Nama : Ayla Huwaida

NIM : 2511017120006

Program Studi : Statistika

Mata Kuliah : Komputasi Statistika 1

Dosen Pengampu : Rifqi Aulya Rahman

  1. Load Library dan Ambil Data
library(tidyverse)
## Warning: package 'tidyverse' was built under R version 4.5.3
## Warning: package 'ggplot2' was built under R version 4.5.3
## Warning: package 'tidyr' was built under R version 4.5.3
## Warning: package 'purrr' was built under R version 4.5.3
## Warning: package 'dplyr' was built under R version 4.5.3
## Warning: package 'stringr' was built under R version 4.5.3
## Warning: package 'lubridate' was built under R version 4.5.3
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.2.1     ✔ readr     2.2.0
## ✔ forcats   1.0.1     ✔ stringr   1.6.0
## ✔ ggplot2   4.0.3     ✔ tibble    3.3.1
## ✔ lubridate 1.9.5     ✔ tidyr     1.3.2
## ✔ purrr     1.2.2     
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
data_raw <- read.csv("https://raw.githubusercontent.com/reisanar/datasets/master/HollywoodMovies.csv")
  1. Manipulasi Data
data_film <- data_raw[!is.na(data_raw$RottenTomatoes) & !is.na(data_raw$AudienceScore), ]

data_film$Label_HP <- ifelse(grepl("Harry Potter",data_film$Movie),"Film Harry Potter", "Film Lainnya")

data_film$Label_HP <- factor(data_film$Label_HP,levels = c("Film Harry Potter", "Film Lainnya"))

glimpse(data_film)
## Rows: 907
## Columns: 17
## $ Movie            <chr> "Spider-Man 3", "Shrek the Third", "Transformers", "P…
## $ LeadStudio       <chr> "Sony", "Paramount", "Paramount", "Disney", "Warner B…
## $ RottenTomatoes   <int> 61, 42, 57, 45, 78, 69, 93, 31, 26, 60, 97, 90, 14, 9…
## $ AudienceScore    <int> 54, 57, 89, 74, 82, 69, 91, 72, 73, 90, 84, 78, 72, 8…
## $ Story            <chr> "Metamorphosis", "Quest", "Monster Force", "Rescue", …
## $ Genre            <chr> "Action", "Animation", "Action", "Action", "Adventure…
## $ TheatersOpenWeek <int> 4252, 4122, 4011, 4362, 4285, 3606, 3660, 3832, 3475,…
## $ OpeningWeekend   <dbl> 151.1, 121.6, 70.5, 114.7, 77.1, 77.2, 69.3, 44.8, 44…
## $ BOAvgOpenWeekend <int> 35540, 29507, 17577, 26302, 17998, 21411, 18929, 1168…
## $ DomesticGross    <dbl> 336.53, 322.72, 319.25, 309.42, 292.00, 256.39, 227.4…
## $ ForeignGross     <dbl> 554.34, 476.24, 390.46, 654.00, 647.88, 328.96, 215.3…
## $ WorldGross       <dbl> 890.87, 798.96, 709.71, 963.42, 939.89, 585.35, 442.8…
## $ Budget           <dbl> 258.0, 160.0, 150.0, 300.0, 150.0, 150.0, 110.0, 130.…
## $ Profitability    <dbl> 345.30, 499.35, 473.14, 321.14, 626.59, 390.23, 402.5…
## $ OpenProfit       <dbl> 58.57, 76.00, 47.00, 38.23, 51.40, 51.47, 63.00, 34.4…
## $ Year             <int> 2007, 2007, 2007, 2007, 2007, 2007, 2007, 2007, 2007,…
## $ Label_HP         <fct> Film Lainnya, Film Lainnya, Film Lainnya, Film Lainny…
  1. Ringkasan Statistik
ringkasan <- aggregate(cbind(RottenTomatoes, AudienceScore) ~ Label_HP,
                       data = data_film, FUN = mean)
names(ringkasan)[2:3] <- c("rata_RT", "rata_aud")
ringkasan
##            Label_HP  rata_RT rata_aud
## 1 Film Harry Potter 84.00000 84.00000
## 2      Film Lainnya 51.60354 61.17054

4.Density Plot Dasar

palet_hp <- c("Film Harry Potter" = "#F48FB1",
              "Film Lainnya"      = "#81D4FA")

gd <- ggplot(data_film, aes(x = RottenTomatoes))

gd +
  geom_density(fill = "#81D4FA", alpha = 0.5, outline.type = "full") +
  geom_vline(xintercept = mean(data_film$RottenTomatoes),
             color = "#FC4E07", linetype = "dashed", size = 1)
## Warning: Using `size` aesthetic for lines was deprecated in ggplot2 3.4.0.
## ℹ Please use `linewidth` instead.
## This warning is displayed once per session.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.

5. Density Plot per Kelompok + Theme Final

p <- ggplot(data_film, aes(x = RottenTomatoes, fill = Label_HP))
p

p <- p +
  geom_density(alpha = 0.4, outline.type = "full")
p

p <- p +
  geom_vline(data     = ringkasan,
             aes(xintercept = rata_RT, color = Label_HP),
             linetype = "dashed",
             size     = 1)
p

p <- p +
  scale_fill_manual(values  = palet_hp) +
  scale_color_manual(values = palet_hp)
p

p <- p +
  labs(
    title    = "Distribusi Skor Kritikus Film Hollywood (2007-2011)",
    subtitle = "Harry Potter vs Film Lainnya - Rotten Tomatoes Score",
    x        = "Skor Rotten Tomatoes",
    y        = "Kepadatan",
    fill     = "Kategori Film",
    color    = "Rata-rata per Grup",
    caption  = "Sumber: reisanar/datasets via GitHub"
  )
p

p <- p +
  theme_minimal(base_size = 10) +
  theme(
    plot.title       = element_text(face = "bold", size = 13),
    plot.subtitle    = element_text(face = "italic", size = 9,
                                    color = "gray40"),
    panel.grid.minor = element_blank(),
    legend.position  = "bottom"
  )
p

R Markdown

This is an R Markdown document. Markdown is a simple formatting syntax for authoring HTML, PDF, and MS Word documents. For more details on using R Markdown see http://rmarkdown.rstudio.com.

When you click the Knit button a document will be generated that includes both content as well as the output of any embedded R code chunks within the document. You can embed an R code chunk like this:

summary(cars)
##      speed           dist       
##  Min.   : 4.0   Min.   :  2.00  
##  1st Qu.:12.0   1st Qu.: 26.00  
##  Median :15.0   Median : 36.00  
##  Mean   :15.4   Mean   : 42.98  
##  3rd Qu.:19.0   3rd Qu.: 56.00  
##  Max.   :25.0   Max.   :120.00

Including Plots

You can also embed plots, for example:

Note that the echo = FALSE parameter was added to the code chunk to prevent printing of the R code that generated the plot.