├── .Rprofile
├── Dockerfile
├── src.Rproj
├── packrat
    ├── packrat.opts
    ├── init.R
    └── packrat.lock
├── README.md
├── .gitignore
├── LICENSE
└── genre_analysis.Rmd


/.Rprofile:
--------------------------------------------------------------------------------
1 | #### -- Packrat Autoloader (version 0.5.0) -- ####
2 | source("packrat/init.R")
3 | #### -- End Packrat Autoloader -- ####
4 | 


--------------------------------------------------------------------------------
/Dockerfile:
--------------------------------------------------------------------------------
1 | FROM rocker/rstudio:latest
2 | 
3 | # Install system packages
4 | RUN apt-get update && \
5 |     apt-get install -y --no-install-recommends git zlib1g-dev libxml2-dev && \
6 |     apt-get clean && \
7 |     rm -rf /var/lib/apt/lists/*


--------------------------------------------------------------------------------
/src.Rproj:
--------------------------------------------------------------------------------
 1 | Version: 1.0
 2 | 
 3 | RestoreWorkspace: No
 4 | SaveWorkspace: No
 5 | AlwaysSaveHistory: No
 6 | 
 7 | EnableCodeIndexing: Yes
 8 | UseSpacesForTab: Yes
 9 | NumSpacesForTab: 4
10 | Encoding: UTF-8
11 | 
12 | RnwWeave: Sweave
13 | LaTeX: pdfLaTeX
14 | 
15 | AutoAppendNewline: Yes
16 | StripTrailingWhitespace: Yes
17 | LineEndingConversion: Posix
18 | 


--------------------------------------------------------------------------------
/packrat/packrat.opts:
--------------------------------------------------------------------------------
 1 | auto.snapshot: FALSE
 2 | use.cache: FALSE
 3 | print.banner.on.startup: auto
 4 | vcs.ignore.lib: TRUE
 5 | vcs.ignore.src: TRUE
 6 | external.packages: 
 7 | local.repos: 
 8 | load.external.packages.on.startup: TRUE
 9 | ignored.packages: 
10 | ignored.directories:
11 |     data
12 |     inst
13 | quiet.package.installation: TRUE
14 | snapshot.recommended.packages: FALSE
15 | snapshot.fields:
16 |     Imports
17 |     Depends
18 |     LinkingTo
19 | symlink.system.packages: TRUE
20 | 


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
 1 | # movies_dataset_eda
 2 | 
 3 | A toy project mainly for practicing rstudio/gt
 4 | 
 5 | [Blog post](https://medium.com/the-artificial-impostor/playing-with-rstudio-gt-r-package-2f37a340c23f).
 6 | 
 7 | ## Docker Instructions
 8 | 
 9 | Go into the project folder and build the Docker:
10 | 
11 | ```
12 | docker build -t rstudio .
13 | ```
14 | 
15 | Start a container:
16 | 
17 | ```
18 | docker run -d -v $(pwd):/home/rstudio/src -e USERID=1000 --name <container_name> -e PASSWORD=<password> -p 8787:8787 rstudio
19 | ```
20 | 
21 | Finally, visit http://localhost:8787 to access RStudio web interface.
22 | 
23 | Reference: [More Portable, Reproducible R Development Environment](https://medium.com/the-artificial-impostor/more-portable-reproducible-r-development-environment-c3074df7a6a8)


--------------------------------------------------------------------------------
/.gitignore:
--------------------------------------------------------------------------------
 1 | # History files
 2 | .Rhistory
 3 | .Rapp.history
 4 | 
 5 | # Session Data files
 6 | .RData
 7 | 
 8 | # Example code in package build process
 9 | *-Ex.R
10 | 
11 | # Output files from R CMD build
12 | /*.tar.gz
13 | 
14 | # Output files from R CMD check
15 | /*.Rcheck/
16 | 
17 | # RStudio files
18 | .Rproj.user/
19 | 
20 | # produced vignettes
21 | vignettes/*.html
22 | vignettes/*.pdf
23 | 
24 | # OAuth2 token, see https://github.com/hadley/httr/releases/tag/v0.3
25 | .httr-oauth
26 | 
27 | # knitr and R markdown default cache directories
28 | /*_cache/
29 | /cache/
30 | 
31 | # Temporary files created by R markdown
32 | *.utf8.md
33 | *.knit.md
34 | 
35 | # Shiny token, see https://shiny.rstudio.com/articles/shinyapps.html
36 | rsconnect/
37 | 
38 | # packrat
39 | packrat/lib*/
40 | packrat/src/
41 | 
42 | .Rproj.user
43 | 


--------------------------------------------------------------------------------
/LICENSE:
--------------------------------------------------------------------------------
 1 | MIT License
 2 | 
 3 | Copyright (c) 2019 CeShine Lee
 4 | 
 5 | Permission is hereby granted, free of charge, to any person obtaining a copy
 6 | of this software and associated documentation files (the "Software"), to deal
 7 | in the Software without restriction, including without limitation the rights
 8 | to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
 9 | copies of the Software, and to permit persons to whom the Software is
10 | furnished to do so, subject to the following conditions:
11 | 
12 | The above copyright notice and this permission notice shall be included in all
13 | copies or substantial portions of the Software.
14 | 
15 | THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
16 | IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
17 | FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
18 | AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
19 | LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
20 | OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
21 | SOFTWARE.
22 | 


--------------------------------------------------------------------------------
/packrat/init.R:
--------------------------------------------------------------------------------
  1 | local({
  2 | 
  3 |   ## Helper function to get the path to the library directory for a
  4 |   ## given packrat project.
  5 |   getPackratLibDir <- function(projDir = NULL) {
  6 |     path <- file.path("packrat", "lib", R.version$platform, getRversion())
  7 | 
  8 |     if (!is.null(projDir)) {
  9 | 
 10 |       ## Strip trailing slashes if necessary
 11 |       projDir <- sub("/+$", "", projDir)
 12 | 
 13 |       ## Only prepend path if different from current working dir
 14 |       if (!identical(normalizePath(projDir), normalizePath(getwd())))
 15 |         path <- file.path(projDir, path)
 16 |     }
 17 | 
 18 |     path
 19 |   }
 20 | 
 21 |   ## Ensure that we set the packrat library directory relative to the
 22 |   ## project directory. Normally, this should be the working directory,
 23 |   ## but we also use '.rs.getProjectDirectory()' if necessary (e.g. we're
 24 |   ## rebuilding a project while within a separate directory)
 25 |   libDir <- if (exists(".rs.getProjectDirectory"))
 26 |     getPackratLibDir(.rs.getProjectDirectory())
 27 |   else
 28 |     getPackratLibDir()
 29 | 
 30 |   ## Unload packrat in case it's loaded -- this ensures packrat _must_ be
 31 |   ## loaded from the private library. Note that `requireNamespace` will
 32 |   ## succeed if the package is already loaded, regardless of lib.loc!
 33 |   if ("packrat" %in% loadedNamespaces())
 34 |     try(unloadNamespace("packrat"), silent = TRUE)
 35 | 
 36 |   if (suppressWarnings(requireNamespace("packrat", quietly = TRUE, lib.loc = libDir))) {
 37 | 
 38 |     # Check 'print.banner.on.startup' -- when NA and RStudio, don't print
 39 |     print.banner <- packrat::get_opts("print.banner.on.startup")
 40 |     if (print.banner == "auto" && is.na(Sys.getenv("RSTUDIO", unset = NA))) {
 41 |       print.banner <- TRUE
 42 |     } else {
 43 |       print.banner <- FALSE
 44 |     }
 45 |     return(packrat::on(print.banner = print.banner))
 46 |   }
 47 | 
 48 |   ## Escape hatch to allow RStudio to handle bootstrapping. This
 49 |   ## enables RStudio to provide print output when automagically
 50 |   ## restoring a project from a bundle on load.
 51 |   if (!is.na(Sys.getenv("RSTUDIO", unset = NA)) &&
 52 |       is.na(Sys.getenv("RSTUDIO_PACKRAT_BOOTSTRAP", unset = NA))) {
 53 |     Sys.setenv("RSTUDIO_PACKRAT_BOOTSTRAP" = "1")
 54 |     setHook("rstudio.sessionInit", function(...) {
 55 |       # Ensure that, on sourcing 'packrat/init.R', we are
 56 |       # within the project root directory
 57 |       if (exists(".rs.getProjectDirectory")) {
 58 |         owd <- getwd()
 59 |         setwd(.rs.getProjectDirectory())
 60 |         on.exit(setwd(owd), add = TRUE)
 61 |       }
 62 |       source("packrat/init.R")
 63 |     })
 64 |     return(invisible(NULL))
 65 |   }
 66 | 
 67 |   ## Bootstrapping -- only performed in interactive contexts,
 68 |   ## or when explicitly asked for on the command line
 69 |   if (interactive() || "--bootstrap-packrat" %in% commandArgs(TRUE)) {
 70 | 
 71 |     needsRestore <- "--bootstrap-packrat" %in% commandArgs(TRUE)
 72 | 
 73 |     message("Packrat is not installed in the local library -- ",
 74 |             "attempting to bootstrap an installation...")
 75 | 
 76 |     ## We need utils for the following to succeed -- there are calls to functions
 77 |     ## in 'restore' that are contained within utils. utils gets loaded at the
 78 |     ## end of start-up anyhow, so this should be fine
 79 |     library("utils", character.only = TRUE)
 80 | 
 81 |     ## Install packrat into local project library
 82 |     packratSrcPath <- list.files(full.names = TRUE,
 83 |                                  file.path("packrat", "src", "packrat")
 84 |     )
 85 | 
 86 |     ## No packrat tarballs available locally -- try some other means of installation
 87 |     if (!length(packratSrcPath)) {
 88 | 
 89 |       message("> No source tarball of packrat available locally")
 90 | 
 91 |       ## There are no packrat sources available -- try using a version of
 92 |       ## packrat installed in the user library to bootstrap
 93 |       if (requireNamespace("packrat", quietly = TRUE) && packageVersion("packrat") >= "0.2.0.99") {
 94 |         message("> Using user-library packrat (",
 95 |                 packageVersion("packrat"),
 96 |                 ") to bootstrap this project")
 97 |       }
 98 | 
 99 |       ## Couldn't find a user-local packrat -- try finding and using devtools
100 |       ## to install
101 |       else if (requireNamespace("devtools", quietly = TRUE)) {
102 |         message("> Attempting to use devtools::install_github to install ",
103 |                 "a temporary version of packrat")
104 |         library(stats) ## for setNames
105 |         devtools::install_github("rstudio/packrat")
106 |       }
107 | 
108 |       ## Try downloading packrat from CRAN if available
109 |       else if ("packrat" %in% rownames(available.packages())) {
110 |         message("> Installing packrat from CRAN")
111 |         install.packages("packrat")
112 |       }
113 | 
114 |       ## Fail -- couldn't find an appropriate means of installing packrat
115 |       else {
116 |         stop("Could not automatically bootstrap packrat -- try running ",
117 |              "\"'install.packages('devtools'); devtools::install_github('rstudio/packrat')\"",
118 |              "and restarting R to bootstrap packrat.")
119 |       }
120 | 
121 |       # Restore the project, unload the temporary packrat, and load the private packrat
122 |       if (needsRestore)
123 |         packrat::restore(prompt = FALSE, restart = TRUE)
124 | 
125 |       ## This code path only reached if we didn't restart earlier
126 |       unloadNamespace("packrat")
127 |       requireNamespace("packrat", lib.loc = libDir, quietly = TRUE)
128 |       return(packrat::on())
129 | 
130 |     }
131 | 
132 |     ## Multiple packrat tarballs available locally -- try to choose one
133 |     ## TODO: read lock file and infer most appropriate from there; low priority because
134 |     ## after bootstrapping packrat a restore should do the right thing
135 |     if (length(packratSrcPath) > 1) {
136 |       warning("Multiple versions of packrat available in the source directory;",
137 |               "using packrat source:\n- ", shQuote(packratSrcPath))
138 |       packratSrcPath <- packratSrcPath[[1]]
139 |     }
140 | 
141 | 
142 |     lib <- file.path("packrat", "lib", R.version$platform, getRversion())
143 |     if (!file.exists(lib)) {
144 |       dir.create(lib, recursive = TRUE)
145 |     }
146 | 
147 |     message("> Installing packrat into project private library:")
148 |     message("- ", shQuote(lib))
149 | 
150 |     surround <- function(x, with) {
151 |       if (!length(x)) return(character())
152 |       paste0(with, x, with)
153 |     }
154 | 
155 | 
156 |     ## Invoke install.packages() in clean R session
157 |     peq <- function(x, y) paste(x, y, sep = " = ")
158 |     installArgs <- c(
159 |       peq("pkgs", surround(packratSrcPath, with = "'")),
160 |       peq("lib", surround(lib, with = "'")),
161 |       peq("repos", "NULL"),
162 |       peq("type", surround("source", with = "'"))
163 |     )
164 | 
165 |     fmt <- "utils::install.packages(%s)"
166 |     installCmd <- sprintf(fmt, paste(installArgs, collapse = ", "))
167 | 
168 |     ## Write script to file (avoid issues with command line quoting
169 |     ## on R 3.4.3)
170 |     installFile <- tempfile("packrat-bootstrap", fileext = ".R")
171 |     writeLines(installCmd, con = installFile)
172 |     on.exit(unlink(installFile), add = TRUE)
173 | 
174 |     fullCmd <- paste(
175 |       surround(file.path(R.home("bin"), "R"), with = "\""),
176 |       "--vanilla",
177 |       "--slave",
178 |       "-f",
179 |       surround(installFile, with = "\"")
180 |     )
181 |     system(fullCmd)
182 | 
183 |     ## Tag the installed packrat so we know it's managed by packrat
184 |     ## TODO: should this be taking information from the lockfile? this is a bit awkward
185 |     ## because we're taking an un-annotated packrat source tarball and simply assuming it's now
186 |     ## an 'installed from source' version
187 | 
188 |     ## -- InstallAgent -- ##
189 |     installAgent <- "InstallAgent: packrat 0.5.0"
190 | 
191 |     ## -- InstallSource -- ##
192 |     installSource <- "InstallSource: source"
193 | 
194 |     packratDescPath <- file.path(lib, "packrat", "DESCRIPTION")
195 |     DESCRIPTION <- readLines(packratDescPath)
196 |     DESCRIPTION <- c(DESCRIPTION, installAgent, installSource)
197 |     cat(DESCRIPTION, file = packratDescPath, sep = "\n")
198 | 
199 |     # Otherwise, continue on as normal
200 |     message("> Attaching packrat")
201 |     library("packrat", character.only = TRUE, lib.loc = lib)
202 | 
203 |     message("> Restoring library")
204 |     if (needsRestore)
205 |       packrat::restore(prompt = FALSE, restart = FALSE)
206 | 
207 |     # If the environment allows us to restart, do so with a call to restore
208 |     restart <- getOption("restart")
209 |     if (!is.null(restart)) {
210 |       message("> Packrat bootstrap successfully completed. ",
211 |               "Restarting R and entering packrat mode...")
212 |       return(restart())
213 |     }
214 | 
215 |     # Callers (source-erers) can define this hidden variable to make sure we don't enter packrat mode
216 |     # Primarily useful for testing
217 |     if (!exists(".__DONT_ENTER_PACKRAT_MODE__.") && interactive()) {
218 |       message("> Packrat bootstrap successfully completed. Entering packrat mode...")
219 |       packrat::on()
220 |     }
221 | 
222 |     Sys.unsetenv("RSTUDIO_PACKRAT_BOOTSTRAP")
223 | 
224 |   }
225 | 
226 | })
227 | 


--------------------------------------------------------------------------------
/packrat/packrat.lock:
--------------------------------------------------------------------------------
  1 | PackratFormat: 1.4
  2 | PackratVersion: 0.5.0
  3 | RVersion: 3.5.1
  4 | Repos: CRAN=https://cran.rstudio.com/
  5 | 
  6 | Package: BH
  7 | Source: CRAN
  8 | Version: 1.66.0-1
  9 | Hash: 4cc8883584b955ed01f38f68bc03af6d
 10 | 
 11 | Package: DBI
 12 | Source: CRAN
 13 | Version: 1.0.0
 14 | Hash: 6abedd7919c4457604c0aa44529a6683
 15 | 
 16 | Package: R6
 17 | Source: CRAN
 18 | Version: 2.3.0
 19 | Hash: 8eccabbf292b5aba632985cde6406fc3
 20 | 
 21 | Package: RColorBrewer
 22 | Source: CRAN
 23 | Version: 1.1-2
 24 | Hash: c0d56cd15034f395874c870141870c25
 25 | 
 26 | Package: Rcpp
 27 | Source: CRAN
 28 | Version: 1.0.0
 29 | Hash: c7273c0f0bc9f5e41f4c52a8cf571f0f
 30 | 
 31 | Package: assertthat
 32 | Source: CRAN
 33 | Version: 0.2.0
 34 | Hash: e8805df54c65ac96d50235c44a82615c
 35 | 
 36 | Package: backports
 37 | Source: CRAN
 38 | Version: 1.1.3
 39 | Hash: a0b8191e6bd2fe71aadd4678bb8f3c98
 40 | 
 41 | Package: base64enc
 42 | Source: CRAN
 43 | Version: 0.1-3
 44 | Hash: c590d29e555926af053055e23ee79efb
 45 | 
 46 | Package: bindr
 47 | Source: CRAN
 48 | Version: 0.1.1
 49 | Hash: 76578c5f543a6ecbc1365d6445f9ebf7
 50 | 
 51 | Package: bindrcpp
 52 | Source: CRAN
 53 | Version: 0.2.2
 54 | Hash: 8ce499301f0dc5c7ff69f0b42e33f5c1
 55 | Requires: Rcpp, bindr, plogr
 56 | 
 57 | Package: bitops
 58 | Source: CRAN
 59 | Version: 1.0-6
 60 | Hash: 67d0775189fd0041d95abca618c5c07e
 61 | 
 62 | Package: broom
 63 | Source: CRAN
 64 | Version: 0.5.1
 65 | Hash: f170bc989c523e039487511e87c1854f
 66 | Requires: backports, dplyr, generics, purrr, reshape2, stringr, tibble,
 67 |     tidyr
 68 | 
 69 | Package: caTools
 70 | Source: CRAN
 71 | Version: 1.17.1.1
 72 | Hash: 1764f9cb70825aa7a1c461e7514ffb73
 73 | Requires: bitops
 74 | 
 75 | Package: callr
 76 | Source: CRAN
 77 | Version: 3.1.1
 78 | Hash: 461cdebafe2c1cfc23ddc37527633185
 79 | Requires: R6, processx
 80 | 
 81 | Package: cellranger
 82 | Source: CRAN
 83 | Version: 1.1.0
 84 | Hash: be9d203e7849f73818b36f93e9273c2c
 85 | Requires: rematch, tibble
 86 | 
 87 | Package: checkmate
 88 | Source: CRAN
 89 | Version: 1.8.5
 90 | Hash: e1bbc5228ab3da931a099208bc95ad23
 91 | Requires: backports
 92 | 
 93 | Package: cli
 94 | Source: CRAN
 95 | Version: 1.0.1
 96 | Hash: a742a3229dbf7085c3a737af10e5065b
 97 | Requires: assertthat, crayon
 98 | 
 99 | Package: clipr
100 | Source: CRAN
101 | Version: 0.4.1
102 | Hash: caf20ae357bfa2ed50e0e7db267f69ce
103 | 
104 | Package: clisymbols
105 | Source: CRAN
106 | Version: 1.2.0
107 | Hash: a76a309884277a4fd8a5d741965fbef5
108 | 
109 | Package: colorspace
110 | Source: CRAN
111 | Version: 1.3-2
112 | Hash: 0bf8618b585fa98eb23414cd3ab95118
113 | 
114 | Package: commonmark
115 | Source: CRAN
116 | Version: 1.7
117 | Hash: 77f4ba718e2bad1877ef26e48cf8fa43
118 | 
119 | Package: crayon
120 | Source: CRAN
121 | Version: 1.3.4
122 | Hash: ff2840dd9b0d563fc80377a5a45510cd
123 | 
124 | Package: curl
125 | Source: CRAN
126 | Version: 3.2
127 | Hash: 82a7cf5bb702ef52329b6d23ea6132a7
128 | 
129 | Package: data.table
130 | Source: CRAN
131 | Version: 1.11.8
132 | Hash: 67c877937c790a0cadb71284febb6b34
133 | 
134 | Package: dbplyr
135 | Source: CRAN
136 | Version: 1.2.2
137 | Hash: f09ea2f1a5c31d86b061d7121fab5db8
138 | Requires: DBI, R6, assertthat, dplyr, glue, purrr, rlang, tibble,
139 |     tidyselect
140 | 
141 | Package: desc
142 | Source: CRAN
143 | Version: 1.2.0
144 | Hash: a0a3ca939997679a52816bae4ed6aaae
145 | Requires: R6, assertthat, crayon, rprojroot
146 | 
147 | Package: devtools
148 | Source: CRAN
149 | Version: 2.0.1
150 | Hash: 4da83470ae57bd2db0ac06e91b1d3a08
151 | Requires: callr, cli, digest, git2r, httr, jsonlite, memoise, pkgbuild,
152 |     pkgload, rcmdcheck, remotes, rstudioapi, sessioninfo, usethis,
153 |     withr
154 | 
155 | Package: digest
156 | Source: CRAN
157 | Version: 0.6.18
158 | Hash: 65f62365ec69ddd17230d2ffe891a6ab
159 | 
160 | Package: dplyr
161 | Source: CRAN
162 | Version: 0.7.8
163 | Hash: d6e576944199cba782a471015a822848
164 | Requires: BH, R6, Rcpp, assertthat, bindrcpp, glue, magrittr,
165 |     pkgconfig, plogr, rlang, tibble, tidyselect
166 | 
167 | Package: evaluate
168 | Source: CRAN
169 | Version: 0.12
170 | Hash: c32505adba4f6eca5aa20dd32300b019
171 | 
172 | Package: fansi
173 | Source: CRAN
174 | Version: 0.4.0
175 | Hash: f147621f72b561485bfffcae78c4f5d5
176 | 
177 | Package: forcats
178 | Source: CRAN
179 | Version: 0.3.0
180 | Hash: 770f3834b97a2c429bdecb7a5f27eb25
181 | Requires: magrittr, rlang, tibble
182 | 
183 | Package: fs
184 | Source: CRAN
185 | Version: 1.2.6
186 | Hash: 8ffb8b293a18e26e435465307cc47f75
187 | Requires: Rcpp
188 | 
189 | Package: generics
190 | Source: CRAN
191 | Version: 0.0.2
192 | Hash: 4aaf002dd434e8c854611c5d11a1d58e
193 | 
194 | Package: ggplot2
195 | Source: CRAN
196 | Version: 3.1.0
197 | Hash: ef541b05dda10b209d509b5bbaf46ea3
198 | Requires: digest, gtable, lazyeval, plyr, reshape2, rlang, scales,
199 |     tibble, viridisLite, withr
200 | 
201 | Package: gh
202 | Source: CRAN
203 | Version: 1.0.1
204 | Hash: 3f8812accd1320227d744bca620e8c42
205 | Requires: httr, ini, jsonlite
206 | 
207 | Package: git2r
208 | Source: CRAN
209 | Version: 0.23.0
210 | Hash: ea0a8f265d61f9356d17fff4d9e1613b
211 | 
212 | Package: glue
213 | Source: CRAN
214 | Version: 1.3.0
215 | Hash: 1fbde6dec830370be696eee8ef31c9e4
216 | 
217 | Package: gt
218 | Source: github
219 | Version: 0.1.0
220 | Hash: 63f3be25f850d24667b9d53cbc8d4971
221 | Requires: checkmate, commonmark, dplyr, ggplot2, glue, htmltools,
222 |     magrittr, rlang, sass, scales, stringr, tibble, tidyr, tidyselect
223 | GithubRepo: gt
224 | GithubUsername: rstudio
225 | GithubRef: master
226 | GithubSha1: b4a75a7ac406bca0a3823bcd416b23d5a305839d
227 | RemoteHost: api.github.com
228 | RemoteRepo: gt
229 | RemoteUsername: rstudio
230 | RemoteRef: master
231 | RemoteSha: b4a75a7ac406bca0a3823bcd416b23d5a305839d
232 | 
233 | Package: gtable
234 | Source: CRAN
235 | Version: 0.2.0
236 | Hash: cd78381a9d3fea966ac39bd0daaf5554
237 | 
238 | Package: haven
239 | Source: CRAN
240 | Version: 2.0.0
241 | Hash: 3180a95083d9ef6da3fafc38e0519e2f
242 | Requires: Rcpp, forcats, hms, readr, tibble
243 | 
244 | Package: highr
245 | Source: CRAN
246 | Version: 0.7
247 | Hash: 20757f5c393ed0ecf96c9e8e6d8d514c
248 | 
249 | Package: hms
250 | Source: CRAN
251 | Version: 0.4.2
252 | Hash: b4096a4f6a6736138e9a825c2baaacf0
253 | Requires: pkgconfig, rlang
254 | 
255 | Package: htmltools
256 | Source: CRAN
257 | Version: 0.3.6
258 | Hash: 9707abea0a9b7406e98fb1242e97e1f6
259 | Requires: Rcpp, digest
260 | 
261 | Package: httr
262 | Source: CRAN
263 | Version: 1.4.0
264 | Hash: 62d62d3ffcc9a34411b6e35a813f72dd
265 | Requires: R6, curl, jsonlite, mime, openssl
266 | 
267 | Package: ini
268 | Source: CRAN
269 | Version: 0.3.1
270 | Hash: 9d6de5178c1cedabfb24e7d2acc9a092
271 | 
272 | Package: jsonlite
273 | Source: CRAN
274 | Version: 1.6
275 | Hash: 5f969e213e966135393e3e304abf3f49
276 | 
277 | Package: knitr
278 | Source: CRAN
279 | Version: 1.21
280 | Hash: 05d92a30fe7f149fef5e82428cbbe0d7
281 | Requires: evaluate, highr, markdown, stringr, xfun, yaml
282 | 
283 | Package: labeling
284 | Source: CRAN
285 | Version: 0.3
286 | Hash: ecf589b42cd284b03a4beb9665482d3e
287 | 
288 | Package: lazyeval
289 | Source: CRAN
290 | Version: 0.2.1
291 | Hash: 88926ad9c43581fd0822a37c8ed09f05
292 | 
293 | Package: lubridate
294 | Source: CRAN
295 | Version: 1.7.4
296 | Hash: a7c783782f0e50be33b31f859c11333e
297 | Requires: Rcpp, stringr
298 | 
299 | Package: magrittr
300 | Source: CRAN
301 | Version: 1.5
302 | Hash: bdc4d48c3135e8f3b399536ddf160df4
303 | 
304 | Package: markdown
305 | Source: CRAN
306 | Version: 0.9
307 | Hash: 730f688930cef3223d59bd8aef679ab9
308 | Requires: mime
309 | 
310 | Package: memoise
311 | Source: CRAN
312 | Version: 1.1.0
313 | Hash: 410fcd334bc626db100237cc1370f2e9
314 | Requires: digest
315 | 
316 | Package: mime
317 | Source: CRAN
318 | Version: 0.6
319 | Hash: 2ed8f98b8284ad733f3907fc6e2f1334
320 | 
321 | Package: modelr
322 | Source: CRAN
323 | Version: 0.1.2
324 | Hash: f691854a99ac7814f3853d499408d9a3
325 | Requires: broom, dplyr, magrittr, purrr, rlang, tibble, tidyr
326 | 
327 | Package: munsell
328 | Source: CRAN
329 | Version: 0.5.0
330 | Hash: 38d0efee9bb99bef143bde41c4ce715c
331 | Requires: colorspace
332 | 
333 | Package: openssl
334 | Source: CRAN
335 | Version: 1.1
336 | Hash: 82c893294829c4badc3d4133b66d1428
337 | 
338 | Package: packrat
339 | Source: CRAN
340 | Version: 0.5.0
341 | Hash: 498643e765d1442ba7b1160a1df3abf9
342 | 
343 | Package: pacman
344 | Source: CRAN
345 | Version: 0.5.0
346 | Hash: c05b1da1943bdd4a7b255df08d0a5e3f
347 | Requires: remotes
348 | 
349 | Package: pillar
350 | Source: CRAN
351 | Version: 1.3.1
352 | Hash: 9ed4c2a5d3047bfba3e852ad5e806d91
353 | Requires: cli, crayon, fansi, rlang, utf8
354 | 
355 | Package: pkgbuild
356 | Source: CRAN
357 | Version: 1.0.2
358 | Hash: 770e918f4c389e4fef9a891d043bf84f
359 | Requires: R6, callr, cli, crayon, desc, prettyunits, rprojroot, withr
360 | 
361 | Package: pkgconfig
362 | Source: CRAN
363 | Version: 2.0.2
364 | Hash: b0fd6ed908e150b77e5f00c6478bd58c
365 | 
366 | Package: pkgload
367 | Source: CRAN
368 | Version: 1.0.2
369 | Hash: 41eb2db35be61f6f9e8864cf87a1ecb0
370 | Requires: desc, pkgbuild, rlang, rprojroot, rstudioapi, withr
371 | 
372 | Package: plogr
373 | Source: CRAN
374 | Version: 0.2.0
375 | Hash: 81a8008a5e7858552503935f1abe48aa
376 | 
377 | Package: plyr
378 | Source: CRAN
379 | Version: 1.8.4
380 | Hash: ec185c885aab7ec91693d78c20cb5d1a
381 | Requires: Rcpp
382 | 
383 | Package: prettyunits
384 | Source: CRAN
385 | Version: 1.0.2
386 | Hash: 49286102a855640daaa38eafe8b1ec30
387 | Requires: assertthat, magrittr
388 | 
389 | Package: processx
390 | Source: CRAN
391 | Version: 3.2.1
392 | Hash: fdc6a66626b75f96ee28ffc770d9ebd7
393 | Requires: R6, ps
394 | 
395 | Package: progress
396 | Source: CRAN
397 | Version: 1.2.0
398 | Hash: 0ff5f631b66daf57857f28062f3e6f30
399 | Requires: R6, crayon, hms, prettyunits
400 | 
401 | Package: ps
402 | Source: CRAN
403 | Version: 1.3.0
404 | Hash: 1d4cae95887ffe5b1a22bea5994476cd
405 | 
406 | Package: purrr
407 | Source: CRAN
408 | Version: 0.2.5
409 | Hash: 8b0c16db10c7e20b70cd37779a673a8b
410 | Requires: magrittr, rlang, tibble
411 | 
412 | Package: rcmdcheck
413 | Source: CRAN
414 | Version: 1.3.2
415 | Hash: 162a63e909423b7c5f44c30711135481
416 | Requires: R6, callr, cli, crayon, desc, digest, pkgbuild, prettyunits,
417 |     rprojroot, sessioninfo, withr, xopen
418 | 
419 | Package: readr
420 | Source: CRAN
421 | Version: 1.3.1
422 | Hash: ed1b5520a0df4007bc971658ee543b00
423 | Requires: BH, R6, Rcpp, clipr, crayon, hms, tibble
424 | 
425 | Package: readxl
426 | Source: CRAN
427 | Version: 1.2.0
428 | Hash: 3d49de1375021e909463ce4bdb613327
429 | Requires: Rcpp, cellranger, progress, tibble
430 | 
431 | Package: rematch
432 | Source: CRAN
433 | Version: 1.0.1
434 | Hash: ad4faf59e7611117ff165817074c50c7
435 | 
436 | Package: remotes
437 | Source: CRAN
438 | Version: 2.0.2
439 | Hash: cfcf5e119ed5e6af4b47530ba59101f3
440 | 
441 | Package: reprex
442 | Source: CRAN
443 | Version: 0.2.1
444 | Hash: b30c7fbcb528a71d7ffcd07c9982589d
445 | Requires: callr, clipr, fs, rlang, rmarkdown, whisker, withr
446 | 
447 | Package: reshape2
448 | Source: CRAN
449 | Version: 1.4.3
450 | Hash: c950c8ac85b81209635acb3ce21b4cce
451 | Requires: Rcpp, plyr, stringr
452 | 
453 | Package: rlang
454 | Source: CRAN
455 | Version: 0.3.0.1
456 | Hash: 35fb7a51d5d756c56f793ed9c381fb84
457 | 
458 | Package: rmarkdown
459 | Source: CRAN
460 | Version: 1.11
461 | Hash: a30b0c41b60d981f41dc8c98f2136297
462 | Requires: base64enc, evaluate, htmltools, jsonlite, knitr, mime,
463 |     stringr, tinytex, yaml
464 | 
465 | Package: rprojroot
466 | Source: CRAN
467 | Version: 1.3-2
468 | Hash: a25c3f70c166fb3fbabc410eb32b6366
469 | Requires: backports
470 | 
471 | Package: rstudioapi
472 | Source: CRAN
473 | Version: 0.8
474 | Hash: 9ba7fe76dcaf96966c449527ca04bb78
475 | 
476 | Package: rvest
477 | Source: CRAN
478 | Version: 0.3.2
479 | Hash: c69f7526520bad66fd2111ebe8b1364b
480 | Requires: httr, magrittr, selectr, xml2
481 | 
482 | Package: sass
483 | Source: github
484 | Version: 0.1.0.9000
485 | Hash: 2b4ab4b71b56f10605e901cae30c2dad
486 | Requires: digest
487 | GithubRepo: sass
488 | GithubUsername: rstudio
489 | GithubRef: master
490 | GithubSha1: c73867da1d7a07b65da1d175ae072417f7387404
491 | RemoteHost: api.github.com
492 | RemoteRepo: sass
493 | RemoteUsername: rstudio
494 | RemoteRef: master
495 | RemoteSha: c73867da1d7a07b65da1d175ae072417f7387404
496 | 
497 | Package: scales
498 | Source: CRAN
499 | Version: 1.0.0
500 | Hash: 7d9b717abcec656ae7c5c982d72b75e5
501 | Requires: R6, RColorBrewer, Rcpp, labeling, munsell, viridisLite
502 | 
503 | Package: selectr
504 | Source: CRAN
505 | Version: 0.4-1
506 | Hash: b12802c11e35dec9d16a74d30ed0f3ed
507 | Requires: R6, stringr
508 | 
509 | Package: sessioninfo
510 | Source: CRAN
511 | Version: 1.1.1
512 | Hash: 9e50c8458e611f166ba702277cbb5096
513 | Requires: cli, withr
514 | 
515 | Package: stringi
516 | Source: CRAN
517 | Version: 1.2.4
518 | Hash: 03ab60ef7fa4627b38ad67c95ce6b04c
519 | 
520 | Package: stringr
521 | Source: CRAN
522 | Version: 1.3.1
523 | Hash: 9f417a1d899ed1f080942ab36998e8b5
524 | Requires: glue, magrittr, stringi
525 | 
526 | Package: tibble
527 | Source: CRAN
528 | Version: 1.4.2
529 | Hash: 83895360ce4f8d2ce92eee00526b5b0b
530 | Requires: cli, crayon, pillar, rlang
531 | 
532 | Package: tidyr
533 | Source: CRAN
534 | Version: 0.8.2
535 | Hash: 9ff92b9b3c11dfcd94d179b75b85c668
536 | Requires: Rcpp, dplyr, glue, magrittr, purrr, rlang, stringi, tibble,
537 |     tidyselect
538 | 
539 | Package: tidyselect
540 | Source: CRAN
541 | Version: 0.2.5
542 | Hash: fad1cf10c5c4996fca6ca68e0716d2e6
543 | Requires: Rcpp, glue, purrr, rlang
544 | 
545 | Package: tidyverse
546 | Source: CRAN
547 | Version: 1.2.1
548 | Hash: 1b090209cb20b6fc6eba75de8b7f0b53
549 | Requires: broom, cli, crayon, dbplyr, dplyr, forcats, ggplot2, haven,
550 |     hms, httr, jsonlite, lubridate, magrittr, modelr, purrr, readr,
551 |     readxl, reprex, rlang, rstudioapi, rvest, stringr, tibble, tidyr,
552 |     xml2
553 | 
554 | Package: tinytex
555 | Source: CRAN
556 | Version: 0.9
557 | Hash: a4ffe98c58eace5a95644d8fd6ca5a50
558 | Requires: xfun
559 | 
560 | Package: usethis
561 | Source: CRAN
562 | Version: 1.4.0
563 | Hash: bdf0ce7802818c5dfc592dd73d62db5b
564 | Requires: clipr, clisymbols, crayon, curl, desc, fs, gh, git2r, glue,
565 |     rlang, rprojroot, rstudioapi, whisker
566 | 
567 | Package: utf8
568 | Source: CRAN
569 | Version: 1.1.4
570 | Hash: f3f97ce59092abc8ed3fd098a59e236c
571 | 
572 | Package: viridisLite
573 | Source: CRAN
574 | Version: 0.3.0
575 | Hash: 78bb072c4f9e729a283d4c40ec93f9c6
576 | 
577 | Package: whisker
578 | Source: CRAN
579 | Version: 0.3-2
580 | Hash: 803d662762e532705c2c066a82d066e7
581 | 
582 | Package: withr
583 | Source: CRAN
584 | Version: 2.1.2
585 | Hash: d534108bcd5f34ec73e9eb523751ba20
586 | 
587 | Package: xfun
588 | Source: CRAN
589 | Version: 0.4
590 | Hash: 76004125b45195c0330ec71904849995
591 | 
592 | Package: xml2
593 | Source: CRAN
594 | Version: 1.2.0
595 | Hash: 3f00e5347a6d7ccad2237fe1bc1df6d0
596 | Requires: Rcpp
597 | 
598 | Package: xopen
599 | Source: CRAN
600 | Version: 1.0.0
601 | Hash: 22c2708f177f9fd9f8a52012bac61d6a
602 | Requires: processx
603 | 
604 | Package: yaml
605 | Source: CRAN
606 | Version: 2.2.0
607 | Hash: a5ad5616d83d89f8d84cbf3cf4034e13
608 | 


--------------------------------------------------------------------------------
/genre_analysis.Rmd:
--------------------------------------------------------------------------------
  1 | ---
  2 | title: "Movie Genre Overlappings, Ratings by Genre and Year"
  3 | author: "Ceshine Lee"
  4 | output:
  5 |   html_notebook
  6 | ---
  7 | 
  8 | ### (Exploring the Moives Dataset with rstudio/gt package)
  9 | 
 10 | Tables can be an effective way of communicating data. Though not as powerful in telling stories as charts, by cramming a lot of numbers into limited space, it can provide readers with accurate and potentially useful information which readers can interpret in their own ways.
 11 | 
 12 | I've come across this new R package [**gt**](https://github.com/rstudio/gt)(Easily generate information-rich, publication-quality tables from R) and decided to give it a try.
 13 | 
 14 | > With the gt package, anyone can make wonderful-looking tables using the R programming language.
 15 | 
 16 | Admittedly, the tables in the documents might not be the optimal way of presentation. They serve as a demonstration of what **gt** can do, and maybe also helpful enough for analyst in constructing their stories about this dataset.
 17 | 
 18 | (Dataset Source: [The Movies Dataset on Kaggle](https://www.kaggle.com/rounakbanik/the-movies-dataset).)
 19 | 
 20 | ![](https://raw.githubusercontent.com/rstudio/gt/master/man/figures/gt_parts_of_a_table.svg?sanitize=true)
 21 | 
 22 | ```{r, message=FALSE, results="hide"}
 23 | # install.packages("packrat")
 24 | # install.packages("pacman")
 25 | # install.packages("devtools")
 26 | # install.packages("tidyverse")
 27 | # devtools::install_github("rstudio/gt")
 28 | library(gt)
 29 | pacman::p_load("tidyverse")
 30 | pacman::p_load("data.table")
 31 | pacman::p_load("jsonlite")
 32 | pacman::p_load("lubridate")
 33 | ```
 34 | 
 35 | ## Read and clean the Metadata
 36 | 
 37 | Some of the fields read in here are not used in the later sections. However, they are kept as a reminder of the potentially useful information.
 38 | 
 39 | ```{r read_clean_metadata}
 40 | metadata <- fread("data/movies_metadata.csv", select=c('adult', 'genres', 'release_date', 'original_language', 'original_title', 'id', 'imdb_id'), fill=T)
 41 | metadata <- metadata[!is.na(as.integer(id)) & (original_language == 'en') & (adult == "False"), ]
 42 | metadata[, id := as.integer(id)]
 43 | # Replace singles quote in 'genre' so 'fromJSON' function can parse it
 44 | metadata[, genre := gsub("\'","\"", metadata$genre)]
 45 | # Remove redundant fields
 46 | metadata[, c('original_language', 'adult', "imdb_id") := NULL]
 47 | ```
 48 | 
 49 | ## Parse Genres
 50 | 
 51 | Genre information is stored as JSON texts. We need to parse it and do some transformation.
 52 | 
 53 | ```{r parse_genre}
 54 | genres <- metadata[, unlist(lapply(genre, fromJSON), recursive=F)['name'], by=id]
 55 | sorted.genres <- genres[, .N, by=name][order(-N)]
 56 | sorted.genres[1:20]
 57 | ```
 58 | 
 59 | Assuming genres are assigned in order of representativeness, taking at most three top genres for each movie. Furthermore, only the top 6 genres are considered.
 60 | 
 61 | ```{r}
 62 | # Dummy variable for the later dcast operation
 63 | genres[, dummy := 1]
 64 | # Only use the first 3 assigned genres
 65 | encoded.genres <- dcast(na.omit(genres[,.SD[1:3], by=id])[name %in% sorted.genres[1:6, name]],
 66 |                         id ~  name, value.var='dummy', fill=0)
 67 | data.w.genre <- merge(encoded.genres,
 68 |       metadata[, .(id, original_title, release_date)],
 69 |       all.x=T, by="id")
 70 | ```
 71 | 
 72 | ## Genre Statistics
 73 | 
 74 | Here I used a for loop to collect and calculate statstics genre by genre. I later figured out the better way to do this is probably using a *melt* call followed by several *ratio* column calculations. The later sections will use the *melt* approach instead.
 75 | 
 76 | ```{r}
 77 | i <- 0
 78 | tmp.raw <- list()
 79 | tmp.ratio <- list()
 80 | for(name in sorted.genres[1:6, name]){
 81 |     i <- i + 1
 82 |     dt.tmp <- data.w.genre[get(name) == 1, lapply(.SD, sum), .SDcols=sorted.genres[1:6, name]]
 83 |     tmp.ratio[[i]] <- copy(dt.tmp)
 84 |     dt.tmp[, genre := name]
 85 |     tmp.raw[[i]] <- dt.tmp
 86 |     tmp.ratio[[i]] <- tmp.ratio[[i]] / dt.tmp[, get(name)]
 87 |     tmp.ratio[[i]][, genre := name]
 88 | }
 89 | genre.stats <- merge(rbindlist(tmp.raw), rbindlist(tmp.ratio), by="genre", suffixes=c("", ".ratio"), sort=F)
 90 | rm(tmp.raw, tmp.ratio, i)
 91 | ```
 92 | 
 93 | The actual table declaration and rendering part. Unfortunately it requires a lot of manual labeling and assignments. But I think it is verbose and readable enough.
 94 | 
 95 | ```{r}
 96 | gt_tbl <- gt(data = genre.stats, rowname_col = "genre")
 97 | gt_tbl %>%
 98 |   tab_header(
 99 |     title = "Movie Metadata Stats"
100 |   ) %>%
101 |   tab_spanner(
102 |     label = "Genre Overlappings",
103 |     columns = vars(Drama, Comedy, Thriller, Romance, Action, Horror)
104 |   ) %>%
105 |   tab_spanner(
106 |     label = "Genre Overlappings(%)",
107 |     columns = vars(Drama.ratio, Comedy.ratio, Thriller.ratio, Romance.ratio, Action.ratio, Horror.ratio)
108 |   ) %>%
109 |   fmt_percent(
110 |     columns = vars(Drama.ratio, Comedy.ratio, Thriller.ratio, Romance.ratio, Action.ratio, Horror.ratio),
111 |     decimals = 1,
112 |     drop_trailing_zeros = F
113 |   ) %>%
114 |   tab_source_note(
115 |     source_note = md("Source:  [\"The Movie Dataset\"](rounakbanik/the-movies-dataset) on Kaggle")
116 |   ) %>%
117 |   cols_label(
118 |     Drama.ratio = "Drama",
119 |     Comedy.ratio = "Comedy",
120 |     Thriller.ratio = "Thriller",
121 |     Romance.ratio = "Romance",
122 |     Action.ratio = "Action",
123 |     Horror.ratio = "Horror"
124 |   ) %>%
125 |   tab_stubhead_label(label = "Genre") %>%
126 |   tab_style(
127 |     style = cells_styles(
128 |       text_size = px(12)),
129 |     locations = list(
130 |         cells_column_labels(columns = 1:12),
131 |         cells_stub(),
132 |         cells_data()
133 |     )) %>%
134 |   tab_style(
135 |     style = cells_styles(
136 |       text_decorate = "underline",
137 |       text_weight = "bold"),
138 |     locations = list(
139 |         cells_data(columns=c(1), rows=c(1)),
140 |         cells_data(columns=c(2), rows=c(2)),
141 |         cells_data(columns=c(3), rows=c(3)),
142 |         cells_data(columns=c(4), rows=c(4)),
143 |         cells_data(columns=c(5), rows=c(5)),
144 |         cells_data(columns=c(6), rows=c(6))
145 |     )) %>%
146 |   tab_style(
147 |     style = cells_styles(
148 |       text_color="lightgrey"),
149 |     locations = list(
150 |         cells_data(columns=c(7), rows=c(1)),
151 |         cells_data(columns=c(8), rows=c(2)),
152 |         cells_data(columns=c(9), rows=c(3)),
153 |         cells_data(columns=c(10), rows=c(4)),
154 |         cells_data(columns=c(11), rows=c(5)),
155 |         cells_data(columns=c(12), rows=c(6))
156 |     ))
157 | ```
158 | 
159 | *How to read the table*: For example, Drama (the first row) has 13008 movies (the first column), and 2639 of them are also under Comedy, which is 20.3% of the 13008 movies.
160 | 
161 | The diagonal elements of 'Genre Overlappings' section are emphasized because they represent the movie count of the respective genre. Similarily, the diagonal elements of 'Genre Overlappings(%)' section are somewhat hiddened since they convey almost no useful information.
162 | 
163 | 
164 | ## Reading Ratings
165 | 
166 | Now we turn our attention to movie ratings (from movielens). We only consider the average rating of a movie (which of course is not perfect).
167 | 
168 | ```{r, read_ratings}
169 | ratings <- fread("data/ratings.csv", select=c('movieId', 'rating'))
170 | ratings.stats <- ratings[, .(n_ratings=.N, avg_rating=mean(rating)), by=movieId]
171 | rm(ratings)
172 | head(ratings.stats)
173 | ```
174 | 
175 | Here we remove movies with less than 500 ratings.
176 | 
177 | ```{r}
178 | data.w.genre.ratings <- merge(data.w.genre, ratings.stats, by.y="movieId", by.x="id")
179 | # Only keep moives with >= 500 ratings
180 | data.w.genre.ratings <- data.w.genre.ratings[n_ratings >= 500]
181 | head(data.w.genre.ratings)
182 | ```
183 | 
184 | ## Rating statistics by Genre
185 | 
186 | Using a *melt* call followed by a bunch of data.table operations to prepare the metrics:
187 | 
188 | ```{r}
189 | rating.by.genre <- melt(
190 |     data.w.genre.ratings, id=c("id", "avg_rating", "n_ratings"), measure.vars=c("Action", "Comedy", "Drama", "Horror", "Romance", "Thriller"), variable.name="genre"
191 |     )[value==1][
192 |     , .(n_movies=.N, min_rating=min(avg_rating), avg_rating=mean(avg_rating), med_rating=median(avg_rating), max_rating=max(avg_rating), sd_rating=sd(avg_rating), n_ratings=sum(n_ratings), avg_n_ratings=mean(n_ratings), max_n_ratings=max(n_ratings), min_n_ratings=min(n_ratings)), by=genre]
193 | head(rating.by.genre)
194 | ```
195 | 
196 | Follows roughly the same recipe (unfortunately I did not find a reasonable way to make use of row group feature of *gt* for this dataset):
197 | 
198 | ```{r}
199 | gt_tbl <- gt(data = rating.by.genre, rowname_col = "genre")
200 | gt_tbl %>%
201 |   tab_header(
202 |     title = "Movie Average Ratings by Genre",
203 |     subtitle = "with # of Ratings >= 500"
204 |   ) %>%
205 |   tab_spanner(
206 |     label = "Average Rating (1-5)",
207 |     columns = vars(min_rating, avg_rating, med_rating, max_rating, sd_rating)
208 |   ) %>%
209 |   fmt_number(
210 |     columns = vars(min_rating, avg_rating, med_rating, max_rating, sd_rating),
211 |     decimals = 2,
212 |     drop_trailing_zeros = F
213 |   ) %>%
214 |   tab_spanner(
215 |     label = "# of Ratings",
216 |     columns = vars(n_ratings, min_n_ratings, avg_n_ratings, max_n_ratings)
217 |   ) %>%
218 |   fmt_number(
219 |     columns = vars(n_ratings, min_n_ratings, avg_n_ratings, max_n_ratings),
220 |     decimals = 0,
221 |     drop_trailing_zeros = F
222 |   ) %>%
223 |   tab_source_note(
224 |     source_note = md("Source:  [\"The Movie Dataset\"](rounakbanik/the-movies-dataset) on Kaggle")
225 |   ) %>%
226 |   cols_label(
227 |     min_rating = "Min",
228 |     avg_rating = "Avg",
229 |     med_rating = "Med",
230 |     max_rating = "Max",
231 |     n_ratings = "Total",
232 |     min_n_ratings = "Min",
233 |     avg_n_ratings = "Avg",
234 |     max_n_ratings = "Max",
235 |     n_movies="Movies",
236 |     sd_rating="Stdev"
237 |   ) %>%
238 |   tab_stubhead_label(label = "Genre") %>%
239 |   tab_style(
240 |     style = cells_styles(
241 |       text_size = px(14)),
242 |     locations = list(
243 |         cells_column_labels(columns = 1:10),
244 |         cells_stub(),
245 |         cells_data()
246 |     ))
247 | ```
248 | 
249 | Suprisingly, the distribution of ratings are quite similar across all genres. Maybe movielens has done some normalization on the ratings?
250 | 
251 | 
252 | ## Rating statistics by Genre and Year
253 | 
254 | We'd also like to know if the distributions of ratings change over time. First we plot the histogram of the years in which the movies were released. This is a case where a histogram is far more readable than a table.
255 | 
256 | ```{r}
257 | data.w.genre.ratings[,release_year:=year(ymd(release_date))]
258 | ggplot(data.w.genre.ratings[release_year >= 1950][order(release_year),.N, by=release_year], aes(x=release_year, y=N)) +
259 |     geom_bar(stat="identity") + ggtitle("# of Movie by Year") + theme_bw() + scale_x_continuous(breaks=seq(1950, 2020, 10))
260 | ```
261 | 
262 | Now we only take movies released after 1979 and before 2010 into account, and put them in to buckets each representing a decade.
263 | 
264 | ```{r}
265 | data.w.genre.ratings <- data.w.genre.ratings[(release_year >= 1980) & (release_year < 2010)]
266 | data.w.genre.ratings[, release_decade := (release_year %/% 10) * 10 ]
267 | ```
268 | 
269 | The same old *melt* trick:
270 | 
271 | ```{r}
272 | rating.by.genre.year <- melt(
273 |     data.w.genre.ratings, id=c("id", "avg_rating", "n_ratings", "release_decade"), measure.vars=c("Action", "Comedy", "Drama", "Horror", "Romance", "Thriller"), variable.name="genre"
274 |     )[value==1][
275 |     , .(n_movies=.N, min_rating=min(avg_rating), avg_rating=mean(avg_rating), med_rating=median(avg_rating), max_rating=max(avg_rating), sd_rating=sd(avg_rating), n_ratings=sum(n_ratings), avg_n_ratings=mean(n_ratings), max_n_ratings=max(n_ratings), min_n_ratings=min(n_ratings)), by=.(genre, release_decade)]
276 | ```
277 | 
278 | Even more manual labeling and a *dcast* call to handle the extra *decade* dimension:
279 | 
280 | ```{r}
281 | gt_tbl <- gt(
282 |     data = dcast(rating.by.genre.year, genre ~ release_decade, value.var = c("avg_rating", "sd_rating", "avg_n_ratings", "n_movies"))[, .(genre,
283 |         n_movies_1980, avg_rating_1980, sd_rating_1980, avg_n_ratings_1980,
284 |         n_movies_1990, avg_rating_1990, sd_rating_1990, avg_n_ratings_1990,
285 |         n_movies_2000, avg_rating_2000, sd_rating_2000, avg_n_ratings_2000
286 |     )],
287 |     rowname_col = "genre")
288 | gt_tbl %>%
289 |   tab_header(
290 |     title = "Movie Average Ratings by Genre & Year",
291 |     subtitle = "with # of Ratings >= 500"
292 |   ) %>%
293 |   tab_spanner(
294 |     label = "1980s",
295 |     columns = vars(n_movies_1980, avg_rating_1980, sd_rating_1980, avg_n_ratings_1980)
296 |   ) %>%
297 |   tab_spanner(
298 |     label = "1990s",
299 |     columns = vars(n_movies_1990, avg_rating_1990, sd_rating_1990, avg_n_ratings_1990)
300 |   ) %>%
301 |   tab_spanner(
302 |     label = "2000s",
303 |     columns = vars(n_movies_2000, avg_rating_2000, sd_rating_2000, avg_n_ratings_2000)
304 |   ) %>%
305 |   fmt_number(
306 |     columns = vars(avg_rating_1980, sd_rating_1980, avg_rating_1990, sd_rating_1990, avg_rating_2000, sd_rating_2000),
307 |     decimals = 2,
308 |     drop_trailing_zeros = F
309 |   ) %>%
310 |   fmt_number(
311 |     columns = vars(avg_n_ratings_1980, avg_n_ratings_1990, avg_n_ratings_2000, n_movies_1980, n_movies_1990, n_movies_2000),
312 |     decimals = 0,
313 |     drop_trailing_zeros = F
314 |   ) %>%
315 |   tab_source_note(
316 |     source_note = md("Source:  [\"The Movie Dataset\"](rounakbanik/the-movies-dataset) on Kaggle")
317 |   ) %>%
318 |   tab_footnote(
319 |     footnote = "#: Number of movies",
320 |     cells_column_labels(columns = c(1, 5, 9))
321 |   ) %>%
322 |   tab_footnote(
323 |     footnote = "Avg #: Average number of ratings.",
324 |     cells_column_labels(columns = c(4, 8, 12))
325 |   ) %>%
326 |   cols_label(
327 |     n_movies_1980 = "#",
328 |     n_movies_1990 = "#",
329 |     n_movies_2000 = "#",
330 |     avg_rating_1980 = "Avg",
331 |     avg_rating_1990 = "Avg",
332 |     avg_rating_2000 = "Avg",
333 |     sd_rating_1980 = "Stdev",
334 |     sd_rating_1990 = "Stdev",
335 |     sd_rating_2000 = "Stdev",
336 |     avg_n_ratings_1980 = "Avg #",
337 |     avg_n_ratings_1990 = "Avg #",
338 |     avg_n_ratings_2000 = "Avg #"
339 |   ) %>%
340 |   tab_stubhead_label(label = "Genre") %>%
341 |   tab_style(
342 |     style = cells_styles(
343 |       text_size = px(14)),
344 |     locations = list(
345 |         cells_column_labels(columns = 1:12),
346 |         cells_stub(),
347 |         cells_data()
348 |     ))
349 | ```
350 | 
351 | It appears the variances of ratings in 1980s are lower than in 1990s and 2000s. (A boxplot or scatterplot might be more appropriate here.)
352 | 
353 | ## Acknowledgements
354 | 
355 | * Erik Bruin's Kaggle notebook ["Movie recommendation systems based on TMDB"](https://www.kaggle.com/erikbruin/movie-recommendation-systems-based-on-tmdb) has been a great source of ideas r.t. manipulating this dataset using R.
356 | 
357 | 


--------------------------------------------------------------------------------