Lab 5 - LF

Lab 5 - LF

library(readr)
library(dplyr)
library(ggplot2)
library(readr)
library(RColorBrewer)
library(ggmap)
library(maptools)
library(gtools)

#Loading in the blank map of the United States and plotting
mapdata <- read_csv('map.csv')

map1 <- ggplot() + theme_nothing(legend=TRUE) +
  geom_polygon(data=mapdata, aes(x=long, y=lat, group=group),fill='white', color='black')

png('map.png',width=1500, height=1000)
print(map1)
dev.off()

#Reading the data and separating out the first generation immigrants
ipums <- read_csv('Lab5.csv', col_types = cols(PERWT=col_double()))
immig <- ipums %>% filter(BPL>150)

#Aggregating 
ds <- immig %>% group_by(YEAR, STATEFIP) %>% summarise(NUMBER=sum(PERWT))

#Join this data frame to our map data frame and ordering
newmap <- mapdata %>% mutate(STATEI=as.integer(STATEFIP))

dsmap <- left_join(ds, newmap, by=(c('STATEFIP'='STATEI')))

dsmap <- dsmap %>% arrange(order)

cuts <- quantcut(ds$NUMBER, q=seq(0,1,.2))

#Population by number of first generation immigrants in each state
dscats <- ds %>% mutate(Population=factor(ifelse(NUMBER<50000, 1,
                                          ifelse(NUMBER<100000, 2,
                                          ifelse(NUMBER<500000, 3,
                                          ifelse(NUMBER<1000000, 4, 5))))))
levels(dscats$Population) <- c('1-49,999','50,000-99,999','100,000-499,999','500,000-1,000,000','1,000,000+')

#Final join of dataframe to our map data frame
dsmap <- left_join(dscats, newmap, by=c('STATEFIP'='STATEI')) %>% arrange(order)


#Plotting
  
  map2 <- map1 + scale_fill_brewer(palette='Blues')  +
    geom_polygon(data=dsmap, aes(x=long, y=lat, group=group, fill=Population), color='black') +
    labs(title='First Generation Immigrants in the United States 1900-2000,', sep='') +
    facet_wrap(~YEAR)
  
  png('map_facet3.png', width=2000, height=800)
  print(map2)
  dev.off()