Mr Beast Youtube channels Analysis
The packages we need
library(tidyverse) # all tidyverse packages## Warning: le package 'tidyverse' a été compilé avec la version R 4.1.3## -- Attaching packages --------------------------------------- tidyverse 1.3.2 --## v ggplot2 3.3.5 v purrr 0.3.4
## v tibble 3.1.6 v dplyr 1.0.7
## v tidyr 1.1.4 v stringr 1.4.0
## v readr 2.1.3 v forcats 0.5.1## Warning: le package 'readr' a été compilé avec la version R 4.1.3## -- Conflicts ------------------------------------------ tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()library(purrr)
library(lubridate)##
## Attachement du package : 'lubridate'## Les objets suivants sont masqués depuis 'package:base':
##
## date, intersect, setdiff, unionlibrary(wordcloud)## Warning: le package 'wordcloud' a été compilé avec la version R 4.1.3## Le chargement a nécessité le package : RColorBrewer## Warning: le package 'RColorBrewer' a été compilé avec la version R 4.1.3library(RColorBrewer)
library(data.table)##
## Attachement du package : 'data.table'## Les objets suivants sont masqués depuis 'package:lubridate':
##
## hour, isoweek, mday, minute, month, quarter, second, wday, week,
## yday, year## Les objets suivants sont masqués depuis 'package:dplyr':
##
## between, first, last## L'objet suivant est masqué depuis 'package:purrr':
##
## transposelibrary(wordcloud)
library(tm)## Warning: le package 'tm' a été compilé avec la version R 4.1.3## Le chargement a nécessité le package : NLP##
## Attachement du package : 'NLP'## L'objet suivant est masqué depuis 'package:ggplot2':
##
## annotateRead the data
View the dataframe created
mrbeastdataframeUse the str function to summrize the data and the type of each colomn
str(mrbeastdataframe)## 'data.frame': 1551 obs. of 12 variables:
## $ X : int 1 2 3 4 5 6 7 8 9 10 ...
## $ id : chr "08wlrlPjWeE" "5rkMxc7yGSk" "7gYpJotNUEs" "aSQUg-h8G4s" ...
## $ title : chr "We Built Houses for Homeless Families" "Feeding a City in Need" "We Gave $3,000,000 of Aid to Ukrainian Refugees!" "We Built Wells in Africa!" ...
## $ publication_date: chr "2022-07-28" "2021-04-05" "2022-06-18" "2022-05-21" ...
## $ description : chr "Download Monster Legends now and go get my monsters! https://monsterlegends.onelink.me/X4Sc/beastphilanthropy\n"| __truncated__ "THIS IS MY FAVORITE VIDEO EVER! Thank you so much for watching this channel and allowing us to grow this charit"| __truncated__ "Go to our sponsor https://betterhelp.com/beastphilanthropy for 10% off your first month of therapy with BetterH"| __truncated__ "Download Dragon City for free, collect all MrBeast Dragons and claim the special rewards: https://dragoncity.on"| __truncated__ ...
## $ channel_id : chr "UCAiLfjNXkNv24uhpzUgPa6A" "UCAiLfjNXkNv24uhpzUgPa6A" "UCAiLfjNXkNv24uhpzUgPa6A" "UCAiLfjNXkNv24uhpzUgPa6A" ...
## $ channel_title : chr "Beast Philanthropy" "Beast Philanthropy" "Beast Philanthropy" "Beast Philanthropy" ...
## $ viewCount : int 9929978 7655799 9312039 24407740 4027048 6312862 15315917 5962100 13432363 4420165 ...
## $ likeCount : int 606477 755297 636795 1389776 302451 771142 869325 364730 638754 281479 ...
## $ favoriteCount : int 0 0 0 0 0 0 0 0 0 0 ...
## $ commentCount : int 14993 37239 53769 43244 9368 37456 38699 7947 26511 11394 ...
## $ url : chr "https://www.youtube.com/watch?v=08wlrlPjWeE" "https://www.youtube.com/watch?v=5rkMxc7yGSk" "https://www.youtube.com/watch?v=7gYpJotNUEs" "https://www.youtube.com/watch?v=aSQUg-h8G4s" ...The str() give us the colomns of the data frame and the type of each variable
we have 1551 observation with 12 variables
Cleaning the data
changing the type of publish_date from string to date using lubridate package
mrbeastdataframe %>%
mutate(publication_date=lubridate::as_date(publication_date)) -> mrbeastdataframechanging the type of the counts from string to numeric
mrbeastdataframe %>%
mutate(viewCount=as.numeric(viewCount),
commentCount=as.numeric(commentCount),
likeCount=as.numeric(likeCount),
favoriteCount =as.numeric(favoriteCount)
) -> mrbeastdataframecreat a year colomn
mrbeastdataframe %>%
mutate(year=year(publication_date)) -> mrbeastdataframecreat a year_mounth colomn
mrbeastdataframe %>%
mutate(year_month = paste(strftime(mrbeastdataframe$publication_date, "%Y"),
"-",
strftime(mrbeastdataframe$publication_date, "%m"),
paste("(",strftime(mrbeastdataframe$publication_date, "%b"), ")", sep=""))) ->mrbeastdataframemake a summary to the new dataframe
mrbeastdataframe %>%
summary()## X id title publication_date
## Min. : 1.0 Length:1551 Length:1551 Min. :2012-02-20
## 1st Qu.: 388.5 Class :character Class :character 1st Qu.:2016-02-12
## Median : 776.0 Mode :character Mode :character Median :2020-01-17
## Mean : 776.0 Mean :2019-04-07
## 3rd Qu.:1163.5 3rd Qu.:2021-12-11
## Max. :1551.0 Max. :2022-12-04
##
## description channel_id channel_title viewCount
## Length:1551 Length:1551 Length:1551 Min. : 0
## Class :character Class :character Class :character 1st Qu.: 344262
## Mode :character Mode :character Mode :character Median : 6550691
## Mean : 21421069
## 3rd Qu.: 27484713
## Max. :311873265
##
## likeCount favoriteCount commentCount url
## Min. : 61 Min. :0 Min. : 0.0 Length:1551
## 1st Qu.: 12702 1st Qu.:0 1st Qu.: 874.2 Class :character
## Median : 199591 Median :0 Median : 4326.0 Mode :character
## Mean : 599293 Mean :0 Mean : 23406.3
## 3rd Qu.: 713609 3rd Qu.:0 3rd Qu.: 25159.2
## Max. :20832736 Max. :0 Max. :1909751.0
## NA's :7 NA's :1
## year year_month
## Min. :2012 Length:1551
## 1st Qu.:2016 Class :character
## Median :2020 Mode :character
## Mean :2019
## 3rd Qu.:2021
## Max. :2022
## STARTING THE ANALYSIS PHASE
The total views for all Mrbeast channels
total_views=sum(mrbeastdataframe$viewCount)total views
total_views## [1] 33224077552ifelse(grepl('%', total_views), total_views, scales::comma(as.numeric(total_views), big = ' '))## [1] "33 224 077 552"#Main channel ####we use the filter to get the date related to the main channel MrBeast
mrbeastdataframe %>%
filter(channel_title=="MrBeast") ->mrbeast_main_channelsummmrize the data
summary(mrbeast_main_channel)## X id title publication_date
## Min. : 18.0 Length:731 Length:731 Min. :2012-02-20
## 1st Qu.:200.5 Class :character Class :character 1st Qu.:2015-04-16
## Median :383.0 Mode :character Mode :character Median :2015-12-23
## Mean :383.0 Mean :2016-09-30
## 3rd Qu.:565.5 3rd Qu.:2018-08-10
## Max. :748.0 Max. :2022-12-03
##
## description channel_id channel_title viewCount
## Length:731 Length:731 Length:731 Min. : 23721
## Class :character Class :character Class :character 1st Qu.: 51906
## Mode :character Mode :character Mode :character Median : 268800
## Mean : 26310059
## 3rd Qu.: 36587012
## Max. :311873265
##
## likeCount favoriteCount commentCount url
## Min. : 500 Min. :0 Min. : 81.0 Length:731
## 1st Qu.: 1783 1st Qu.:0 1st Qu.: 291.5 Class :character
## Median : 10665 Median :0 Median : 1251.5 Mode :character
## Mean : 781997 Mean :0 Mean : 31157.3
## 3rd Qu.: 1059317 3rd Qu.:0 3rd Qu.: 44323.8
## Max. :20832736 Max. :0 Max. :732669.0
## NA's :7 NA's :1
## year year_month
## Min. :2012 Length:731
## 1st Qu.:2015 Class :character
## Median :2015 Mode :character
## Mean :2016
## 3rd Qu.:2018
## Max. :2022
## total views of the main channel
creat a function rewrite to get write that put space between each 3 degit
rewrite <- function(i) {
ifelse(grepl('%', i), i, scales::comma(as.numeric(i), big = ' '))
} mrbeast_main_channel$viewCount %>%
sum() -> total_views_of_the_main_channel
rewrite(total_views_of_the_main_channel)## [1] "19 232 652 811"% of the the main channel from the total views
total_views_of_the_main_channel/total_views*100## [1] 57.8877####we can see the more then half of the views are coming from the main channel
mrbeast_main_channel$viewCount %>%
max() -> the_best
rewrite(the_best)## [1] "311 873 265"the_best/total_views_of_the_main_channel*100## [1] 1.621582views grouped by year
mrbeast_main_channel %>%
group_by(year) %>%
summarise(totaal=rewrite(sum(viewCount)))see the most used word in the titles :
mrbeast_main_channel %>%
select(title) ->titles
titles <- as.data.table(titles)
text <-titles
docs <- Corpus(VectorSource(text))
docs <- docs %>%
tm_map(removePunctuation) %>%
tm_map(stripWhitespace)## Warning in tm_map.SimpleCorpus(., removePunctuation): transformation drops
## documents## Warning in tm_map.SimpleCorpus(., stripWhitespace): transformation drops
## documentsdocs <- tm_map(docs, content_transformer(tolower))## Warning in tm_map.SimpleCorpus(docs, content_transformer(tolower)):
## transformation drops documentsdocs <- tm_map(docs, removeWords, stopwords("english"))## Warning in tm_map.SimpleCorpus(docs, removeWords, stopwords("english")):
## transformation drops documentsdtm <- TermDocumentMatrix(docs)
matrix <- as.matrix(dtm)
words <- sort(rowSums(matrix),decreasing=TRUE)
df <- data.frame(word = names(words),freq=words)set.seed(1234) # for reproducibility
wordcloud(words = df$word, freq = df$freq, min.freq = 3, max.words=100, random.order=FALSE, rot.per=0.350, colors=brewer.pal(8, "Paired"))