movies: Movie Rating Model and Predictor

## ----knitr_init, echo=FALSE, cache=FALSE, warning=FALSE, message=FALSE--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
options(knitr.table.format = "html")
options(max.print=100, scipen=999, width = 800)
knitr::opts_chunk$set(echo=FALSE,
	             cache=FALSE,
               prompt=FALSE,
	             eval = TRUE,
               tidy=TRUE,
               root.dir = "..",
               fig.height = 8,
               fig.width = 20,
               comment=NA,
               message=FALSE,
               warning=FALSE)
knitr::opts_knit$set(width=100, figr.prefix = T, figr.link = T)
knitr::knit_hooks$set(inline = function(x) {
  prettyNum(x, big.mark=",")
})

## ----load-data----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
load("../data/movies.Rdata")
load("../data/mdb2.Rdata")

## ----load-libraries-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
library(dplyr)
library(extrafont)
library(ggplot2)

## ----preprocess---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
dataSets  <- movies::preprocess(movies, mdb2)
mdb1 <- dataSets$mdb
mdb2 <- dataSets$mdbBox

## ----selected-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
raw <- openxlsx::read.xlsx("../data/features.xlsx", sheet = 1)
selected <- raw %>% filter(uni == "yes" & Source == "IMDB/RT/BO") %>% arrange(Group, No) %>% select(Type, Variable, Description)
knitr::kable(selected, align = 'l') %>%  
  kableExtra::kable_styling(bootstrap_options = c("hover", "condensed", "responsive"), full_width = T, position = "center") %>%
  kableExtra::group_rows("Overview", 1,3) %>%
  kableExtra::group_rows("Organization", 4,5) %>%
  kableExtra::group_rows("Dates", 6,6) %>%
  kableExtra::group_rows("Performance", 7,16) %>%
  kableExtra::group_rows("Box Office", 17,18) 

## ----derived------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
derived <- raw %>% filter(uni == "yes" & Source == "Derived") %>% arrange(Group, No) %>% select(Type, Variable, Description)
knitr::kable(derived, align = 'l') %>%  
  kableExtra::kable_styling(bootstrap_options = c("hover", "condensed", "responsive"), full_width = T, position = "center") %>%
  kableExtra::group_rows("Dates", 1,1) %>%
  kableExtra::group_rows("Experience", 2,4) %>%
  kableExtra::group_rows("Performance", 5,9) %>%
  kableExtra::group_rows("Interaction", 10,19) 

## ----omitted------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
omitted <- raw %>% filter(uni == "no") %>% select(Variable, Description)
knitr::kable(omitted) %>%  
  kableExtra::kable_styling(bootstrap_options = c("hover", "condensed", "responsive"), full_width = T, position = "center")