Data Manipulation

We install the packages we need for this analysis.

library(tidyverse)
library(lubridate)
library(ggplot2)
library(dplyr)
library(readr)
library(knitr)
library(kableExtra)
library(rmdformats)

We read file and control data type of columns. Also, if we want to show the table in a compact format, we can use the kable function.

df_raw <- read.csv("C:/Users/bmire/Desktop/MEF BDA/R Course/R Studio/netflix_titles.csv", stringsAsFactors = FALSE, na.strings=c("","NA"))
str(df_raw)

## 'data.frame':    6234 obs. of  12 variables:
##  $ show_id     : int  81145628 80117401 70234439 80058654 80125979 80163890 70304989 80164077 80117902 70304990 ...
##  $ type        : chr  "Movie" "Movie" "TV Show" "TV Show" ...
##  $ title       : chr  "Norm of the North: King Sized Adventure" "Jandino: Whatever it Takes" "Transformers Prime" "Transformers: Robots in Disguise" ...
##  $ director    : chr  "Richard Finn, Tim Maltby" NA NA NA ...
##  $ cast        : chr  "Alan Marriott, Andrew Toth, Brian Dobson, Cole Howard, Jennifer Cameron, Jonathan Holmes, Lee Tockar, Lisa Duru"| __truncated__ "Jandino Asporaat" "Peter Cullen, Sumalee Montano, Frank Welker, Jeffrey Combs, Kevin Michael Richardson, Tania Gunadi, Josh Keaton"| __truncated__ "Will Friedle, Darren Criss, Constance Zimmer, Khary Payton, Mitchell Whitfield, Stuart Allan, Ted McGinley, Peter Cullen" ...
##  $ country     : chr  "United States, India, South Korea, China" "United Kingdom" "United States" "United States" ...
##  $ date_added  : chr  "September 9, 2019" "September 9, 2016" "September 8, 2018" "September 8, 2018" ...
##  $ release_year: int  2019 2016 2013 2016 2017 2016 2014 2017 2017 2014 ...
##  $ rating      : chr  "TV-PG" "TV-MA" "TV-Y7-FV" "TV-Y7" ...
##  $ duration    : chr  "90 min" "94 min" "1 Season" "1 Season" ...
##  $ listed_in   : chr  "Children & Family Movies, Comedies" "Stand-Up Comedy" "Kids' TV" "Kids' TV" ...
##  $ description : chr  "Before planning an awesome wedding for his grandfather, a polar bear king must take back a stolen artifact from"| __truncated__ "Jandino Asporaat riffs on the challenges of raising kids and serenades the audience with a rousing rendition of"| __truncated__ "With the help of three human allies, the Autobots once again protect Earth from the onslaught of the Decepticon"| __truncated__ "When a prison ship crash unleashes hundreds of Decepticons on Earth, Bumblebee leads a new Autobot force to protect humankind." ...

kable(df_raw[1:3,], "simple")

We control whether there is any null data. Now, I don’t want to delete the null data. Because we might need in the next steps.

colSums(is.na(df_raw))

##      show_id         type        title     director         cast      country 
##            0            0            0         1969          570          476 
##   date_added release_year       rating     duration    listed_in  description 
##           11            0           10            0            0            0

Then, we delete the columns that we do not need in the analysis.

df_raw$show_id <- NULL
df_raw$description <- NULL

We change the data types of categorical and date columns. Then, we check it again.

df_raw$type <- as.factor(df_raw$type)
df_raw$rating <- as.factor(df_raw$rating)
df_raw$listed_in <- as.factor(df_raw$listed_in)
df_raw$date_added <- mdy(df_raw$date_added)
str(df_raw) #check datatype

## 'data.frame':    6234 obs. of  10 variables:
##  $ type        : Factor w/ 2 levels "Movie","TV Show": 1 1 2 2 1 2 1 1 2 1 ...
##  $ title       : chr  "Norm of the North: King Sized Adventure" "Jandino: Whatever it Takes" "Transformers Prime" "Transformers: Robots in Disguise" ...
##  $ director    : chr  "Richard Finn, Tim Maltby" NA NA NA ...
##  $ cast        : chr  "Alan Marriott, Andrew Toth, Brian Dobson, Cole Howard, Jennifer Cameron, Jonathan Holmes, Lee Tockar, Lisa Duru"| __truncated__ "Jandino Asporaat" "Peter Cullen, Sumalee Montano, Frank Welker, Jeffrey Combs, Kevin Michael Richardson, Tania Gunadi, Josh Keaton"| __truncated__ "Will Friedle, Darren Criss, Constance Zimmer, Khary Payton, Mitchell Whitfield, Stuart Allan, Ted McGinley, Peter Cullen" ...
##  $ country     : chr  "United States, India, South Korea, China" "United Kingdom" "United States" "United States" ...
##  $ date_added  : Date, format: "2019-09-09" "2016-09-09" ...
##  $ release_year: int  2019 2016 2013 2016 2017 2016 2014 2017 2017 2014 ...
##  $ rating      : Factor w/ 14 levels "G","NC-17","NR",..: 10 9 13 12 7 9 6 9 9 6 ...
##  $ duration    : chr  "90 min" "94 min" "1 Season" "1 Season" ...
##  $ listed_in   : Factor w/ 461 levels "Action & Adventure",..: 111 421 382 382 168 218 338 421 273 58 ...

kable(df_raw[1:3,], "simple")

We remove duplicate columns.

df_raw = 
    distinct(df_raw, type, title,   director, cast, country, .keep_all = TRUE)
kable(df_raw[1:3,], "simple")

Data Visualization

Now, we can start the analysis and visualize.

df_type <- df_raw %>% group_by(type) %>% summarise(number_of_type = n())

ggplot(df_type,aes(x=type,y=number_of_type)) + geom_bar(stat="identity",aes(fill=type))

df_listed <- df_raw %>% na.omit(df_raw) %>% group_by(type,listed_in) %>% summarise(number_of_type = n()) %>% slice_max(order_by = number_of_type, n = 3)

kable(df_listed, "simple")

k <- strsplit(df_raw$country, split = ", ")
df_countries<- data.frame(type = rep(df_raw$type, sapply(k, length)), country = unlist(k))
df_countries$country <- as.character(df_countries$country)

df_top10 <- df_countries %>% na.omit(df_countries) %>% group_by(type, country) %>% summarise(number_of_type = n()) %>% 
            slice_max(order_by = number_of_type, n = 10)
ggplot(df_top10, aes(x=country, y = number_of_type)) + 
  geom_bar(stat = "identity",position = position_dodge(), aes(fill = type)) +
  theme(axis.text.x = element_text(angle = 90))

df_raw$year <- year(df_raw$date_added)

df_ts <- df_raw %>% group_by(year,type) %>% summarise(number_of_type = n()) %>% na.omit(df_raw)

ggplot(df_ts, aes(x=year, y = number_of_type)) + 
  geom_line(aes(colour = type), size = 2)+ 
  geom_point() 

df_genre10 <- df_raw  %>% na.omit(df_raw) %>% group_by(listed_in) %>% summarise(number_of_type = n()) %>% slice_max(order_by = number_of_type, n = 10)

kable(df_genre10, "simple")

df_dir10 <- df_raw  %>% na.omit(df_raw) %>% group_by(director) %>% summarise(number_of_type = n()) %>% slice_max(order_by = number_of_type, n = 10)

kable(df_dir10, "simple")