Mercurial > hg > plosone_underreview

changeset 91:d3e05cd49feb branch-tests

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
trying to plot wrt PLOSONE guidelines
author Maria Panteli <m.x.panteli@gmail.com>
date Mon, 02 Oct 2017 15:32:51 +0100
parents 8a2d56880050
children ce525367960e
files notebooks/explain_components.ipynb scripts_R/MetadataPlots.R scripts_R/Metadata_subsetBLSM.R scripts_R/PlotOutliersCountry.R
diffstat 4 files changed, 68 insertions(+), 24 deletions(-) [+]
line wrap: on
line diff
--- a/notebooks/explain_components.ipynb	Mon Oct 02 12:37:55 2017 +0100
+++ b/notebooks/explain_components.ipynb	Mon Oct 02 15:32:51 2017 +0100
@@ -32,7 +32,9 @@
   {
    "cell_type": "code",
    "execution_count": 2,
-   "metadata": {},
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [
     {
      "name": "stdout",
@@ -63,6 +65,7 @@
    "cell_type": "code",
    "execution_count": 14,
    "metadata": {
+    "collapsed": false,
     "scrolled": false
    },
    "outputs": [
@@ -229,7 +232,9 @@
   {
    "cell_type": "code",
    "execution_count": 3,
-   "metadata": {},
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [
     {
      "name": "stdout",
@@ -267,7 +272,9 @@
   {
    "cell_type": "code",
    "execution_count": 62,
-   "metadata": {},
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [
     {
      "name": "stdout",
@@ -299,7 +306,9 @@
   {
    "cell_type": "code",
    "execution_count": 13,
-   "metadata": {},
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [
     {
      "data": {
@@ -362,7 +371,9 @@
   {
    "cell_type": "code",
    "execution_count": 4,
-   "metadata": {},
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [
     {
      "name": "stdout",
@@ -405,7 +416,9 @@
   {
    "cell_type": "code",
    "execution_count": 6,
-   "metadata": {},
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [
     {
      "name": "stdout",
@@ -423,7 +436,9 @@
   {
    "cell_type": "code",
    "execution_count": 65,
-   "metadata": {},
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [
     {
      "name": "stdout",
@@ -493,7 +508,9 @@
   {
    "cell_type": "code",
    "execution_count": 69,
-   "metadata": {},
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [
     {
      "data": {
@@ -528,7 +545,9 @@
   {
    "cell_type": "code",
    "execution_count": 67,
-   "metadata": {},
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [
     {
      "name": "stdout",
@@ -568,7 +587,9 @@
   {
    "cell_type": "code",
    "execution_count": 51,
-   "metadata": {},
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [
     {
      "data": {
@@ -627,7 +648,9 @@
   {
    "cell_type": "code",
    "execution_count": 26,
-   "metadata": {},
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [
     {
      "data": {
@@ -659,7 +682,9 @@
   {
    "cell_type": "code",
    "execution_count": 31,
-   "metadata": {},
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [
     {
      "data": {
@@ -692,7 +717,9 @@
   {
    "cell_type": "code",
    "execution_count": 33,
-   "metadata": {},
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [
     {
      "data": {
--- a/scripts_R/MetadataPlots.R	Mon Oct 02 12:37:55 2017 +0100
+++ b/scripts_R/MetadataPlots.R	Mon Oct 02 15:32:51 2017 +0100
@@ -1,6 +1,13 @@
 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)
@@ -13,7 +20,7 @@
   #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))
+  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))}
@@ -76,7 +83,11 @@
   #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!=''){
-    pdf(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)
--- a/scripts_R/Metadata_subsetBLSM.R	Mon Oct 02 12:37:55 2017 +0100
+++ b/scripts_R/Metadata_subsetBLSM.R	Mon Oct 02 15:32:51 2017 +0100
@@ -12,17 +12,17 @@
 par(family="Arial")
 
 #pdf(file="data/country_distribution_BL.pdf")
-pdf(file="../data/results/country_distribution.pdf")
+pdf(file="../data/results/country_distribution.pdf", pointsize=12, width=6, height=4)
 PlotCountryCounts(df)
 dev.off()
-postscript(file="../data/results/country_distribution.eps")
+postscript(file="../data/results/country_distribution.eps", pointsize=12, width=6, height=4)
 PlotCountryCounts(df)
 dev.off()
 
-pdf(file="../data/results/year_distribution.pdf", width=6, height=4)
+pdf(file="../data/results/year_distribution.pdf", width=6, height=4, pointsize=12)
 PlotYearDistribution(df)
 dev.off()
-postscript("../data/results/year_distribution.eps", width=10)
+postscript("../data/results/year_distribution.eps", width=10, pointsize=12)
 PlotYearDistribution(df)
 dev.off()
 #PlotBarChart(df, cat="Year", ordercat="REGION", mincount=10)
@@ -33,10 +33,10 @@
 levels(df$Language)[which(levels(df$Language)=="Lesser Antillean Creole French")]="Lesser Antil. Creole French"
 df$Language[which(df$Language=="Lesser Antillean Creole French")] = "Lesser Antil. Creole French"
 df$REGION[which(df$Country=="French Guiana")] = "South America"
-pdf(file="../data/results/language_distribution.pdf")
+pdf(file="../data/results/language_distribution.pdf", pointsize=12)
 PlotBarChart(df, cat="Language", ordercat="Region", mincount=10)
 dev.off()
-postscript("../data/results/language_distribution.eps", width=8, height=10)
+postscript("../data/results/language_distribution.eps", width=8, height=10, pointsize=12)
 PlotBarChart(df, cat="Language", ordercat="Region", mincount=10)
 dev.off()
 
@@ -128,5 +128,5 @@
 g = g+guides(fill = guide_legend(title = "Region"))+theme(legend.position="top",legend.title = element_text(size=9),legend.text = element_text(size=9))
 g = g+theme(panel.border = element_rect(colour = "white"),strip.background=element_rect(fill="white"),strip.text.x = element_blank())
 #g = g+theme(axis.text.y = element_text(colour = ddata$labels$col))
-ggsave('../data/results/clusters_top3.pdf',plot=g)
-ggsave('../data/results/clusters_top3.eps',plot=g)
+ggsave('../data/results/clusters_top3.pdf',plot=g, pointsize=12)
+ggsave('../data/results/clusters_top3.eps',plot=g, pointsize=12)
--- a/scripts_R/PlotOutliersCountry.R	Mon Oct 02 12:37:55 2017 +0100
+++ b/scripts_R/PlotOutliersCountry.R	Mon Oct 02 15:32:51 2017 +0100
@@ -12,12 +12,18 @@
 
 df = read.csv("../data/results/cluster_freq.csv")
 data = df[,2:dim(df)[2]]
+levels(df$labels)[which(levels(df$labels)=="Democratic Republic of the Congo")]="DR Congo"
+df$labels[which(df$labels=="Democratic Republic of the Congo")] = "DR Congo"
 rownames(data) <- df$labels
 distMahal = as.dist(apply(data, 1, function(i) mahalanobis(data, i, cov = cov(data),tol=1e-18)))
 hc=hclust(distMahal, method="average")
 mypal = c("#000000", "#9B0000", "#9B0000", "#9B0000", "#9B0000")
 clus5 = cutree(hc, 4)
-pdf('../data/results/hierarchical_cluster.pdf')
+pdf('../data/results/hierarchical_cluster.pdf', pointsize=12)
 par(mar=c(1,1,1,1))
 plot(as.phylo(hc),type="fan",tip.color=mypal[clus5], cex=.5, label.offset=.5)
 dev.off()
+postscript('../data/results/hierarchical_cluster.eps', pointsize=12)
+par(mar=c(1,1,1,1))
+plot(as.phylo(hc),type="fan",tip.color=mypal[clus5], cex=.5, label.offset=.5)
+dev.off()