Analysis of the data on Crime against Women in India in 2012.

gistfile1.r

library(sp)
library(RColorBrewer)
crimeW12 <- read.csv(url("http://data.gov.in/access-point-download-count?url=http://data.gov.in/sites/default/files/crdCAW_1.csv"), header = TRUE)
load(url("http://biogeo.ucdavis.edu/data/gadm2/R/IND_adm1.RData"))

#divide the data set into different crime headers

temp <- crimeW12[,c(1,4)]
crimeRep1 <- data.frame(State = temp[1:38,1],
                       Rape = temp[1:38,2], Kidnap = temp[39:76,2],
                       DowryDeath = temp[77:114,2], Assault = temp[115:152,2],
                       Insult = temp[153:190,2], Husband = temp[191:228,2],
                       Import = temp[229:266,2], Sati = temp[267:304,2],
                       Traffic = temp[305:342,2], Indecent = temp[343:380,2],
                       Dowry = temp[381:418, 2], Total = temp[419:456,2])

crimeRep <- crimeRep1[-c(29,37,38),]
temporder <- crimeRep[order(crimeRep$State),]
gadm$Rape <- temporder$Rape
gadm$Kidnap <- temporder$Kidnap
gadm$DowryDeath <- temporder$DowryDeath
gadm$Assault <- temporder$Assault
gadm$Insult <- temporder$Insult
gadm$Husband <- temporder$Husband
gadm$Import <- temporder$Import
gadm$Sati <- temporder$Sati
gadm$Traffic <- temporder$Traffic
gadm$Indecent <- temporder$Indecent
gadm$Dowry <- temporder$Dowry
gadm$Total <- temporder$Total

#plot state wise crime

spplot(gadm, "Rape", col.regions = col, at = c(0,50,100,200, 500,1000, 1500,2000,2500,4000), main = "Rape")
spplot(gadm, "Kidnap", col.regions = col, at = c(0,50,100,200, 500,1000,2000,3000,5000,8000), main = "Kidnapping and Abduction")
spplot(gadm, "DowryDeath", col.regions = col, at = c(0,25, 50,100,250, 500,1000, 1500,2000,2500), main = "Dowry Death")
spplot(gadm, "Assault", col.regions = col, at = c(0,50,100,200, 500,1000,2000,3000,5000,7000),main = "Assault")
spplot(gadm, "Insult", col.regions = col, at = c(0,50,100,250,500,1000,1500,2000,3000,4000),main = "Insult to Modesty")
spplot(gadm, "Husband", col.regions = col, at = c(0,50,100,250,500,1000,2500,5000,10000,20000),main = "Cruelty by Husband and Others")
spplot(gadm, "Import", col.regions = col, at = c(0,5,10,20,30,50,100,200,500,1000),main = "Importing Girls")
spplot(gadm, "Sati", col.regions = col, at = c(0,5,10,15,20,30),main = "Sati")
spplot(gadm, "Traffic", col.regions = col, at = c(0,10,25,50,100,150,200,300,400,500),main = "Immoral Traffic")
spplot(gadm, "Indecent", col.regions = col, at = c(0,5,10,25,50,75,100), main = "Indecent Representation")
spplot(gadm, "Dowry", col.regions = col, at = c(0,50,100,250,500,1000,1500,2000,2500,3000),main = "Dowry")
spplot(gadm, "Total", col.regions = col, at = c(0,100,500,1000,2500,5000,10000,15000,25000,32000),main = "Total cases")

# clustering
row.names(crimeRep) <- crimeRep$State
crimeRep <- subset(crimeRep, select=-State)

d <- dist(crimeRep)
par(mfrow = c(1,3))
hcs <- hclust(d, "single")
hca <- hclust(d, "average")
hcc <- hclust(d, "complete")
plot(hcs,frame.plot = TRUE)
plot(hca,frame.plot = TRUE)
plot(hcc,frame.plot = TRUE)
par(mfrow = c(1,1))
plot(hcc,frame.plot = TRUE)
rect.hclust(hcc, k = 5, border = "red")


dt <- dist(t(crimeRep[,-12]))
par(mfrow = c(1,3))
hcst <- hclust(dt, "single")
hcat <- hclust(dt, "average")
hcct <- hclust(dt, "complete")
plot(hcst,frame.plot = TRUE)
plot(hcat,frame.plot = TRUE)
plot(hcct,frame.plot = TRUE)
par(mfrow = c(1,1))
plot(hcct,frame.plot = TRUE)