annotate scripts_R/MetadataPlots.R @ 105:edd82eb89b4b branch-tests tip

Merge

library(rworldmap)
library(ggplot2)

library(extrafont)
font_import()
loadfonts()
Arial <- Type1Font(family="Arial", metrics=c("ArialMT.afm","arial-BoldMT.afm","Arial-ItalicMT.afm", "Arial-BoldItalicMT.afm"))
postscriptFonts(Arial=Arial)
par(family="Arial")

PlotBarChart<- function(df, cat="Language", ordercat="REGION", mincount=10, legend=T, color_plt="Paired"){
  idx_cat = which(colnames(df)==cat)
  idx_ordercat = which(colnames(df)==ordercat)
  dfsub <- subset(df, df[,idx_cat]!="")
  dfsub <- dfsub[ dfsub[,idx_cat] %in%  names(table(dfsub[,idx_cat]))[table(dfsub[,idx_cat]) >mincount] , ]
  #dfsub <- dfsub[order(dfsub$REGION.y),]
  dfsub <- dfsub[order(dfsub[,idx_ordercat]),]
  dfsub[,idx_cat] <- factor(dfsub[,idx_cat], levels=unique(dfsub[,idx_cat]))
  g = ggplot(dfsub,aes(dfsub[,idx_cat], fill=dfsub[,idx_ordercat], order=-as.numeric(dfsub[,idx_ordercat])))+geom_bar()
  #g = g+ylim("0", "100")#+scale_y_discrete(breaks=c("100"),labels=c("100+"))
  g=g+scale_y_continuous(limits=c(0, 200), breaks=seq(0,200,40))
  g=g+scale_fill_brewer(palette=color_plt)
  g=g+theme(axis.text.x=element_text(angle=90,hjust=1,vjust=0.5), text = element_text(size=12))
  g=g+labs(y="Counts",x=cat)+coord_flip()+theme_bw()
  if (legend){
    g=g+guides(fill = guide_legend(title = ordercat))}
  else{
    g=g+guides(fill="none")
  }
  return(g)
}

PlotCountryCounts <- function(df, output=F){
  countrycounts = table(df$Country)
  dd=data.frame(countrycounts)
  names(dd)=c("Country","Counts")
  spdf<-joinCountryData2Map(dd,joinCode="NAME",nameCountryColumn="Country",nameJoinColumn="Country")
  spdf<-spdf[-which(spdf$ADMIN=='Antarctica'),]
  #mapParams <- mapCountryData(spdf, nameColumnToPlot="Counts",catMethod=as.numeric(levels(as.factor(spdf$Counts))),missingCountryCol='grey',borderCol='black',oceanCol="white",colourPalette='heat', mapTitle="",addLegend=F)
  mapParams <- mapCountryData(spdf, nameColumnToPlot="Counts",catMethod=seq(10,100,10),missingCountryCol='grey',borderCol='black',oceanCol="white",colourPalette="heat", mapTitle="",addLegend=F)
  #do.call( addMapLegend, c(mapParams, labelFontSize=0.7, legendShrink=0.5,legendWidth=0.5, tcl=0.3, legendMar = 7, legendLabels="all",horizontal=T, legendIntervals="page"))
  legend("left", legend = c(paste(seq(90,1,-10),'-',seq(100,11,-10)), 'NA'), fill = c(heat.colors(9, alpha = 1), 'grey'), cex = 0.56, bty = "o",bg="white",box.lwd=0,box.col="white")
  if (output){
    pdf(file="countrycounts.pdf")
    mapParams <- mapCountryData(spdf, nameColumnToPlot="Counts",catMethod=seq(10,100,10),missingCountryCol='grey',borderCol='black',oceanCol="white",colourPalette="heat", mapTitle="",addLegend=F)
    #mapParams <- mapCountryData(spdf, nameColumnToPlot="Counts",catMethod=as.numeric(levels(as.factor(spdf$Counts))),missingCountryCol='grey',borderCol='black',oceanCol="lightblue",colourPalette='heat', mapTitle="",addLegend=F)
    #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"))
    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")
    dev.off()
  }
}

PlotYearDistribution <- function(df, output=F){
  df$Year<-as.numeric(as.character(df$Year))
  g = ggplot(df,aes(x=Year,y=..count..))+geom_histogram(breaks=seq(1895, 2015, by = 1))
  #g = ggplot(df,aes(x=Year,y=..count..))+geom_bar()+geom_density(alpha=.3, fill="grey")
  #g = g+scale_x_continuous(breaks = pretty(df$Year, n=10))
  g = g+theme_bw()+labs(x ='Year', y ='Count') 
  #g = ggplot(df,aes(x=Year,y=..count..))+geom_histogram()+theme_bw()
  print(g)
  if (output){
    ggsave('yeardistribution.pdf',plot=g)
  }
}

PlotLanguageDistribution <- function(df, mincount=1){
  dfsubset <- subset(df, df$Language!="") # ignore the recordings culture info
  culturecounts = table(dfsubset$Culture)
  culturecounts = culturecounts[culturecounts>=mincount]
  barplot(culturecounts, las=2, cex.names=0.2)
  #g = ggplot(df,aes(x=Language))+geom_bar()
  #g+theme(axis.text.x=element_text(angle=90,hjust=1,vjust=0.5))
}

PlotCountryOutliers <- function(df, output=''){
  par(mar = rep(2, 4))
  spdf<-joinCountryData2Map(df,joinCode="NAME",nameCountryColumn="Country",nameJoinColumn="Country")
  spdf<-spdf[-which(spdf$ADMIN=='Antarctica'),]
  #mapParams <- mapCountryData(spdf, nameColumnToPlot="Outliers",catMethod=seq(0,70,5),missingCountryCol='grey',colourPalette='heat', mapTitle="", addLegend=FALSE)
  mapParams <- mapCountryData(spdf, nameColumnToPlot="Outliers", catMethod=seq(0,1,0.1), missingCountryCol='grey',colourPalette='heat', mapTitle="", addLegend=FALSE)
  # avoid antarctica
  #mapParams <- mapCountryData(spdf, nameColumnToPlot="Outliers", ylim=c(-60,90), catMethod=seq(0,1,0.1), missingCountryCol='grey',colourPalette='heat', mapTitle="", addLegend=FALSE)
  #do.call( addMapLegend, c(mapParams, labelFontSize=0.7, legendWidth=0.5, tcl=0.3, legendMar = 7, legendLabels="all",horizontal=T, legendIntervals="page"))
  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")
  if (output!=''){
    if (grepl('.pdf', output)){
      pdf(output, pointsize=12)
    } else if (grepl('.eps', output)){
      postscript(output, pointsize=12)
    }
    #mapParams <- mapCountryData(spdf, nameColumnToPlot="Outliers",catMethod=seq(0,70,5),missingCountryCol='grey',colourPalette='heat', mapTitle="", addLegend=FALSE)
    mapParams <- mapCountryData(spdf, nameColumnToPlot="Outliers", catMethod=seq(0,1,0.1), missingCountryCol='grey',colourPalette='heat', mapTitle="", addLegend=FALSE)
    #mapParams <- mapCountryData(spdf, nameColumnToPlot="Outliers", ylim=c(-60,90), catMethod=seq(0,1,0.1), missingCountryCol='grey',colourPalette='heat', mapTitle="", addLegend=FALSE)
    #do.call( addMapLegend, c(mapParams, labelFontSize=0.7, legendWidth=0.5, tcl=0.3, legendMar=7, legendLabels="all",horizontal=T, legendIntervals="page"))
    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")
    dev.off()
  }
  else {
    return(mapParams)
  }
}