1 INDIA

setwd("~/IS607Spring2016/project-final")
dat.india.url = "http://knoema.com/api/1.0/data/wiwuiff"
dat.india.parms = "?Time=2005-2005&region=1000130,1000020,1000040,1000050,1000060,1000080,1000090,1000100,1000110,1000120,1000140,1000150,1000160,1000220,1000210,1000230,1000290,1000280,1000270,1000250&variable=1000130,1000140,1000070,1000080&Frequencies=A"
dat.india.query = paste0(dat.india.url,dat.india.parms)
dat.india.province = fromJSON(dat.india.query)
dat.india.province = subset(dat.india.province$data, select = -c(Unit, Time, RegionId, Frequency, Scale))
dat.india.province = data.frame(spread(dat.india.province, variable, Value))
colnames(dat.india.province)[2:5] = c("PercentageRural", "PercentageUrban", "RuralGini", "UrbanGini")
dat.india.province$region[8] = "Jammu and Kashmir"
dat.india.province$region[14] = "Odisha"

dir.ind.regions.shpfiles <- paste0(getwd(),"/ind-files/IND_adm_shp")
map.ind.regions1 <- readShapePoly(paste0(dir.ind.regions.shpfiles,"/IND_adm1.shp"), proj4string=CRS("+proj=longlat +datum=NAD27"))


dat.india.province <- rbind(dat.india.province, data.frame(region = 'Telangana', subset(dat.india.province, region == "Andhra Pradesh", select = -c(region))))
dat.india.province <- dat.india.province[order(dat.india.province$region),]
#Recalc overall average per province as weighted average of rural and urban populations.
dat.india.province$GINI <- (
      (dat.india.province$RuralGini)*(dat.india.province$PercentageRural) +
      (dat.india.province$UrbanGini)*(dat.india.province$PercentageUrban)
)/100
dat.india.url = "http://knoema.com/api/1.0/data/wiwuiff"
dat.india.parms = "?Time=2005-2005&variable=1000130,1000140,1000080,1000070&region=1000000&Frequencies=A"
dat.india.query = paste0(dat.india.url,dat.india.parms)
dat.india = fromJSON(dat.india.query)
dat.india = subset(dat.india$data,select = -c(Unit, Time, RegionId, Frequency, Scale))
#clarify what's happening here
dat.india = data.frame(spread(dat.india, variable, Value))
colnames(dat.india)[2:5] = c("PercentageRural", "PercentageUrban", "RuralGini", "UrbanGini")
dat.india$GINI = ((dat.india$RuralGini)*(dat.india$PercentageRural) + (dat.india$UrbanGini)*(dat.india$PercentageUrban))/100

map.ind.regions1 = fortify(map.ind.regions1, region = "NAME_1")
map.ind.regions1 = rename(map.ind.regions1,x=long,y=lat)
mycolors = brewer.pal(9,"BrBG")
ggplot(data=dat.india.province) +
  geom_map(
    aes(fill=GINI, map_id=region),
    map=map.ind.regions1
  ) +
  expand_limits(map.ind.regions1) +
  theme_bw() +
  scale_fill_gradientn(name="Coverage", colours = mycolors)

2 US STATES

3 US COUNTIES

setwd("~/IS607Spring2016/project-final/usa-files")
df_county <- read.csv(paste0(getwd(),"/GINI-2014-County.csv"))
df_county <- mutate(df_county,FIPS=substring(df_county$GEOID,10,15))

setwd("~/IS607Spring2016/project-final/usa-files/cb_2014_us_county_5m/")
US.counties <- readOGR(dsn=".",layer="gz_2010_us_050_00_5m")
## OGR data source with driver: ESRI Shapefile 
## Source: ".", layer: "gz_2010_us_050_00_5m"
## with 3221 features
## It has 6 fields
#leave out AK, HI, and PR (state FIPS: 02, 15, and 72)
US.counties <- US.counties[!(US.counties$STATE %in% c("02","15","72")),]  
county.data <- US.counties@data
county.data <- cbind(id=rownames(county.data),county.data)
county.data <- data.table(county.data)
county.data[,FIPS:=paste0(STATE,COUNTY)] # this is the state + county FIPS code
setkey(county.data,FIPS)      
gini.data <- data.table(df_county)
setkey(gini.data,FIPS)
county.data[gini.data,GINI:=GINI]

map.df <- data.table(fortify(US.counties))
## Regions defined for each Polygons
setkey(map.df,id)
setkey(county.data,id)
map.df[county.data,GINI:=GINI]
map.df <- mutate(map.df,GINI.NUM=as.numeric(as.character((GINI))))
g2 <- ggplot(map.df, aes(x=long, y=lat, group=group, fill=GINI.NUM)) +
      scale_fill_gradientn("",colours=brewer.pal(9,"PuBuGn")) +
      geom_polygon() + coord_map("polyconic") +
      labs(title="US 2014 GINI Index by County range (0 -> 1) ",x="",y="") +
      theme_bw() +
      theme(legend.justification=c(0,1),legend.position=c(0,1),
            legend.background=element_rect(colour="black"))
g2 <- g2 + guides(fill=guide_legend(title="GINI",nrow=3,title.position="top",
                title.hjust=0.5,title.theme=element_text(face="bold",angle=0)))
g2 <- g2 + scale_x_continuous("") + scale_y_continuous("")


g3 <- ggplot(data=dat.usa.state) +
          geom_map(data=map.usa.states, map=map.usa.states,
                        aes(x=long, y=lat, map_id=region),
                        fill="#ffffff", color="#ffffff", size=0.15) + 
          geom_map(data=dat.usa.state, map=map.usa.states,
                        aes(fill=GINI, map_id=STATE),
                        color="#ffffff", size=0.15)   
g3 <- g3 + scale_fill_gradientn(name="Coverage", colours = mycolors)
g3 <- g3 + coord_map("polyconic") +
      labs(title="US 2014 GINI Index by State range (0 -> 1) ",x="",y="")+
      theme_bw() +
      theme(legend.justification=c(0,1),legend.position=c(0,1),
            legend.background=element_rect(colour="black"))
g3 <- g3 + guides(fill=guide_legend(title="GINI",nrow=3,title.position="top",legend.key.width = unit(1, "cm"),
                title.hjust=0.5,title.theme=element_text(face="bold",angle=0)))
par(mfrow = c(2, 2))
g2

g3