Push 0.2.0

DESCRIPTION

@@ -1,6 +1,6 @@
 Package: schrute
 Title: The Entire Transcript from the Office in Tidy Format
-Version: 0.1.1
+Version: 0.2.0
 Authors@R: 
     c(person(given = "Brad",
              family = "Lindblad",
@@ -36,4 +36,4 @@ VignetteBuilder:
 Encoding: UTF-8
 LazyData: true
 Roxygen: list(markdown = TRUE)
-RoxygenNote: 6.1.1
+RoxygenNote: 7.0.2

NEWS.md

@@ -1,3 +1,6 @@
+schrute 0.1.2
+* Added IMDB ratings, votes and air dates
+
 # schrute 0.1.1
 * Minor bug fixes
 * Added writer and director feature columns

R/data-theoffice.R

@@ -1,7 +1,7 @@
 #' The entire script transcriptions from The Office
 #'
 #'
-#' @format A tibble with 55130 observations of 9 variables:
+#' @format A tibble with 55130 observations of 12 variables:
 #'   \describe{
 #'   \item{index}{row index}
 #'   \item{season}{season number}
@@ -12,6 +12,9 @@
 #'   \item{character}{name of the character saying the line}
 #'   \item{text}{words spoken by that actor}
 #'   \item{text_w_direction}{words spoken by that actor with stage direction included}
+#'   \item{imdb_rating}{rating from imdb}
+#'   \item{total_votes}{total votes for episode on imdb}
+#'   \item{air_date}{date the episode originally aired}
 #'}
 #' @source \url{https://transcripts.foreverdreaming.org}
 "theoffice"

README.md

@@ -17,8 +17,6 @@ downloads](https://cranlogs.r-pkg.org/badges/schrute)](https://cran.r-project.or
 
 Analyze and have fun with the text from the best series of all time
 
-Also available in python as the [schrutepy package](https://github.com/bradlindblad/schrutepy)
-
 ## Installation
 
 You can install the released version of schrute from
@@ -42,16 +40,19 @@ library(tibble)
 
 tibble::glimpse(schrute::theoffice)
 #> Observations: 55,130
-#> Variables: 9
-#> $ index            <int> 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, …
-#> $ season           <chr> "01", "01", "01", "01", "01", "01", "01", "01",…
-#> $ episode          <chr> "01", "01", "01", "01", "01", "01", "01", "01",…
-#> $ episode_name     <chr> "Pilot", "Pilot", "Pilot", "Pilot", "Pilot", "P…
-#> $ director         <chr> "Ken Kwapis", "Ken Kwapis", "Ken Kwapis", "Ken …
-#> $ writer           <chr> "Ricky Gervais;Stephen Merchant;Greg Daniels", …
-#> $ character        <chr> "Michael", "Jim", "Michael", "Jim", "Michael", …
-#> $ text             <chr> "All right Jim. Your quarterlies look very good…
-#> $ text_w_direction <chr> "All right Jim. Your quarterlies look very good…
+#> Variables: 12
+#> $ index            <int> 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 1…
+#> $ season           <chr> "01", "01", "01", "01", "01", "01", "01", "01", "01"…
+#> $ episode          <chr> "01", "01", "01", "01", "01", "01", "01", "01", "01"…
+#> $ episode_name     <chr> "Pilot", "Pilot", "Pilot", "Pilot", "Pilot", "Pilot"…
+#> $ director         <chr> "Ken Kwapis", "Ken Kwapis", "Ken Kwapis", "Ken Kwapi…
+#> $ writer           <chr> "Ricky Gervais;Stephen Merchant;Greg Daniels", "Rick…
+#> $ character        <chr> "Michael", "Jim", "Michael", "Jim", "Michael", "Mich…
+#> $ text             <chr> "All right Jim. Your quarterlies look very good. How…
+#> $ text_w_direction <chr> "All right Jim. Your quarterlies look very good. How…
+#> $ imdb_rating      <dbl> 7.6, 7.6, 7.6, 7.6, 7.6, 7.6, 7.6, 7.6, 7.6, 7.6, 7.…
+#> $ total_votes      <int> 3706, 3706, 3706, 3706, 3706, 3706, 3706, 3706, 3706…
+#> $ air_date         <fct> 2005-03-24, 2005-03-24, 2005-03-24, 2005-03-24, 2005…
 ```
 
 Or view the short vignette with:

cran-comments.md

@@ -1,8 +1,7 @@
-## Resubmission comments
-* Minor bug fix
+* added 3 new fields to dataset
 
 ## Test environments
-* local Linux Mint 19.3, R 3.6.1
+* local Linux Mint 19.3, R 3.6.3
 * ubuntu 14.04 (on travis-ci), R 3.6.1
 * win-builder (devel and release)
 

data-raw/get_data.R

@@ -47,6 +47,13 @@ theoffice <- final %>%
          director,writer,
          character,text,text_w_direction)
 
+imdb <- read.csv('https://github.com/raw/rfordatascience/tidytuesday/master/data/2020/2020-03-17/office_ratings.csv') %>%
+  dplyr::mutate(season = ifelse(nchar(season) < 2, paste0("0", season), season)) %>%
+  dplyr::mutate(episode = ifelse(nchar(episode) < 2, paste0("0", episode), episode))
+
+theoffice <- theoffice %>%
+  dplyr::left_join(imdb, by = c('season', 'episode')) %>%
+  dplyr::select(-title)
 
 usethis::use_data(theoffice, overwrite = TRUE)