svendvn

"V1","V2","V3","V4"
"Everest",8849,688.582,"Indian Ocean"
"Kanchenjunga",8586,670,"Indian Ocean"
"Chomolhari",7090,614,"Indian Ocean"
"Gangkhar Puensum",7570,605,"Indian Ocean"
"Chimborazo",6263.47,175,"Pacific"
"Mishahuanga",4118,91,"Pacific"
"Huascaran",6746,97.7,"Pacific"
"Coropuna",6405,112,"Pacific"
"El Misti",5822,103,"Pacific"

svendvn

name ujo pop uea lernu www pas edu nat
AFG afghanistan 0 27.7 1 48 - 0 0 0
ALB albanien 0 2.8 14 64 0.6 1 5 33
DZA algeriet 1 39.2 6 503 0.15 1 8 0
AND andorra - 0.078 0 167 - 0 8 0
AGO angola 1 21.5 2 42 0.19 0 0 -
ARG argentino 27 41.5 29 1965 0.60 16 61 140
ARM armenien 0 3.0 12 92 - 0 1 27
AUS australio 23 23.1 40 2568 0.83 16 52 130
AUT austria 4 8.6 44 780 0.81 8 23 79

svendvn

---
title: "Linguistic differences"
output: html_notebook
---

Read in all the data. In the working directory, I have put several files from the AJSP database. Any subset of files will do.

```{r}
lf=list.files(pattern=".csv")

svendvn

CODE	Country	Count	Percent	Established	Immigrant	Total	Mean	Median	Index	Coverage
AFG	Afghanistan	42	0.59	41	1	22,964,800	560,117	8,000	0.790	98%
ALB	Albania	12	0.17	8	4	2,801,786	280,179	4,220	0.503	83%
DZA	Algeria	21	0.30	18	3	33,135,600	1,743,979	40,000	0.360	90%
-	American Samoa	7	0.10	2	5	55,910	9,318	25,800	0.210	86%
AND	Andorra	5	0.07	4	1	74,270	14,854	19,650	0.671	100%
AGO	Angola	40	0.56	40	0	23,511,670	602,863	43,900	0.748	98%
-	Anguilla	2	0.03	2	0	12,450	6,225	6,225	0.141	100%
-	Antigua and Barbuda	5	0.07	2	3	135,000	33,750	66,500	0.515	80%
ARG	Argentina	38	0.54	24	14	44,146,270	1,337,766	8,410	0.165	87%

svendvn

a=read.table('usa_big.txt', header=F)
remove_and_make_numeric=function(s){
  return(as.numeric(substr(x = s, start = 1, stop = nchar(s)-1)))
}

summarize=function(x){
  y=x/100
  within=sum(y)
  res=0
  for(i in 1:length(y)){

svendvn

ad=read.csv('parsed_data.txt', header=T)
ad=as.data.frame(apply(ad, c(1,2), function(x) ifelse(is.na(x),0,x)), stringsAsFactors = F)
ad[,3:ncol(ad)]=apply(ad[,3:ncol(ad)], c(1,2), as.numeric)
View(ad)
colnames(ad)[1] <- 'Rank'
barplot(height=ad$Speakers[1:10], names.arg=ad$Language[1:10])
ad$Learners=apply(ad[,c("Advanced","Intermediate","Beginner")],1,sum)
ad$Learners=sapply(ad$Learners, function(x) max(x,1))
normed_d=ad[,c("Advanced","Intermediate","Beginner")]/ad$Learners
apply(normed_d,1,sum)

svendvn

language1,language2,Distance
AFAR,AFAR,0
AFAR,AFRIKAANS,0.967213114754098
AFAR,ALBANIAN,0.918269230769231
AFAR,AMHARIC,0.873170731707317
AFAR,AMOY_MINNAN_CHINESE,0.942982456140351
AFAR,AZERBAIJANI_NORTH,0.9375
AFAR,B41_SHIRA,0.919540229885057
AFAR,BAMBARA,0.92948717948718
AFAR,BANGANDU,0.923076923076923