library(knitr)
library(rmarkdown)
library(magrittr)
library(plyr)
library(dplyr)##
## Attaching package: 'dplyr'## The following objects are masked from 'package:plyr':
##
## arrange, count, desc, failwith, id, mutate, rename, summarise,
## summarize## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unionmy_url <- "https://raw.githubusercontent.com/geedoubledee/R/main/rpdr_contep.csv"
rpdr_df <- read.csv(file=my_url, header=TRUE, stringsAsFactors=FALSE)A lot of the summary statistics returned by the summary function are meaningless for this particular dataset, so below I calculate means/medians for two attributes I am interested in: the number of episodes per season and the ranks of the Miss Congeniality winners.
summary(rpdr_df)## X season rank missc
## Min. : 1.0 Length:2320 Min. : 1.00 Min. :0.00000
## 1st Qu.: 580.8 Class :character 1st Qu.: 3.00 1st Qu.:0.00000
## Median :1160.5 Mode :character Median : 7.00 Median :0.00000
## Mean :1160.5 Mean : 7.08 Mean :0.07545
## 3rd Qu.:1740.2 3rd Qu.:10.00 3rd Qu.:0.00000
## Max. :2320.0 Max. :15.00 Max. :1.00000
## NA's :14 NA's :14
## contestant episode outcome eliminated
## Length:2320 Min. : 1.000 Length:2320 Min. :0.0000
## Class :character 1st Qu.: 4.000 Class :character 1st Qu.:0.0000
## Mode :character Median : 7.000 Mode :character Median :0.0000
## Mean : 7.132 Mean :0.0897
## 3rd Qu.:10.000 3rd Qu.:0.0000
## Max. :16.000 Max. :1.0000
## NA's :870
## participant minichalw finale penultimate
## Min. :0.000 Min. :0.0000 Min. :0.00000 Min. :0.00000
## 1st Qu.:0.000 1st Qu.:0.0000 1st Qu.:0.00000 1st Qu.:0.00000
## Median :1.000 Median :0.0000 Median :0.00000 Median :0.00000
## Mean :0.625 Mean :0.0455 Mean :0.07931 Mean :0.01724
## 3rd Qu.:1.000 3rd Qu.:0.0000 3rd Qu.:0.00000 3rd Qu.:0.00000
## Max. :1.000 Max. :1.0000 Max. :1.00000 Max. :1.00000
## NA's :870rpdr_df_temp <- rpdr_df
rpdr_df_temp %<>%
group_by(season) %>%
summarize(ep_count=max(episode))
head(rpdr_df_temp)## # A tibble: 6 × 2
## season ep_count
## <chr> <int>
## 1 S01 8
## 2 S02 11
## 3 S03 15
## 4 S04 14
## 5 S05 14
## 6 S06 14print("The mean number of episodes per season is:")## [1] "The mean number of episodes per season is:"mean(rpdr_df_temp$ep_count)## [1] 13.42857print("The median number of episodes per season is:")## [1] "The median number of episodes per season is:"median(rpdr_df_temp$ep_count)## [1] 14rpdr_df_temp <- rpdr_df
rpdr_df_temp %<>%
filter(missc == TRUE) %>% #display only Miss Congeniality winners
distinct(season, contestant, rank) #remove duplicate rows
head(rpdr_df_temp)## season rank contestant
## 1 S01 2 Nina Flowers
## 2 S02 5 Pandora Boxx
## 3 S03 4 Yara Sofia
## 4 S04 4 Latrice Royale
## 5 S05 7 Ivy Winters
## 6 S06 5 BenDeLaCremeprint("The mean rank of the Miss Congeniality winners is:")## [1] "The mean rank of the Miss Congeniality winners is:"mean(rpdr_df_temp$rank)## [1] 6.285714print("The median rank of the Miss Congeniality winners is:")## [1] "The median rank of the Miss Congeniality winners is:"median(rpdr_df_temp$rank)## [1] 5.5rpdr_df_wins_only <- rpdr_df
rpdr_df_wins_only %<>%
select(season, contestant, rank, episode, outcome) %>%
# display only the winning outcomes
filter(outcome %in% c("WIN", "WIN+RTRN", "Winner")) %>%
arrange(rank, contestant)
head(rpdr_df_wins_only)## season contestant rank episode outcome
## 1 S10 Aquaria 1 4 WIN
## 2 S10 Aquaria 1 7 WIN
## 3 S10 Aquaria 1 11 WIN
## 4 S10 Aquaria 1 14 WIN
## 5 S01 BeBe Zahara Benet 1 3 WIN
## 6 S01 BeBe Zahara Benet 1 6 WINcolnames(rpdr_df_wins_only) <- c("SEAS", "CONT", "RANK", "EPIS", "OUTC")
head(rpdr_df_wins_only)## SEAS CONT RANK EPIS OUTC
## 1 S10 Aquaria 1 4 WIN
## 2 S10 Aquaria 1 7 WIN
## 3 S10 Aquaria 1 11 WIN
## 4 S10 Aquaria 1 14 WIN
## 5 S01 BeBe Zahara Benet 1 3 WIN
## 6 S01 BeBe Zahara Benet 1 6 WINAgain, the summary function isn’t particularly useful for this dataset. Neither the mean nor the median number of episodes should have changed for our subset of the data though, and I recalculated them below to confirm. They remain the same.
summary(rpdr_df_wins_only)## SEAS CONT RANK EPIS
## Length:192 Length:192 Min. : 1.000 Min. : 1.000
## Class :character Class :character 1st Qu.: 1.000 1st Qu.: 3.000
## Mode :character Mode :character Median : 2.000 Median : 7.000
## Mean : 3.142 Mean : 6.781
## 3rd Qu.: 4.000 3rd Qu.:10.000
## Max. :12.000 Max. :16.000
## NA's :2
## OUTC
## Length:192
## Class :character
## Mode :character
##
##
##
## rpdr_df_wins_only_temp <- rpdr_df_wins_only
rpdr_df_wins_only_temp %<>%
group_by(SEAS) %>%
summarize(EP_COUNT=max(EPIS))
head(rpdr_df_wins_only_temp)## # A tibble: 6 × 2
## SEAS EP_COUNT
## <chr> <int>
## 1 S01 8
## 2 S02 11
## 3 S03 15
## 4 S04 14
## 5 S05 14
## 6 S06 14print("The mean number of episodes per season is still:")## [1] "The mean number of episodes per season is still:"mean(rpdr_df_wins_only_temp$EP_COUNT)## [1] 13.42857print("The median number of episodes per season is still:")## [1] "The median number of episodes per season is still:"median(rpdr_df_wins_only_temp$EP_COUNT)## [1] 14Our subset of the data no longer includes the Miss Congeniality winner data, so let’s look at the mean number of episode wins for each season winner (where rank == 1) instead.
rpdr_df_wins_only_temp <- rpdr_df_wins_only
rpdr_df_wins_only_temp %<>%
filter(RANK == 1) %>% #display only the winners of each season
group_by(SEAS, CONT) %>%
summarize(WINS = n())## `summarise()` has grouped output by 'SEAS'. You can override using the
## `.groups` argument.colnames(rpdr_df_wins_only_temp) <- c("SEASON", "WINNER", "WINS")
head(rpdr_df_wins_only_temp)## # A tibble: 6 × 3
## # Groups: SEASON [6]
## SEASON WINNER WINS
## <chr> <chr> <int>
## 1 S01 BeBe Zahara Benet 3
## 2 S02 Tyra Sanchez 4
## 3 S03 Raja 4
## 4 S04 Sharon Needles 5
## 5 S05 Jinkx Monsoon 3
## 6 S06 Bianca Del Rio 5print("The mean number of episode wins for each season winner is:")## [1] "The mean number of episode wins for each season winner is:"mean(rpdr_df_wins_only_temp$WINS)## [1] 3.928571print("The median number of episode wins for each season winner is:")## [1] "The median number of episode wins for each season winner is:"median(rpdr_df_wins_only_temp$WINS)## [1] 4rpdr_df_ranks_renamed <- rpdr_df
rank_words <- c("FIRST", "SECOND", "THIRD", "FOURTH", "FIFTH",
"SIXTH", "SEVENTH", "EIGHTH", "NINTH", "TENTH",
"ELEVENTH", "TWELFTH", "THIRTEENTH",
"FOURTEENTH", "FIFTEENTH", "SIXTEENTH")
rpdr_df_ranks_renamed %<>%
mutate(rank = rank_words[rank])
head(rpdr_df_ranks_renamed)## X season rank missc contestant episode outcome eliminated
## 1 1 S01 FIRST 0 BeBe Zahara Benet 1 SAFE 0
## 2 2 S01 SECOND 1 Nina Flowers 1 WIN 0
## 3 3 S01 THIRD 0 Rebecca Glasscock 1 LOW 0
## 4 4 S01 FOURTH 0 Shannel 1 SAFE 0
## 5 5 S01 FIFTH 0 Ongina 1 HIGH 0
## 6 6 S01 SIXTH 0 Jade 1 SAFE 0
## participant minichalw finale penultimate
## 1 1 0 0 0
## 2 1 0 0 0
## 3 1 0 0 0
## 4 1 0 0 0
## 5 1 0 0 0
## 6 1 0 0 0