection(rawData),sep = "",
                     col.names = c("Year","Counts","Percent")) 
DSData


## ----WoSCompare_readFunction---------------------------------------------
readFile <- function(file,colName) {
  rawData <- readLines(file)
  rawData <- rawData[-1]
  rawData <- head(rawData,-2)
  data <- read.table(textConnection(rawData),sep = "",
                     col.names = c("Year",colName,"Percent")) 
  data$Percent <- NULL
  return(data)
}


## ----WoSCompare_testReadFunction-----------------------------------------
AIData <- readFile("Data/WoS/WoS_AI.txt","Artificial Intelligence") 
DLData <- readFile("Data/WoS/WoS_DL.txt","Deep Learning") 
DMData <- readFile("Data/WoS/WoS_DM.txt","Data Mining") 
DSData <- readFile("Data/WoS/WoS_DS.txt","Data Science") 
ESData <- readFile("Data/WoS/WoS_ES.txt","Expert Systems") 
MLData <- readFile("Data/WoS/WoS_ML.txt","Machine Learning") 
NNData <- readFile("Data/WoS/WoS_NN.txt","Neural Networks") 


## ----WoSCompare_merge----------------------------------------------------
allData <- Reduce(function(dtf1, dtf2) 
                  merge(dtf1,dtf2,by="Year",all=TRUE),
                  list(AIData,DLData,DMData,DSData,ESData,MLData,NNData))
head(allData)


## ----WoSCompare_cleanNAs-------------------------------------------------
allData[is.na(allData)] <- 0
str(allData)


## ----WoSCompare_restrictYears--------------------------------------------
allData <- allData[allData$Year >= 1980, ]
allData <- allData[allData$Year < 2019, ]


## ----WoSCompare_plot, fig.width=12,fig.height=6--------------------------
# Melt the data in the proper format, with specific column names.
melted <- melt(allData,id="Year")
colnames(melted) <- c("Year","Term","Count")
# Set the thickness depending on the term.
melted$thickness <- 1
melted$thickness[melted$Term=="Data.Science"] <- 3
# Plot it with style!
ggplot(melted,aes(x=Year,y=Count,colour=Term,group=Term,size=thickness)) + 
  geom_line()+
  scale_size(range = c(1,3), guide="none")+
  scale_x_continuous("Year",breaks=seq(1980,2018,2))+
  guides(colour = guide_legend(override.aes = list(size=3)))+
  ggtitle("Terms' Count")+
  theme(axis.title=element_text(size=14),
        axis.text.x=element_text(size=11,angle=-90,vjust=0.5,hjust=1),
        axis.text.y=element_text(size=12),
        legend.title=element_text(size=14), 
        legend.text=element_text(size=12),
        plot.title=element_text(size=22))