## ----CAP394_books_libs, message=FALSE------------------------------------
library(data.table)
library(ggplot2)


## ----CAP394_books_readdata1----------------------------------------------
data <- read.csv("Data/OldPubs/libgenbooks.csv", header = TRUE,stringsAsFactors=FALSE)


## ----CAP394_books_readdata2----------------------------------------------
str(data)


## ----CAP394_books_count1-------------------------------------------------
filteredDS <- data[grep("Data Science", data$Title,ignore.case=TRUE), ]
nrow(filteredDS)


## ----CAP394_books_count2-------------------------------------------------
filteredDM <- data[grep("Data Mining", data$Title,ignore.case=TRUE), ]
nrow(filteredDM)


## ----CAP394_books_count3-------------------------------------------------
filteredBD <- data[grep("Big Data", data$Title,ignore.case=TRUE), ]
nrow(filteredBD)


## ----CAP394_books_count4-------------------------------------------------
filteredAI <- data[grep("Artificial Intelligence", data$Title,ignore.case=TRUE), ]
nrow(filteredAI)


## ----CAP394_books_count5-------------------------------------------------
filteredNN <- data[grep("Neural Network", data$Title,ignore.case=TRUE), ]
nrow(filteredNN)


## ----CAP394_books_count6-------------------------------------------------
filteredML <- data[grep("Machine Learning", data$Title,ignore.case=TRUE), ]
nrow(filteredML)


## ----CAP394_books_table--------------------------------------------------
table(filteredDS$Year)


## ----CAP394_books_tables-------------------------------------------------
DSFrequency <- as.data.frame(table(filteredDS$Year))
names(DSFrequency) <- c("Year","Data Science")
DSFrequency$Year <- as.numeric(levels(DSFrequency$Year))[DSFrequency$Year]
DSFrequency


## ----CAP394_books_tablesasdf---------------------------------------------
DMFrequency <- as.data.frame(table(filteredDM$Year))
names(DMFrequency) <- c("Year","Data Mining")
DMFrequency$Year <- as.numeric(levels(DMFrequency$Year))[DMFrequency$Year]
BDFrequency <- as.data.frame(table(filteredBD$Year))
names(BDFrequency) <- c("Year","Big Data")
BDFrequency$Year <- as.numeric(levels(BDFrequency$Year))[BDFrequency$Year]
AIFrequency <- as.data.frame(table(filteredAI$Year))
names(AIFrequency) <- c("Year","Artificial Intelligence")
AIFrequency$Year <- as.numeric(levels(AIFrequency$Year))[AIFrequency$Year]
NNFrequency <- as.data.frame(table(filteredNN$Year))
names(NNFrequency) <- c("Year","Neural Networks")
NNFrequency$Year <- as.numeric(levels(NNFrequency$Year))[NNFrequency$Year]
MLFrequency <- as.data.frame(table(filteredML$Year))
names(MLFrequency) <- c("Year","Machine Learning")
MLFrequency$Year <- as.numeric(levels(MLFrequency$Year))[MLFrequency$Year]


## ----CAP394_books_mergedtables-------------------------------------------
all <- Reduce(function(dtf1, dtf2) 
             merge(dtf1,dtf2,by="Year",all=TRUE),
             list(DSFrequency,DMFrequency,BDFrequency,AIFrequency,NNFrequency,MLFrequency))
head(all)


## ----CAP394_books_fixedtables1-------------------------------------------
all[is.na(all)] <- 0
str(all)


## ----CAP394_books_fixedtables2-------------------------------------------
all <- all[all$Year >= 1980, ]
all <- all[all$Year < 2018, ]


## ----CAP394_books_plot, fig.width=12,fig.height=6------------------------
melted <- melt(all,id="Year")
colnames(melted) <- c("Year", "Keyword","Count")
melted$thickness <- 1
melted$thickness[melted$Keyword=="Data Science"] <- 3
head(melted)
ggplot(melted,aes(x=Year,y=Count,colour=Keyword,group=Keyword,size=thickness)) + 
  geom_line()+
  scale_size(range = c(1,3), guide="none")+
  scale_x_continuous("Year", breaks=seq(1980,2017,2))+
  guides(colour = guide_legend(override.aes = list(size=3)))+
  ggtitle("Books")+
  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))