Poll residential power rates for Top 50 Metro regions

poweR.R

library(dplyr)
library(tidyr)
library(magrittr)
library(httr)
library(ggplot2)
library(ggvis)

#Inspired by original utility rate API post at 
#http://www.numbrcrunch.com/blog/using-the-httr-package-to-retrieve-data-from-apis-in-r


census_url <- "http://www.census.gov/popest/data/metro/totals/2013/files/CBSA-EST2013-alldata.csv"

s <- read.csv(url(census_url), stringsAsFactors=F)

top_50_cities <- s %>% filter(LSAD=="Metropolitan Division") %>% arrange(desc(POPESTIMATE2013)) %>% head(50) %>% select(NAME, pop=POPESTIMATE2013) %>%
  separate(NAME, c("city", "state"), sep=", ", remove=F)

#key <- "Insert your key here"


# Combining both the Google Maps API and the Data.gov API to get utility rates by city - preferred
google_url <- "https://maps.googleapis.com/maps/api/geocode/json"
gov_url <- "http://api.data.gov/nrel/utility_rates/v3.json"
geoCode <- function(address,verbose=FALSE) {
  r <- GET(google_url, query = list(address = address))
  stop_for_status(r)
  result1 <- content(r)
  
  if (!identical(result1$status, "OK")) {
    warning("Please input a valid US address.", call. = FALSE)
    return(c(NA,NA,NA,NA,NA,NA))
  }
  
  s <- GET(gov_url, query = list(api_key = key, lat = result1$results[[1]]$geometry$location$lat, lon = result1$results[[1]]$geometry$location$lng))
  stop_for_status(s)
  result2 <- content(s)
  
  if (result2$outputs$utility_name == "no data") {
    warning("Please input a valid US address.", call. = FALSE)
    return(c(NA,NA,NA,NA,NA,NA))
  }
  
  first <- result1$results[[1]]
  second <- result2$outputs
  list(
    lat = first$geometry$location$lat,
    lon = first$geometry$location$lng,
    type = first$geometry$location_type,
    address = first$formatted_address,
    utility = second$utility_info[[1]]$utility_name,
    residential_rate_kwh = second$residential
  )
}

geoCode(top_50_cities$NAME[1])

rates <- lapply(top_50_cities$NAME, geoCode)
rates <- data.frame(matrix(unlist(rates), ncol=6, byrow=T))

top_50_cities$rate  <- rates$X6
top_50_cities$utility  <- rates$X5

top_50_cities %>% mutate(rate=as.numeric(levels(rate))[rate]*100) %>%
  mjs_plot(x=NAME, y=rate, width=500, height=500) %>%
  mjs_bar()

plot <- top_50_cities %>% mutate(rate=as.numeric(levels(rate))[rate]*100)  %>% 
  arrange(desc(rate))
plot$NAME <- factor(plot$NAME, levels = plot[order(plot$rate), "NAME"])
#levels(plot$NAME) <- levels(plot$NAME)[order(plot$rate)]
ggplot(plot, aes(NAME, rate)) + geom_bar(stat="identity", fill="steelblue") + coord_flip() + 
  ylab("Electrical rate (cents/kwh)") +
  xlab("Metro Region") +
  ggtitle("Electrical Rate for Top 50 Metro Regions") +
  geom_text(aes(NAME, rate, label=rate), hjust=0) +
  theme_bw()

plot %>%
  ggvis(~NAME, ~rate) %>%
  layer_bars() %>%
  add_axis("x", properties=axis_props(
    labels=list(angle=45, align="left")))