TreefortBnB_analysis.R

library(dplyr)

raw_data <- read.csv("https://s3.amazonaws.com/pix-media/Data+for+TreefortBnB+Puzzle.csv") %>%
  mutate(City = tolower(City))

simpleCap <- function(x) {
  s <- strsplit(x, " ")[[1]]
  paste(toupper(substring(s, 1, 1)), substring(s, 2),
        sep = "", collapse = " ")
}

city_statecount_data <-
  raw_data %>%
  group_by(City, State) %>%
  do(data.frame(cs_count=length(.$Unique.id))) %>%
  subset(cs_count >= 5) %>%
  select(City, State)

summary_data <-
  raw_data %>%
  merge(city_statecount_data) %>%
  group_by(City, State) %>%
  do(data.frame(medianprice = median(.$X..Price))) %>%
  rowwise() %>%
  mutate(City = simpleCap(City)) %>%
  arrange(desc(medianprice))

write.csv(summary_data[1:100, ], "TreefortBNB_summary.csv", row.names=F)