Harold Nelson
3/9/2021
This is from Tidy Tuesday of March 2, 2021.
youtube <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2021/2021-03-02/youtube.csv')##
## ── Column specification ────────────────────────────────────────────────────────
## cols(
## .default = col_character(),
## year = col_double(),
## funny = col_logical(),
## show_product_quickly = col_logical(),
## patriotic = col_logical(),
## celebrity = col_logical(),
## danger = col_logical(),
## animals = col_logical(),
## use_sex = col_logical(),
## view_count = col_double(),
## like_count = col_double(),
## dislike_count = col_double(),
## favorite_count = col_double(),
## comment_count = col_double(),
## published_at = col_datetime(format = ""),
## category_id = col_double()
## )
## ℹ Use `spec()` for the full column specifications.## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.0 ──## ✓ ggplot2 3.3.3 ✓ purrr 0.3.4
## ✓ tibble 3.0.6 ✓ dplyr 1.0.4
## ✓ tidyr 1.1.2 ✓ stringr 1.4.0
## ✓ readr 1.4.0 ✓ forcats 0.5.1## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()## Rows: 247
## Columns: 25
## $ year <dbl> 2018, 2020, 2006, 2018, 2003, 2020, 2020, 2…
## $ brand <chr> "Toyota", "Bud Light", "Bud Light", "Hynuda…
## $ superbowl_ads_dot_com_url <chr> "https://superbowl-ads.com/good-odds-toyota…
## $ youtube_url <chr> "https://www.youtube.com/watch?v=zeBZvwYQ-h…
## $ funny <lgl> FALSE, TRUE, TRUE, FALSE, TRUE, TRUE, TRUE,…
## $ show_product_quickly <lgl> FALSE, TRUE, FALSE, TRUE, TRUE, TRUE, FALSE…
## $ patriotic <lgl> FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, F…
## $ celebrity <lgl> FALSE, TRUE, FALSE, FALSE, FALSE, TRUE, TRU…
## $ danger <lgl> FALSE, TRUE, TRUE, FALSE, TRUE, TRUE, FALSE…
## $ animals <lgl> FALSE, FALSE, TRUE, FALSE, TRUE, TRUE, TRUE…
## $ use_sex <lgl> FALSE, FALSE, FALSE, FALSE, TRUE, FALSE, FA…
## $ id <chr> "zeBZvwYQ-hA", "nbbp0VW7z8w", "yk0MQD5YgV8"…
## $ kind <chr> "youtube#video", "youtube#video", "youtube#…
## $ etag <chr> "rn-ggKNly38Cl0C3CNjNnUH9xUw", "1roDoK-SYqS…
## $ view_count <dbl> 173929, 47752, 142310, 198, 13741, 23636, 3…
## $ like_count <dbl> 1233, 485, 129, 2, 20, 115, 1470, 78, 342, …
## $ dislike_count <dbl> 38, 14, 15, 0, 3, 11, 384, 6, 7, 0, 14, 0, …
## $ favorite_count <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ comment_count <dbl> NA, 14, 9, 0, 2, 13, 227, 6, 30, 0, 8, 1, 1…
## $ published_at <dttm> 2018-02-03 11:29:14, 2020-01-31 21:04:13, …
## $ title <chr> "Toyota Super Bowl Commercial 2018 Good Odd…
## $ description <chr> "Toyota Super Bowl Commercial 2018 Good Odd…
## $ thumbnail <chr> "https://i.ytimg.com/vi/zeBZvwYQ-hA/sddefau…
## $ channel_title <chr> "Funny Commercials", "VCU Brandcenter", "Jo…
## $ category_id <dbl> 1, 27, 17, 22, 24, 1, 24, 2, 24, 24, 24, 24…## spec_tbl_df [247 × 25] (S3: spec_tbl_df/tbl_df/tbl/data.frame)
## $ year : num [1:247] 2018 2020 2006 2018 2003 ...
## $ brand : chr [1:247] "Toyota" "Bud Light" "Bud Light" "Hynudai" ...
## $ superbowl_ads_dot_com_url: chr [1:247] "https://superbowl-ads.com/good-odds-toyota/" "https://superbowl-ads.com/2020-bud-light-seltzer-inside-posts-brain/" "https://superbowl-ads.com/2006-bud-light-bear-attack/" "https://superbowl-ads.com/hope-detector-nfl-super-bowl-lii-hyundai/" ...
## $ youtube_url : chr [1:247] "https://www.youtube.com/watch?v=zeBZvwYQ-hA" "https://www.youtube.com/watch?v=nbbp0VW7z8w" "https://www.youtube.com/watch?v=yk0MQD5YgV8" "https://www.youtube.com/watch?v=lNPccrGk77A" ...
## $ funny : logi [1:247] FALSE TRUE TRUE FALSE TRUE TRUE ...
## $ show_product_quickly : logi [1:247] FALSE TRUE FALSE TRUE TRUE TRUE ...
## $ patriotic : logi [1:247] FALSE FALSE FALSE FALSE FALSE FALSE ...
## $ celebrity : logi [1:247] FALSE TRUE FALSE FALSE FALSE TRUE ...
## $ danger : logi [1:247] FALSE TRUE TRUE FALSE TRUE TRUE ...
## $ animals : logi [1:247] FALSE FALSE TRUE FALSE TRUE TRUE ...
## $ use_sex : logi [1:247] FALSE FALSE FALSE FALSE TRUE FALSE ...
## $ id : chr [1:247] "zeBZvwYQ-hA" "nbbp0VW7z8w" "yk0MQD5YgV8" "lNPccrGk77A" ...
## $ kind : chr [1:247] "youtube#video" "youtube#video" "youtube#video" "youtube#video" ...
## $ etag : chr [1:247] "rn-ggKNly38Cl0C3CNjNnUH9xUw" "1roDoK-SYqSpqYwKbYrMH0jEJQ4" "OHiDfHTB3kilXfN8W0VTH0nwUIg" "G9Dhby9Xe1UpnfcIrHmcnZYRCFI" ...
## $ view_count : num [1:247] 173929 47752 142310 198 13741 ...
## $ like_count : num [1:247] 1233 485 129 2 20 ...
## $ dislike_count : num [1:247] 38 14 15 0 3 11 384 6 7 0 ...
## $ favorite_count : num [1:247] 0 0 0 0 0 0 0 0 0 0 ...
## $ comment_count : num [1:247] NA 14 9 0 2 13 227 6 30 0 ...
## $ published_at : POSIXct[1:247], format: "2018-02-03 11:29:14" "2020-01-31 21:04:13" ...
## $ title : chr [1:247] "Toyota Super Bowl Commercial 2018 Good Odds" "Bud Light: Post Malone #PostyStore Inside Post's Brain" "Super Bowl 2006: Bud Light \"Save Yourself\"" "Hyundai / Hope Detector (2018)" ...
## $ description : chr [1:247] "Toyota Super Bowl Commercial 2018 Good Odds. You can watch Toyota Super Bowl 2018 commercial. Toyota has aired "| __truncated__ "Bud Light, Post Malone \"#PostyStore Inside Post's Brain\"\n\nGarrick Sheldon (Copywriting, 2014)\nWieden + Ken"| __truncated__ "Bud Light Super Bowl commercial where two guys camping encounter a bear." "TV or Web Commercial, shot on location in MN with a non-union crew and contract, 2018. This commercial is uplo"| __truncated__ ...
## $ thumbnail : chr [1:247] "https://i.ytimg.com/vi/zeBZvwYQ-hA/sddefault.jpg" "https://i.ytimg.com/vi/nbbp0VW7z8w/sddefault.jpg" NA NA ...
## $ channel_title : chr [1:247] "Funny Commercials" "VCU Brandcenter" "John Keehler" "IATSE 490" ...
## $ category_id : num [1:247] 1 27 17 22 24 1 24 2 24 24 ...
## - attr(*, "spec")=
## .. cols(
## .. year = col_double(),
## .. brand = col_character(),
## .. superbowl_ads_dot_com_url = col_character(),
## .. youtube_url = col_character(),
## .. funny = col_logical(),
## .. show_product_quickly = col_logical(),
## .. patriotic = col_logical(),
## .. celebrity = col_logical(),
## .. danger = col_logical(),
## .. animals = col_logical(),
## .. use_sex = col_logical(),
## .. id = col_character(),
## .. kind = col_character(),
## .. etag = col_character(),
## .. view_count = col_double(),
## .. like_count = col_double(),
## .. dislike_count = col_double(),
## .. favorite_count = col_double(),
## .. comment_count = col_double(),
## .. published_at = col_datetime(format = ""),
## .. title = col_character(),
## .. description = col_character(),
## .. thumbnail = col_character(),
## .. channel_title = col_character(),
## .. category_id = col_double()
## .. )## year brand superbowl_ads_dot_com_url youtube_url
## Min. :2000 Length:247 Length:247 Length:247
## 1st Qu.:2005 Class :character Class :character Class :character
## Median :2010 Mode :character Mode :character Mode :character
## Mean :2010
## 3rd Qu.:2015
## Max. :2020
##
## funny show_product_quickly patriotic celebrity
## Mode :logical Mode :logical Mode :logical Mode :logical
## FALSE:76 FALSE:78 FALSE:206 FALSE:176
## TRUE :171 TRUE :169 TRUE :41 TRUE :71
##
##
##
##
## danger animals use_sex id
## Mode :logical Mode :logical Mode :logical Length:247
## FALSE:172 FALSE:155 FALSE:181 Class :character
## TRUE :75 TRUE :92 TRUE :66 Mode :character
##
##
##
##
## kind etag view_count like_count
## Length:247 Length:247 Min. : 10 Min. : 0
## Class :character Class :character 1st Qu.: 6431 1st Qu.: 19
## Mode :character Mode :character Median : 41379 Median : 130
## Mean : 1407556 Mean : 4146
## 3rd Qu.: 170016 3rd Qu.: 527
## Max. :176373378 Max. :275362
## NA's :16 NA's :22
## dislike_count favorite_count comment_count
## Min. : 0.0 Min. :0 Min. : 0.00
## 1st Qu.: 1.0 1st Qu.:0 1st Qu.: 1.00
## Median : 7.0 Median :0 Median : 10.00
## Mean : 833.5 Mean :0 Mean : 188.64
## 3rd Qu.: 24.0 3rd Qu.:0 3rd Qu.: 50.75
## Max. :92990.0 Max. :0 Max. :9190.00
## NA's :22 NA's :16 NA's :25
## published_at title description
## Min. :2006-02-06 10:02:36 Length:247 Length:247
## 1st Qu.:2009-02-02 03:59:35 Class :character Class :character
## Median :2013-01-31 09:13:55 Mode :character Mode :character
## Mean :2012-12-23 22:41:37
## 3rd Qu.:2016-04-09 11:09:50
## Max. :2021-01-27 13:11:29
## NA's :16
## thumbnail channel_title category_id
## Length:247 Length:247 Min. : 1.00
## Class :character Class :character 1st Qu.:17.00
## Mode :character Mode :character Median :23.00
## Mean :19.32
## 3rd Qu.:24.00
## Max. :29.00
## NA's :16The skimr package is an option for examining a dataframe. It returns a dataframe.
Get the skimr output and use View()
| skim_type | skim_variable | n_missing | complete_rate | character.min | character.max | character.empty | character.n_unique | character.whitespace | logical.mean | logical.count | numeric.mean | numeric.sd | numeric.p0 | numeric.p25 | numeric.p50 | numeric.p75 | numeric.p100 | numeric.hist | POSIXct.min | POSIXct.max | POSIXct.median | POSIXct.n_unique |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| character | brand | 0 | 1.0000000 | 3 | 9 | 0 | 10 | 0 | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA |
| character | superbowl_ads_dot_com_url | 0 | 1.0000000 | 34 | 120 | 0 | 244 | 0 | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA |
| character | youtube_url | 11 | 0.9554656 | 43 | 43 | 0 | 233 | 0 | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA |
| character | id | 11 | 0.9554656 | 11 | 11 | 0 | 233 | 0 | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA |
| character | kind | 16 | 0.9352227 | 13 | 13 | 0 | 1 | 0 | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA |
| character | etag | 16 | 0.9352227 | 27 | 27 | 0 | 228 | 0 | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA |
| character | title | 16 | 0.9352227 | 6 | 99 | 0 | 228 | 0 | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA |
| character | description | 50 | 0.7975709 | 3 | 3527 | 0 | 194 | 0 | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA |
| character | thumbnail | 129 | 0.4777328 | 48 | 48 | 0 | 118 | 0 | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA |
| character | channel_title | 16 | 0.9352227 | 3 | 37 | 0 | 185 | 0 | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA |
| logical | funny | 0 | 1.0000000 | NA | NA | NA | NA | NA | 0.6923077 | TRU: 171, FAL: 76 | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA |
| logical | show_product_quickly | 0 | 1.0000000 | NA | NA | NA | NA | NA | 0.6842105 | TRU: 169, FAL: 78 | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA |
| logical | patriotic | 0 | 1.0000000 | NA | NA | NA | NA | NA | 0.1659919 | FAL: 206, TRU: 41 | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA |
| logical | celebrity | 0 | 1.0000000 | NA | NA | NA | NA | NA | 0.2874494 | FAL: 176, TRU: 71 | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA |
| logical | danger | 0 | 1.0000000 | NA | NA | NA | NA | NA | 0.3036437 | FAL: 172, TRU: 75 | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA |
| logical | animals | 0 | 1.0000000 | NA | NA | NA | NA | NA | 0.3724696 | FAL: 155, TRU: 92 | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA |
| logical | use_sex | 0 | 1.0000000 | NA | NA | NA | NA | NA | 0.2672065 | FAL: 181, TRU: 66 | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA |
| numeric | year | 0 | 1.0000000 | NA | NA | NA | NA | NA | NA | NA | 2.010190e+03 | 5.860872e+00 | 2000 | 2005 | 2010 | 2015.00 | 2020 | ▇▇▇▇▆ | NA | NA | NA | NA |
| numeric | view_count | 16 | 0.9352227 | NA | NA | NA | NA | NA | NA | NA | 1.407556e+06 | 1.197111e+07 | 10 | 6431 | 41379 | 170015.50 | 176373378 | ▇▁▁▁▁ | NA | NA | NA | NA |
| numeric | like_count | 22 | 0.9109312 | NA | NA | NA | NA | NA | NA | NA | 4.146031e+03 | 2.392040e+04 | 0 | 19 | 130 | 527.00 | 275362 | ▇▁▁▁▁ | NA | NA | NA | NA |
| numeric | dislike_count | 22 | 0.9109312 | NA | NA | NA | NA | NA | NA | NA | 8.335378e+02 | 6.948522e+03 | 0 | 1 | 7 | 24.00 | 92990 | ▇▁▁▁▁ | NA | NA | NA | NA |
| numeric | favorite_count | 16 | 0.9352227 | NA | NA | NA | NA | NA | NA | NA | 0.000000e+00 | 0.000000e+00 | 0 | 0 | 0 | 0.00 | 0 | ▁▁▇▁▁ | NA | NA | NA | NA |
| numeric | comment_count | 25 | 0.8987854 | NA | NA | NA | NA | NA | NA | NA | 1.886396e+02 | 9.864569e+02 | 0 | 1 | 10 | 50.75 | 9190 | ▇▁▁▁▁ | NA | NA | NA | NA |
| numeric | category_id | 16 | 0.9352227 | NA | NA | NA | NA | NA | NA | NA | 1.931602e+01 | 8.004328e+00 | 1 | 17 | 23 | 24.00 | 29 | ▃▁▂▆▇ | NA | NA | NA | NA |
| POSIXct | published_at | 16 | 0.9352227 | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA | 2006-02-06 10:02:36 | 2021-01-27 13:11:29 | 2013-01-31 09:13:55 | 227 |