moved DCF-2015 data to separate file

mdsr-book · Aug 23, 2016 · b5fef9e · b5fef9e
1 parent 21a57a1
commit b5fef9e
Show file tree

Hide file tree

Showing 13 changed files with 95 additions and 83 deletions.
diff --git a/DESCRIPTION b/DESCRIPTION
@@ -1,6 +1,6 @@
 Package: mdsr
 Title: Complement to Forthcoming Book: Modern Data Science with R
-Version: 0.1.2.9007
+Version: 0.1.2.9008
 Date: 2016-06-23
 Authors@R: as.person(c(
     "Ben Baumer <ben.baumer@gmail.com> [aut, cre]",

diff --git a/R/data.R b/R/data.R
@@ -14,18 +14,19 @@
 #'  \item{WPct}{winning percentage}
 #'  \item{attendance}{number of fans in attendance}
 #'  \item{normAttend}{number of fans in attendance, relative to the team with
-#'#'the highest attendance in this sample (the 2008 New York Yankees)}
+#'  the highest attendance in this sample (the 2008 New York Yankees)}
 #'  \item{payroll}{the sum of the salaries of the players on each team. Note
-#'#'that this number is only an estimate of the actual team payroll -- and may
-#'#'not even be a very good one. Salaries are accumulated from \code{\link[Lahman]{Salaries}}}
+#'  that this number is only an estimate of the actual team payroll -- and may
+#'  not even be a very good one. Salaries are accumulated from \code{\link[Lahman]{Salaries}}}
 #'  \item{metroPop}{the size of the team's home city's metropolitan population, according
-#'#'to Wikipedia and the 2010 US Census}
+#'  to Wikipedia and the 2010 US Census}
 #'  \item{name}{the full name of the team}
 #' }
 #' 
 #' @seealso \code{\link[Lahman]{Teams}}
 #' 
-#' @source The \code{\link[Lahman]{Teams}} data set and \url{https://en.wikipedia.org/wiki/List_of_Metropolitan_Statistical_Areas}
+#' @source The \code{\link[Lahman]{Teams}} table from \code{\link{Lahman}} 
+#' and \url{https://en.wikipedia.org/wiki/List_of_Metropolitan_Statistical_Areas}
 #' 
 "MLB_teams" 
 
@@ -66,8 +67,20 @@
 #' 
 "CIACountries"
 
-#' election statistics
+#' Election Statistics
 #' @docType data
+#' @format An object of class \\code{tbl_df} (inherits from \\code{tbl}, \\code{data.frame}) 
+#' with 117 rows and 13 columns.
+#' \describe{
+#' \item{Ward}{Name of the country} 
+#' \item{Precinct}{number of people, 2119}
+#' \item{Registered.Voters.at.7am}{area (sq km), 2147} 
+#' \item{Voters.Registering.at.Polls}{Crude oil - production (bbl/day), 2241}
+#' \item{gdp}{Gross Domestic Product per capita ($/person), 2001}
+#' \item{educ}{education spending (\% of GDP), 2206}
+#' \item{roadways}{Roadways per unit area (km/sq km), 2085}
+#' \item{net_users}{Fraction of Internet users (\% of population), 2153}
+#' }
 "Elections"
 
 #' Cherry Blossom runs

diff --git a/R/scidb.R b/R/scidb.R
@@ -1,11 +1,10 @@
 #' src_scidb
-#' 
-#' @description Connect to the scidb server at Smith
+#' @description Connect to the scidb server at Smith College.
 #' 
 #' @param dbname the name of the database to which you want to connect
 #' @param ... arguments passed to \code{\link[dplyr]{src_mysql}} or \code{\link[DBI]{dbConnect}}
 #' 
-#' @details this is a public, read-only account. Any abuse will be considered a 
+#' @details This is a public, read-only account. Any abuse will be considered a 
 #' hostile act. 
 #' 
 #' @return For \code{\link{src_mysql}}, a \code{\link[dplyr]{src_mysql}} object
@@ -26,8 +25,6 @@ src_scidb <- function(dbname, ...) {
                    user = "mth292", password = "RememberPi")
 }
 
-#' Create a DBI connection to the scidb server at Smith
-#' 
 #' @rdname src_scidb
 #' @export
 #'  
@@ -47,9 +44,6 @@ dbConnect_scidb <- function(dbname, ...) {
             user = "mth292", password = "RememberPi")
 }
 
-#' Create a string of arguments for the scidb server at Smith to be used on the
-#' command line
-#' 
 #' @rdname src_scidb
 #' @export
 #' 
@@ -59,8 +53,9 @@ dbConnect_scidb <- function(dbname, ...) {
 #' @seealso \code{\link[knitr]{opts_chunk}}
 #' @examples 
 #' 
-#' library(knitr)
-#' opts_chunk$set(engine.opts = mysql_scidb("airlines"))
+#' if (require(knitr)) {
+#'   opts_chunk$set(engine.opts = mysql_scidb("airlines"))
+#' }
 
 mysql_scidb <- function(dbname, ...) {
   paste("-h scidb.smith.edu -u mth292 -pRememberPi -t", dbname)

diff --git a/data-raw/DCF-2015.R b/data-raw/DCF-2015.R
@@ -0,0 +1,44 @@
+# Elections
+url <- "https://raw.githubusercontent.com/dtkaplan/DCF-2015/master/Book/Sections/Data/electionStatistics.csv"
+download.file(url, destfile = "inst/extdata/electionStatistics.csv")
+
+Elections <- readr::read_csv("inst/extdata/electionStatistics.csv")
+save(Elections, file = "data/Elections.rda", compress = "xz")
+
+# Cherry
+url <- "https://raw.githubusercontent.com/dtkaplan/DCF-2015/master/Book/Sections/Data/Cherry-Blossom-Longitudinal.csv"
+Cherry <- read.csv(url)
+Cherry <- readr::read_csv("inst/extdata/cherry.csv")
+save(Cherry, file = "data/Cherry.rda", compress = "xz")
+
+# nciNetwork
+url <- "https://raw.githubusercontent.com/dtkaplan/DCF-2015/master/Book/Sections/Data/nciNetwork.csv?token=ACpUw4Vh3a3YvWLDcGd9nLbnBX6ZiFUlks5XxNu_wA%3D%3D"
+download.file(url, destfile = "inst/extdata/nciNetwork.csv")
+Cancer <- readr::read_csv("inst/extdata/nciNetwork.csv")
+save(Cancer, file = "data/Cancer.rda", compress = "xz")
+
+
+# VotesS1-tally
+# download.file("https://raw.githubusercontent.com/dtkaplan/DCF-2015/master/Book/Sections/Data/VotesS1-tally.csv", "inst/extdata/VotesS1-tally.csv")
+Votes <- read.csv("inst/extdata/VotesS1-tally.csv", skip = 1) %>%
+  rename(bill = VOTE) %>%
+  tidyr::gather(key = "name", value = "vote", -bill) %>%
+  mutate(name = gsub("\\.\\.", ", ", name)) %>%
+  mutate(name = gsub("\\.", " ", name))
+Encoding(levels(Votes$bill)) <- "latin1"
+levels(Votes$bill) <- iconv(levels(Votes$bill), from = "latin1", to = "UTF-8")
+Parties <- read.csv("inst/extdata/VotesS1-tally.csv",
+                    header = FALSE, nrows = 2, row.names = 1, 
+                    stringsAsFactors = FALSE) %>%
+  t() %>%
+  as.data.frame() %>%
+  rename(party = PARTY, name = VOTE) %>%
+  mutate(party = as.character(party), name = as.character(name)) %>%
+  mutate(name = gsub("-", " ", name))
+# check to see that all names match
+setdiff(Parties$name, unique(Votes$name))
+save(Votes, file = "data/Votes.rda", compress = "xz")
+save(Parties, file = "data/Parties.rda", compress = "xz")
+
+
+
diff --git a/data-raw/DataComputing.R b/data-raw/DataComputing.R
@@ -47,12 +47,6 @@ cat(create_roxygen(parse_file("https://raw.githubusercontent.com/DataComputing/D
 load("data/Minneapolis2013.rda")
 save(Minneapolis2013, file = "data/Minneapolis2013.rda", compress = "xz")
 
-
-# NCI for graph
-Cancer <- read.csv("inst/extdata/nciNetwork.csv")
-save(Cancer, file = "data/Cancer.rda", compress = "xz")
-download.file("https://github.com/DataComputing/DataComputing/raw/master/R/NetworkHelpers.R", "R/NetworkHelpers.R")
-
 # WorldCities
 download.file("https://github.com/DataComputing/DataComputing/raw/master/data/WorldCities.rda", "data/WorldCities.rda")
 cat(create_roxygen(parse_file("https://raw.githubusercontent.com/DataComputing/DataComputing/master/man/WorldCities.Rd")), sep = "\n")
@@ -61,24 +55,3 @@ Encoding(WorldCities$name) <- "latin1"
 WorldCities$name <- iconv(WorldCities$name, from = "latin1", to = "UTF-8")
 save(WorldCities, file = "data/WorldCities.rda", compress = "xz")
 
-# VotesS1-tally
-# download.file("https://raw.githubusercontent.com/dtkaplan/DCF-2015/master/Book/Sections/Data/VotesS1-tally.csv", "inst/extdata/VotesS1-tally.csv")
-Votes <- read.csv("inst/extdata/VotesS1-tally.csv", skip = 1) %>%
-  rename(bill = VOTE) %>%
-  tidyr::gather(key = "name", value = "vote", -bill) %>%
-  mutate(name = gsub("\\.\\.", ", ", name)) %>%
-  mutate(name = gsub("\\.", " ", name))
-Encoding(levels(Votes$bill)) <- "latin1"
-levels(Votes$bill) <- iconv(levels(Votes$bill), from = "latin1", to = "UTF-8")
-Parties <- read.csv("inst/extdata/VotesS1-tally.csv",
-                     header = FALSE, nrows = 2, row.names = 1, 
-                    stringsAsFactors = FALSE) %>%
-  t() %>%
-  as.data.frame() %>%
-  rename(party = PARTY, name = VOTE) %>%
-  mutate(party = as.character(party), name = as.character(name)) %>%
-  mutate(name = gsub("-", " ", name))
-# check to see that all names match
-setdiff(Parties$name, unique(Votes$name))
-save(Votes, file = "data/Votes.rda", compress = "xz")
-save(Parties, file = "data/Parties.rda", compress = "xz")
diff --git a/data-raw/electionStatistics.R b/data-raw/electionStatistics.R
diff --git a/data/Cancer.rda b/data/Cancer.rda
diff --git a/data/Cherry.rda b/data/Cherry.rda
diff --git a/data/Elections.rda b/data/Elections.rda
diff --git a/man/Cancer.Rd b/man/Cancer.Rd
diff --git a/man/Elections.Rd b/man/Elections.Rd
diff --git a/man/MLB_teams.Rd b/man/MLB_teams.Rd
diff --git a/man/src_scidb.Rd b/man/src_scidb.Rd