source("acs_stem.R") # universe = USA usa <- read.dta("ipums13.dta") year <- 2013 print(names(usa)) print(sprintf("usa[%d] = %d", dim(usa)[1], sum(usa$perwt))) # state = TX state <- usa[as.integer(usa$statefip)==44,] print(sprintf("state[%d] = %d", dim(state)[1], sum(state$perwt))) # area1 = [15] "Austin-Round Rock, TX" area1 <- state[as.integer(state$MET2013) == 15,] print(sprintf("area1[%d] = %d", dim(area1)[1], sum(area1$perwt))) # area2 = [57] "Dallas-Fort Worth-Arlington, TX area2 <- state[as.integer(state$MET2013) == 57,] print(sprintf("area2[%d] = %d", dim(area2)[1], sum(area2$perwt))) # area3 = [100] "Houston-The Woodlands-Sugar Land, TX" area3 <- state[as.integer(state$MET2013) == 100,] print(sprintf("area3[%d] = %d", dim(area3)[1], sum(area3$perwt))) # area4 = [214] "San Antonio-New Braunfels, TX" area4 <- state[as.integer(state$MET2013) == 214,] print(sprintf("area4[%d] = %d", dim(area4)[1], sum(area4$perwt))) main <- c("Texas Workforce", "Texas Workforce") titles1 <- c("","","","") titles2 <- c("Austin-Round Rock", "Dallas-Fort Worth-Arlington", "Houston-The Woodlands-Sugar Land", "San Antonio-New Braunfels") print_tables(area1, area2, area3, area4, year, main, titles1, titles2, "tx") labels <- c("Austin", "Dallas-Ft Worth", "Houston", "San Antonio") title <- "Software Developers, Applications, System Software" plot_percent(area1, area2, area3, area4, 2013, c(0,70), c(1020), title, labels) title <- "All Computer and Mathematical" plot_percent(area1, area2, area3, area4, 2013, c(0,70), c(110,1000:1249), title, labels)