## ----sampindia01--------------------------------------------------------------
x <- read.csv("PC_2011.csv", stringsAsFactors = FALSE)
head(x)
dim(x)
table(x$Level)


## ----sampindia10--------------------------------------------------------------
villages <- x[x$Level == "VILLAGE" & x$TRU == "Rural", ]
dim(villages)


## ----sampindia100-------------------------------------------------------------
set.seed(352020)
samplesize <- 40
i <- sample(nrow(villages), samplesize, prob=villages$No_HH)
sort(i)
sel_villages <- villages[i, ]
sort(sel_villages$Name)


## ----sampindia20--------------------------------------------------------------
subdist <- unique(x[x$Level == "SUB-DISTRICT", c("Subdistt", "Name")])
colnames(subdist)[2] <- "Subdistrict"
head(subdist)


## ----sampindia201-------------------------------------------------------------
sel_villages <- merge(sel_villages, subdist, by="Subdistt")
head(sel_villages)


## ----sampindia30--------------------------------------------------------------
sel_villages <- sel_villages[, c("State", "District", "Subdistt", "Town.Village", "Subdistrict", "Name", "No_HH")]
sel_villages <- sel_villages[order(sel_villages$Subdistrict, sel_villages$Name), ]


## ----pdf----------------------------------------------------------------------
#library(pdftools)
voterfile <- "Bariyarpur-1.pdf"
# read the file
s <- pdftools::pdf_text(voterfile)
class(s)
length(s)


## ----sampvoter01--------------------------------------------------------------

	housepattern = "गतह सपखयच : "
	namepattern = "ननरचरचक कच नचम : "

	ss <- trimws(unlist(strsplit(s, "\r\n")))

	i <- grep(paste0("^", namepattern), ss)
	si <- trimws(unlist(strsplit(ss[i], namepattern)))

	j <- grep(paste0("^", housepattern), ss)
	sj <- trimws(unlist(strsplit(ss[j], housepattern)))
	
	# this should be TRUE
	(length(si) == length(sj))
  
	x <- cbind(sj, si)
	x <- x[x[,1] != "", ]
	colnames(x) <- c("household", "name")


## ----xxx----------------------------------------------------------------------
hn <- unique(x)
head(hn)


## ----sampvoter20--------------------------------------------------------------
uhh <- unique(hn[, "household"])
head(uhh)
#hns <- sample(uhh, 15)
#hns


## ----sampvoter30--------------------------------------------------------------
#x <- hn[hn[, "household"] %in% hns, ]
#y <- tapply(x[,2], x[,1], function(i) paste(i, collapse=", "))
#z <- cbind(house=names(y), names=as.vector(y))


## ----sampvoter40--------------------------------------------------------------
#knitr::kable(z[1:5,])


## -----------------------------------------------------------------------------
#write.csv(z, "selection.csv", row.names = FALSE)