Maria@70: library(rworldmap)
Maria@70: library(ggplot2)
Maria@70: 
m@91: library(extrafont)
m@91: font_import()
m@91: loadfonts()
m@91: Arial <- Type1Font(family="Arial", metrics=c("ArialMT.afm","arial-BoldMT.afm","Arial-ItalicMT.afm", "Arial-BoldItalicMT.afm"))
m@91: postscriptFonts(Arial=Arial)
m@91: par(family="Arial")
m@91: 
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$REGION.y),]
Maria@70:   dfsub <- dfsub[order(dfsub[,idx_ordercat]),]
Maria@70:   dfsub[,idx_cat] <- factor(dfsub[,idx_cat], levels=unique(dfsub[,idx_cat]))
Maria@70:   g = ggplot(dfsub,aes(dfsub[,idx_cat], fill=dfsub[,idx_ordercat], order=-as.numeric(dfsub[,idx_ordercat])))+geom_bar()
Maria@70:   #g = g+ylim("0", "100")#+scale_y_discrete(breaks=c("100"),labels=c("100+"))
Maria@70:   g=g+scale_y_continuous(limits=c(0, 200), breaks=seq(0,200,40))
Maria@70:   g=g+scale_fill_brewer(palette=color_plt)
m@91:   g=g+theme(axis.text.x=element_text(angle=90,hjust=1,vjust=0.5), text = element_text(size=12))
Maria@70:   g=g+labs(y="Counts",x=cat)+coord_flip()+theme_bw()
Maria@70:   if (legend){
Maria@70:     g=g+guides(fill = guide_legend(title = ordercat))}
Maria@70:   else{
Maria@70:     g=g+guides(fill="none")
Maria@70:   }
Maria@70:   return(g)
Maria@70: }
Maria@70: 
Maria@70: PlotCountryCounts <- function(df, output=F){
Maria@70:   countrycounts = table(df$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: 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: 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!=''){
m@91:     if (grepl('.pdf', output)){
m@91:       pdf(output, pointsize=12)
m@91:     } else if (grepl('.eps', output)){
m@91:       postscript(output, pointsize=12)
m@91:     }
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: }