Maria@70: library(rworldmap)
Maria@70: library(ggplot2)
Maria@70: 
Maria@70: PlotBarChart<- function(df, cat="Language", ordercat="REGION", mincount=10, legend=T, color_plt="Paired"){
Maria@70:   idx_cat = which(colnames(df)==cat)
Maria@70:   idx_ordercat = which(colnames(df)==ordercat)
Maria@70:   dfsub <- subset(df, df[,idx_cat]!="")
Maria@70:   dfsub <- dfsub[ dfsub[,idx_cat] %in%  names(table(dfsub[,idx_cat]))[table(dfsub[,idx_cat]) >mincount] , ]
Maria@70:   #dfsub <- dfsub[order(dfsub$REGION.y),]
Maria@70:   dfsub <- dfsub[order(dfsub[,idx_ordercat]),]
Maria@70:   dfsub[,idx_cat] <- factor(dfsub[,idx_cat], levels=unique(dfsub[,idx_cat]))
Maria@70:   g = ggplot(dfsub,aes(dfsub[,idx_cat], fill=dfsub[,idx_ordercat], order=-as.numeric(dfsub[,idx_ordercat])))+geom_bar()
Maria@70:   #g = g+ylim("0", "100")#+scale_y_discrete(breaks=c("100"),labels=c("100+"))
Maria@70:   g=g+scale_y_continuous(limits=c(0, 200), breaks=seq(0,200,40))
Maria@70:   g=g+scale_fill_brewer(palette=color_plt)
Maria@70:   g=g+theme(axis.text.x=element_text(angle=90,hjust=1,vjust=0.5))
Maria@70:   g=g+labs(y="Counts",x=cat)+coord_flip()+theme_bw()
Maria@70:   if (legend){
Maria@70:     g=g+guides(fill = guide_legend(title = ordercat))}
Maria@70:   else{
Maria@70:     g=g+guides(fill="none")
Maria@70:   }
Maria@70:   return(g)
Maria@70: }
Maria@70: 
Maria@70: PlotCountryNCounts <- function(df, mincount=10){
Maria@70:   countrycounts = table(df$Country)
Maria@70:   dd=data.frame(countrycounts)
Maria@70:   names(dd)=c("Country","Counts")
Maria@70:   cols <- rep(2, dim(dd)[1])
Maria@70:   cols[dd$Counts<mincount]=1
Maria@70:   dd$NCounts = cols
Maria@70:   spdf<-joinCountryData2Map(dd,joinCode="NAME",nameCountryColumn="Country",nameJoinColumn="Country")
Maria@70:   mapParams <- mapCountryData(spdf, nameColumnToPlot="NCounts",catMethod='categorical',missingCountryCol="grey",oceanCol="lightblue",colourPalette='heat', mapTitle=paste("Country sample size, n_recordings>",mincount),addLegend=F)
Maria@70:   mapParams$legendText <- c(paste('<',mincount),paste('>=',mincount),'na')  
Maria@70:   do.call(addMapLegendBoxes, c(mapParams,x='bottomleft'))
Maria@70: }
Maria@70: 
Maria@70: PlotCountryCounts <- function(df, output=F){
Maria@70:   countrycounts = table(df$Country)
Maria@70:   dd=data.frame(countrycounts)
Maria@70:   names(dd)=c("Country","Counts")
Maria@70:   spdf<-joinCountryData2Map(dd,joinCode="NAME",nameCountryColumn="Country",nameJoinColumn="Country")
Maria@70:   spdf<-spdf[-which(spdf$ADMIN=='Antarctica'),]
Maria@70:   #mapParams <- mapCountryData(spdf, nameColumnToPlot="Counts",catMethod=as.numeric(levels(as.factor(spdf$Counts))),missingCountryCol='grey',borderCol='black',oceanCol="white",colourPalette='heat', mapTitle="",addLegend=F)
Maria@70:   mapParams <- mapCountryData(spdf, nameColumnToPlot="Counts",catMethod=seq(10,100,10),missingCountryCol='grey',borderCol='black',oceanCol="white",colourPalette="heat", mapTitle="",addLegend=F)
Maria@70:   #do.call( addMapLegend, c(mapParams, labelFontSize=0.7, legendShrink=0.5,legendWidth=0.5, tcl=0.3, legendMar = 7, legendLabels="all",horizontal=T, legendIntervals="page"))
Maria@70:   legend("left", legend = c(paste(seq(90,1,-10),'-',seq(100,11,-10)), 'NA'), fill = c(heat.colors(9, alpha = 1), 'grey'), cex = 0.56, bty = "o",bg="white",box.lwd=0,box.col="white")
Maria@70:   if (output){
Maria@70:     pdf(file="countrycounts.pdf")
Maria@70:     mapParams <- mapCountryData(spdf, nameColumnToPlot="Counts",catMethod=seq(10,100,10),missingCountryCol='grey',borderCol='black',oceanCol="white",colourPalette="heat", mapTitle="",addLegend=F)
Maria@70:     #mapParams <- mapCountryData(spdf, nameColumnToPlot="Counts",catMethod=as.numeric(levels(as.factor(spdf$Counts))),missingCountryCol='grey',borderCol='black',oceanCol="lightblue",colourPalette='heat', mapTitle="",addLegend=F)
Maria@70:     #do.call( addMapLegend, c(mapParams, labelFontSize=0.7, legendShrink=0.5,legendWidth=0.5, tcl=0.3, legendMar = 7, legendLabels="all",horizontal=T, legendIntervals="page"))
Maria@70:     legend("left", legend = c(paste(seq(90,1,-10),'-',seq(100,11,-10)), 'NA'), fill = c(heat.colors(9, alpha = 1), 'grey'), cex = 0.56, bty = "o",bg="white",box.lwd=0,box.col="white")
Maria@70:     dev.off()
Maria@70:   }
Maria@70: }
Maria@70: 
Maria@70: PlotYearDistribution <- function(df, output=F){
Maria@70:   df$Year<-as.numeric(as.character(df$Year))
Maria@70:   g = ggplot(df,aes(x=Year,y=..count..))+geom_histogram(breaks=seq(1895, 2015, by = 1))
Maria@70:   #g = ggplot(df,aes(x=Year,y=..count..))+geom_bar()+geom_density(alpha=.3, fill="grey")
Maria@70:   #g = g+scale_x_continuous(breaks = pretty(df$Year, n=10))
Maria@70:   g = g+theme_bw()+labs(x ='Year', y ='Count') 
Maria@70:   #g = ggplot(df,aes(x=Year,y=..count..))+geom_histogram()+theme_bw()
Maria@70:   print(g)
Maria@70:   if (output){
Maria@70:     ggsave('yeardistribution.pdf',plot=g)
Maria@70:   }
Maria@70: }
Maria@70: 
Maria@70: PlotCountryDistribution <- function(df){
Maria@70:   #countrycounts = table(df$Country)
Maria@70:   #dd=data.frame(countrycounts)
Maria@70:   #names(dd)=c("Country","Counts")
Maria@70:   g = ggplot(df,aes(x=Country))+geom_bar()
Maria@70:   g=g+theme(axis.text.x=element_text(angle=90,hjust=1,vjust=0.5))
Maria@70: }
Maria@70: 
Maria@70: #PlotCultureDistribution <- function(df){
Maria@70: #  g = ggplot(df,aes(x=Culture))+geom_bar()
Maria@70: #  g+theme(axis.text.x=element_text(angle=90,hjust=1,vjust=0.5))
Maria@70: #}
Maria@70: 
Maria@70: PlotLanguageDistribution <- function(df, mincount=1){
Maria@70:   dfsubset <- subset(df, df$Language!="") # ignore the recordings culture info
Maria@70:   culturecounts = table(dfsubset$Culture)
Maria@70:   culturecounts = culturecounts[culturecounts>=mincount]
Maria@70:   barplot(culturecounts, las=2, cex.names=0.2)
Maria@70:   #g = ggplot(df,aes(x=Language))+geom_bar()
Maria@70:   #g+theme(axis.text.x=element_text(angle=90,hjust=1,vjust=0.5))
Maria@70: }
Maria@70: 
Maria@70: PlotBarForCategory <- function(df, cat="Language", mincount=1){
Maria@70:   idx_cat = which(colnames(df)==cat)
Maria@70:   dfsubset <- subset(df, df[,idx_cat]!="")
Maria@70:   counts = table(dfsubset[,idx_cat])
Maria@70:   counts = counts[counts>=mincount]
Maria@70:   barplot(counts, las=2, cex.names=0.2)  
Maria@70:   #g = ggplot(df,aes(x=Language))+geom_bar()
Maria@70:   #g+theme(axis.text.x=element_text(angle=90,hjust=1,vjust=0.5))
Maria@70: }
Maria@70: 
Maria@70: PlotCountryYearCutoff <- function(df, cutoffyear=1960){
Maria@70:   df$BeforeYear = df$Year<cutoffyear
Maria@70:   dfsubset <- subset(df, BeforeYear==T)
Maria@70:   countrycounts = table(dfsubset$Country)
Maria@70:   dd=data.frame(countrycounts)
Maria@70:   names(dd)=c("Country","Counts")
Maria@70:   spdf<-joinCountryData2Map(dd,joinCode="NAME",nameCountryColumn="Country",nameJoinColumn="Country")
Maria@70:   mapParams <- mapCountryData(spdf, nameColumnToPlot="Counts",catMethod=as.numeric(levels(as.factor(spdf$Counts))),missingCountryCol='grey',oceanCol="lightblue",colourPalette='heat', mapTitle=paste("Country sample size, year<",cutoffyear),addLegend=F)
Maria@70:   do.call( addMapLegend, c(mapParams, labelFontSize=0.3, legendWidth=0.5, tcl=-0.3, legendMar = 4, legendLabels="all",horizontal=F, legendIntervals="page"))
Maria@70: }
Maria@70: 
Maria@70: #dftemp$Decade<-floor(df$Year/10)*10
Maria@70: #yearcounts = sapply(levels(dftemp$Country),function(x)table(subset(dftemp,Country==x)$Before1960))
Maria@70: #decadecounts = sapply(levels(df$Country),function(x)table(subset(dftemp,Country==x & Before1960=="TRUE")$Before1960))
Maria@70: #print(yearcounts)
Maria@70: 
Maria@70: #metadata we are interested in:
Maria@70: #Artist,AlbumTitle,Culture, Language/Language_Album, Subject_Album
Maria@70: PlotCountryCulture <- function(df){
Maria@70:   dfsubset <- subset(df, df$Culture!="")
Maria@70:   countrycounts = table(dfsubset$Country)
Maria@70:   dd=data.frame(countrycounts)
Maria@70:   names(dd)=c("Country","Counts")
Maria@70:   spdf<-joinCountryData2Map(dd,joinCode="NAME",nameCountryColumn="Country",nameJoinColumn="Country")
Maria@70:   #mapParams <- mapCountryData(spdf, nameColumnToPlot="Counts",catMethod=as.numeric(levels(as.factor(spdf$Counts))),missingCountryCol='grey',oceanCol="lightblue",colourPalette='heat', mapTitle="Recordings with culture information",addLegend=F)
Maria@70:   mapParams <- mapCountryData(spdf, nameColumnToPlot="Counts",catMethod="logFixedWidth",missingCountryCol='grey',oceanCol="lightblue",colourPalette='heat', mapTitle="Number of recordings with culture information",addLegend=F)
Maria@70:   do.call( addMapLegend, c(mapParams, labelFontSize=0.3, legendWidth=0.5, tcl=-0.3, legendMar = 4, legendLabels="all",horizontal=F, legendIntervals="page"))
Maria@70: }
Maria@70: 
Maria@70: PlotCultureDistribution <- function(df){
Maria@70:   dfsubset <- subset(df, df$Culture!="") # ignore the recordings culture info
Maria@70:   culturecounts = table(dfsubset$Culture)
Maria@70:   barplot(culturecounts, las=2, cex.names=0.2)
Maria@70:   #g = ggplot(df,aes(x=Year,y=..count..))+geom_histogram(breaks=seq(1875, 2015, by = 1))
Maria@70:   #print(g)
Maria@70: }
Maria@70: 
Maria@70: PlotCountryNCulture <- function(df){
Maria@70:   dfsubset <- subset(df, df$Culture!="")
Maria@70:   #culturecounts = table(dfsubset$Culture)
Maria@70:   countrycounts = table(dfsubset$Country, dfsubset$Culture)
Maria@70:   aa <- addmargins(countrycounts, FUN = list(Total = sum), quiet = TRUE)
Maria@70:   print(paste(">1000",row.names(aa)[aa[,dim(aa)[2]]>1000]))
Maria@70:   print(paste(">500",row.names(aa)[aa[,dim(aa)[2]]>500]))
Maria@70:   print(paste(">100",row.names(aa)[aa[,dim(aa)[2]]>100]))
Maria@70:   inds = which(aa[,dim(aa)[2]]>500 & row.names(aa)!="Total")
Maria@70:   mosaicplot(aa[inds,1:5])
Maria@70:   dd=data.frame(countrycounts[inds,])
Maria@70:   dd=data.frame(countrycounts)
Maria@70:   names(dd)=c("Country","Culture","Counts")
Maria@70:   ddsub <- subset(dd, (Country=="Canada"| Country=="United Kingdom" | Country=="United States of America") & Counts>20)
Maria@70:   g=ggplot(ddsub, aes(x=Culture,y=Counts))+geom_point()+facet_wrap(~Country, scales = "free")
Maria@70:   g+theme(axis.text.x=element_text(angle=90,hjust=1,vjust=0.5))
Maria@70: }
Maria@70: 
Maria@70: PlotCountryCultureNcounts <- function(df,mincount=50){
Maria@70:   dfsubset <- subset(df, df$Culture!="")
Maria@70:   #culturecounts = table(dfsubset$Culture)
Maria@70:   countrycounts = table(dfsubset$Country, dfsubset$Culture)
Maria@70:   dd=data.frame(countrycounts)
Maria@70:   names(dd)=c("Country","Culture","Counts")
Maria@70:   ddsub <- subset(dd, Counts>mincount)
Maria@70:   g=ggplot(ddsub, aes(x=Culture,y=Counts))+geom_point()+facet_wrap(~Country, scales = "free")
Maria@70:   g+theme(axis.text.x=element_text(angle=90,hjust=1,vjust=0.5))#+title(main=paste("Cultures per country, count>",mincount))
Maria@70: }
Maria@70: 
Maria@70: PlotCountryLanguageNcounts <- function(df,mincount=50){
Maria@70:   dfsubset <- subset(df, df$Language!="" & df$Language!=" ")
Maria@70:   countrycounts = table(dfsubset$Country, dfsubset$Language)
Maria@70:   dd=data.frame(countrycounts)
Maria@70:   names(dd)=c("Country","Language","Counts")
Maria@70:   ddsub <- subset(dd, Counts>mincount)
Maria@70:   g=ggplot(ddsub, aes(x=Language,y=Counts))+geom_point()+facet_wrap(~Country, scales = "free")
Maria@70:   g+theme(axis.text.x=element_text(angle=90,hjust=1,vjust=0.5))#+title(main=paste("Cultures per country, count>",mincount))
Maria@70: }
Maria@70: 
Maria@70: PlotNxNcounts <- function(df, cat1="Country", cat2="Culture", mincount=50, figname=""){
Maria@70:   indcat1 = which(colnames(df)==cat1)
Maria@70:   indcat2 = which(colnames(df)==cat2)
Maria@70:   dfsubset <- subset(df, df[,indcat1]!="" & df[,indcat2]!="")  # avoid nan values
Maria@70:   NNcounts <- table(dfsubset[,indcat1], dfsubset[,indcat2])
Maria@70:   dd=data.frame(NNcounts)
Maria@70:   names(dd) <- c("Cat1","Cat2","Counts")
Maria@70:   ddsub <- subset(dd, Counts>mincount)
Maria@70:   if (figname==""){
Maria@70:     g=ggplot(ddsub, aes(x=Cat2,y=Counts))+geom_point()+facet_wrap(~Cat1)
Maria@70:     g+coord_flip()+theme(axis.text.y=element_text(hjust=1,vjust=0.5,size=5))+labs(y="Counts",x=cat2)
Maria@70:   }else{
Maria@70:     g=ggplot(ddsub, aes(x=Cat2,y=Counts))+geom_point()+facet_wrap(~Cat1)
Maria@70:     g+coord_flip()+theme(axis.text.y=element_text(hjust=1,vjust=0.5,size=5))+labs(y="Counts",x=cat2)
Maria@70:     ggsave(figname)
Maria@70:   }
Maria@70: }
Maria@70: 
Maria@70: Wordcloud<- function(df, cat="Language", output=F){
Maria@70:   require(wordcloud)
Maria@70:   require(RColorBrewer)
Maria@70:   ind_cat = which(colnames(df)==cat)
Maria@70:   counts <- table(df[,ind_cat])
Maria@70:   dd=data.frame(counts)
Maria@70:   names(dd) <- c("words","freq")
Maria@70:   pal2 <- brewer.pal(8,"Dark2")
Maria@70:   wordcloud(dd$words,dd$freq,random.order=FALSE, colors=pal2)
Maria@70:   if (output){
Maria@70:     pdf("wordcloud.pdf")
Maria@70:     wordcloud(dd$words,dd$freq,random.order=FALSE, colors=pal2)
Maria@70:     dev.off()
Maria@70:   }
Maria@70: }
Maria@70: PlotCountryOutliers <- function(df, output=''){
Maria@70:   par(mar = rep(2, 4))
Maria@70:   spdf<-joinCountryData2Map(df,joinCode="NAME",nameCountryColumn="Country",nameJoinColumn="Country")
Maria@70:   spdf<-spdf[-which(spdf$ADMIN=='Antarctica'),]
Maria@70:   #mapParams <- mapCountryData(spdf, nameColumnToPlot="Outliers",catMethod=seq(0,70,5),missingCountryCol='grey',colourPalette='heat', mapTitle="", addLegend=FALSE)
Maria@70:   mapParams <- mapCountryData(spdf, nameColumnToPlot="Outliers", catMethod=seq(0,1,0.1), missingCountryCol='grey',colourPalette='heat', mapTitle="", addLegend=FALSE)
Maria@70:   # avoid antarctica
Maria@70:   #mapParams <- mapCountryData(spdf, nameColumnToPlot="Outliers", ylim=c(-60,90), catMethod=seq(0,1,0.1), missingCountryCol='grey',colourPalette='heat', mapTitle="", addLegend=FALSE)
Maria@70:   #do.call( addMapLegend, c(mapParams, labelFontSize=0.7, legendWidth=0.5, tcl=0.3, legendMar = 7, legendLabels="all",horizontal=T, legendIntervals="page"))
Maria@70:   legend("left", legend = c(paste(seq(90,0,-10),'-',seq(100,10,-10),'%'), 'NA'), fill = c(heat.colors(10, alpha = 1), 'grey'), cex = 0.56, bty = "o",bg="white",box.lwd=0,box.col="white")
Maria@70:   if (output!=''){
Maria@70:     pdf(output)
Maria@70:     #mapParams <- mapCountryData(spdf, nameColumnToPlot="Outliers",catMethod=seq(0,70,5),missingCountryCol='grey',colourPalette='heat', mapTitle="", addLegend=FALSE)
Maria@70:     mapParams <- mapCountryData(spdf, nameColumnToPlot="Outliers", catMethod=seq(0,1,0.1), missingCountryCol='grey',colourPalette='heat', mapTitle="", addLegend=FALSE)
Maria@70:     #mapParams <- mapCountryData(spdf, nameColumnToPlot="Outliers", ylim=c(-60,90), catMethod=seq(0,1,0.1), missingCountryCol='grey',colourPalette='heat', mapTitle="", addLegend=FALSE)
Maria@70:     #do.call( addMapLegend, c(mapParams, labelFontSize=0.7, legendWidth=0.5, tcl=0.3, legendMar=7, legendLabels="all",horizontal=T, legendIntervals="page"))
Maria@70:     legend("left", legend = c(paste(seq(90,0,-10),'-',seq(100,10,-10),'%'), 'NA'), fill = c(heat.colors(10, alpha = 1), 'grey'), cex = 0.56, bty = "o",bg="white",box.lwd=0,box.col="white")
Maria@70:     dev.off()
Maria@70:   }
Maria@70:   else {
Maria@70:     return(mapParams)
Maria@70:   }
Maria@70: }