upsettest.r

nobs <- 4000
pb <- round(runif(n=1, min=0.1, max=0.8),1)
August <- rbinom(n=nobs, size=1, prob=pb)
pb <- round(runif(n=1, min=0.1, max=0.8),1)
September <- rbinom(n=nobs, size=1, prob=pb)
pb <- round(runif(n=1, min=0.1, max=0.8),1)
October <- rbinom(n=nobs, size=1, prob=pb)
pb <- round(runif(n=1, min=0.1, max=0.8),1)
November <- rbinom(n=nobs, size=1, prob=pb)
pb <- round(runif(n=1, min=0.1, max=0.8),1)
December <- rbinom(n=nobs, size=1, prob=pb)


#generate random id
myFun <- function(n = nobs) {
  a <- do.call(paste0, replicate(5, sample(LETTERS, n, TRUE), FALSE))
  paste0(a, sprintf("%04d", sample(9999, n, TRUE)), sample(LETTERS, n, TRUE))
}

round(runif(n=1, min=200000, max=300000),1)


AumPre <- log(runif(nobs, min=100000, max=250000))
AumAft <- log(runif(nobs, min=100000, max=250000))
AumIncrease <- as.integer(AumAft > AumPre) + 1
table(AumIncrease)

ID <- myFun()
df <- data.frame(ID
                 , August
                 , September
                 , October
                 , November
                 , December
                 , AumPre
                 , AumAft
                 , AumIncrease)
str(df)
#NA replacement
df[is.na(df)] <- 0

df %>% select(ID, AumPre, AumAft, AumIncrease
              , August
              , September
              , October
              , November
              , December) -> df
upset(df, keep.order = T,
      sets = c("August"
               , "September"
               , "October"
               , "November"
               , "December"),boxplot.summary = c("AumAft"))

colnames(df)

summary(df)
nrow(df)
movies <- read.csv( system.file("extdata", "movies.csv", package = "UpSetR"), header=T, sep=";" )
df$x <- log(rep(x = movies$Watches+10,2)[1:nrow(df)])
df$y <- log(rep(x = movies$AvgRating+10,2)[1:nrow(df)])
upset(df
      , sets = c("August"
                 , "September"
                 , "October"
                 , "November"
                 , "December")
      , query.legend = "bottom"
      , number.angles = 30
      , point.size = 3.5
      , line.size = 2
      , sets.x.label = "Total Participants" 
      , queries = list(
        list(
          query = elements,
          params = list("AumIncrease", 1),
          color = "red",
          active = F
        )
        ,list(
          query = elements,
          params = list("AumIncrease", 2),
          color = "green",
          active = F
        )
      )
)

colnames(df)
upset(df
      , attribute.plots = list(gridrows = 100, ncols = 1, 
                               plots = list(
                                 list(plot = histogram, x = "x",queries = F),
                                 list(plot = scatter_plot, y = "AumAft", x = "AumPre", queries = T),
                                 list(plot = scatter_plot, y = "x", x = "y", queries = T)))
      , sets = c("August", "September", "October", "November", "December")
      , queries = list(
        list(
          query = elements,
          params = list("AumIncrease", 1),
          color = "red",
          active = F
        )
        ,list(
          query = elements,
          params = list("AumIncrease", 2),
          color = "green",
          active = F
        )
      )
)