Add new txhousing dataset

NEWS

@@ -1,6 +1,10 @@
 ggplot2 1.0.1.9xxx
 ----------------------------------------------------------------
 
+* New `txhousing` dataset containing information about the Texas housing
+  market. Useful for examples that need multiple time series, and for
+  demonstrating model+vis methods.
+
 * The default font size in `geom_text()` has been decreased from 5mm (14 pts)
   to 3.8 mm (11 pts) to match the new default theme sizes.
 

R/ggplot2.r

@@ -183,3 +183,21 @@ NULL
 #' \item{col}{Colour name}
 #' }
 "luv_colours"
+
+#' Housing sales in TX.
+#'
+#' Information about the housing market in Texas provided by the TAMU
+#' real estate center, \url{http://recenter.tamu.edu/}.
+#'
+#' @format A data frame with 8602 observations and 9 variables:
+#' \itemize{
+#' \item{city}{Name of MLS area}
+#' \item{year,month,date}{Date}
+#' \item{sales}{Number of sales}
+#' \item{volume}{Total value of sales}
+#' \item{median}{Median sale price}
+#' \item{listings}{Total active listings}
+#' \item{inventory}{"Months inventory": amount of time it would take to sell
+#'   all current listings at current pace of sales.}
+#' }
+"txhousing"

data-raw/tx-housing.R

@@ -0,0 +1,64 @@
+library(rvest)
+library(tidyr)
+library(readr)
+library(dplyr)
+
+# Find list of all pages -------------------------------------------------------
+root <- read_html("http://recenter.tamu.edu/Data/hs/")
+links <- root %>%
+  html_nodes(".threecol a")
+pages <- links %>%
+  html_attr("href") %>%
+  url_absolute(xml_url(root)) %>%
+  setNames(html_text(links))
+
+# Extract table from each page -------------------------------------------------
+to_char <- function(df) {
+  df[] <- lapply(df, as.character)
+  df
+}
+
+tamu_table <- . %>%
+  html() %>%
+  html_node(".dataTable") %>%
+  html_table()
+
+tables <- lapply(pages, tamu_table)
+data <- lapply(tables, . %>% .[-1, ] %>% to_char) %>%
+  Map(function(df, city) {
+    df$city <- city
+    df
+  }, ., names(.)) %>%
+  bind_rows() %>%
+  as_data_frame()
+
+data[data == "-"] <- NA
+
+months <- c("Jan", "Feb", "Mar", "Apr", "May", "Jun", "Jul", "Aug", "Sep",
+  "Oct", "Nov", "Dec")
+
+txhousing <- data %>%
+  mutate(
+    Sales         = parse_numeric(Sales),
+    DollarVolume  = parse_numeric(DollarVolume),
+    AveragePrice  = parse_numeric(AveragePrice),
+    MedianPrice   = parse_numeric(MedianPrice),
+    TotalListings = parse_numeric(TotalListings),
+    MonthsInventory = parse_numeric(MonthsInventory)
+  ) %>%
+  extract(Date, c("Year", "Month"), "(\\d*)-?([a-zA-Z]*)", convert = TRUE) %>%
+  mutate(
+    Year = zoo::na.locf(ifelse(Year == "", NA, Year)),
+    Month = match(Month, months)) %>%
+  select(city, year = Year, month = Month, sales = Sales,
+    volume = DollarVolume, average = AveragePrice, median = MedianPrice,
+    listings = TotalListings, inventory = MonthsInventory) %>%
+  mutate(date = year + (month - 1) / 12) %>%
+  # Don't need totals & Palestine is v. low quality
+  filter(!(city %in% c("Texas Totals", "Palestine"))) %>%
+  # Reduce file size
+  filter(year >= 2000) %>%
+  select(-average)
+
+write.csv(txhousing, "data-raw/tx-housing.csv", row.names = FALSE, quote = FALSE)
+devtools::use_data(txhousing, overwrite = TRUE)