realtor-ut.R

# set working directory
setwd("~/Projects/zillow")

# import libraries
library(tidyverse)

### REALTOR ###

# import realtor.com
# source: https://www.realtor.com/research/data/ (Inventory, Monthly)
url = 'https://econdata.s3-us-west-2.amazonaws.com/Reports/Core/RDC_Inventory_Core_Metrics_Zip_History.csv'
download.file(url, 'realtor-inventory-zip.csv')
rltr = read_csv('realtor-inventory-zip.csv')
glimpse(rltr)

# import zipcodes
url = 'https://gist.githubusercontent.com/erikgregorywebb/af025a0f9290c7bfc00797dbcc7f9bef/raw/56860e735c57dee11b0ec03917d716cf38388e4e/utah-zipcodes.csv'
download.file(url, 'utah-zipcodes.csv')
zip = read_csv('utah-zipcodes.csv')
glimpse(zip)

# inner join, filtering for utah zipcodes
rltr_ut = inner_join(x = rltr, y = zip, by = c('postal_code' = 'zipcode'))

# export
write_csv(rltr_ut, 'realtor-utah-zip.csv')

### REALTOR ###



library(lubridate)
library(scales)

rltr_ut %>% filter(postal_code == 84045) %>% arrange(month_date_yyyymm) %>%
  mutate(month_date_yyyymm = ymd(paste(month_date_yyyymm, '01', sep = ''))) %>%
  mutate(month = month(month_date_yyyymm, abbr = T, label = T)) %>% 
  mutate(season = ifelse(month %in% c('Dec', 'Jan', 'Feb'), 'Winter', 
                         ifelse(month %in% c('Mar', 'Apr', 'May'), 'Spring', 
                                ifelse(month %in% c('Jun', 'Jul', 'Aug'), 'Summer', 
                                       ifelse(month %in% c('Sep', 'Oct', 'Nov'), 'Fall', ''))))) %>%
  ggplot(., aes(x = month_date_yyyymm, y = median_listing_price)) + 
  geom_point(aes(col = season, size = 2)) + geom_line() +
  scale_y_continuous(limits = c(100000, 500000), label = comma)




library(tidyverse)
library(zipcode)
library(lubridate)

# import "market hotness" data from realtor.com
setwd("~/Projects/zillow")
url = 'https://econdata.s3-us-west-2.amazonaws.com/Reports/Hotness/RDC_Inventory_Hotness_Metrics_Zip_History.csv'
download.file(url, 'realtor-hotness-zip.csv')
raw = read_csv('realtor-hotness-zip.csv')
glimpse(raw)

# clean the dataframe
rltr = raw %>%
  mutate(month_date_yyyymm = lubridate::ymd(paste(month_date_yyyymm, '01', sep = ''))) %>%
  separate(zip_name, into = c('city', 'state'), sep = ', ', remove = F)

# import zipcodes
url = 'https://gist.githubusercontent.com/erikgregorywebb/af025a0f9290c7bfc00797dbcc7f9bef/raw/56860e735c57dee11b0ec03917d716cf38388e4e/utah-zipcodes.csv'
download.file(url, 'utah-zipcodes.csv')
zip = read_csv('utah-zipcodes.csv')
glimpse(zip)

# inner join, filtering for utah zipcodes
rltr_ut = inner_join(x = select(rltr, -city), y = zip, by = c('postal_code' = 'zipcode'))
glimpse(rltr_ut)

# export
write_csv(rltr_ut, 'realtor-utah-hotness-by-zip.csv')