TidyVerseRecipe

Nilsa Bermudez

library(tidyverse);
library(reshape)
library(plyr)

For this assignment I will create an example. Using one or more TidyVerse packages, and any dataset from fivethirtyeight.com or Kaggle, create a programming sample “vignette” that demonstrates how to use one or more of the capabilities of the selected TidyVerse package with my selected dataset.”

In light of the current situation across the world, I chose the Bob Ross elements by episode recordset.

Load the Bob Ross dataset from fivethirtyeight into the RStudio environment:

url<-"https://raw.githubusercontent.com/fivethirtyeight/data/master/bob-ross/elements-by-episode.csv"
BobRoss <- read_csv(url)

## Parsed with column specification:
## cols(
##   .default = col_double(),
##   EPISODE = col_character(),
##   TITLE = col_character()
## )

## See spec(...) for full column specifications.

df <- data.frame(BobRoss)

Use the Reshape library’s method ‘melt’ to transform the data set froma wide format to a long format

Bulkbobr <- reshape::melt(df, id=c("EPISODE","TITLE"))
Bob <- unique(subset(Bulkbobr, value == 1, select = c("EPISODE","TITLE","variable")))
Bob <-Bob[order(Bob$EPISODE),]
Bob <- rename(Bob, c("variable"="object"))
head(Bob,10)

##       EPISODE                 TITLE    object
## 2822   S01E01 "A WALK IN THE WOODS"    BUSHES
## 6449   S01E01 "A WALK IN THE WOODS" DECIDUOUS
## 10882  S01E01 "A WALK IN THE WOODS"     GRASS
## 19345  S01E01 "A WALK IN THE WOODS"     RIVER
## 23375  S01E01 "A WALK IN THE WOODS"      TREE
## 23778  S01E01 "A WALK IN THE WOODS"     TREES
## 3226   S01E02        "MT. MCKINLEY"     CABIN
## 5241   S01E02        "MT. MCKINLEY"    CLOUDS
## 5644   S01E02        "MT. MCKINLEY"   CONIFER
## 14913  S01E02        "MT. MCKINLEY"  MOUNTAIN

Bob2 <-count(Bob,vars="object", wt_var = NULL)
Bob2 <- Bob2 %>% dplyr::arrange( freq )

  top10 <- tail(Bob2, n = 10)
  ggplot(data=top10,aes(x=object, y=freq)) +  
  ggplot2::aes(x=reorder(object, -freq), y=freq) +
  ggplot2::geom_bar(stat="identity",fill="steelblue") +
  ggplot2::labs(x="Objects",y="Frequency") +
  ggplot2::ggtitle("Most used objects in Bob Ross Paintings") +
  ggplot2::theme(axis.text.x = ggplot2::element_text(angle = 90, vjust = 0.5, hjust=1))

Now use tidyr’s ‘pivot_longer()’ and dplyr methods to replicate same reshaping of the the data and reproduce the same figure as above:

Bob3 <- df %>%
    pivot_longer(cols=3:69,names_to = "variable", values_to = "value") %>%
    filter(value==1) %>%
    select(-value) %>%
    dplyr::rename( object = variable ) %>%
    group_by( object ) %>%
    dplyr::summarise('count'= n()) %>%
    dplyr::arrange( desc(count)) %>%
    dplyr::top_n(10) %>%
    ggplot(aes(x=object, y=count)) +  
    ggplot2::aes(x=reorder(object, -count), y=count) +
    ggplot2::geom_bar(stat="identity",fill="steelblue") +
    ggplot2::labs(x="Objects",y="Frequency") +
    ggplot2::ggtitle("Most used objects in Bob Ross Paintings") +
    ggplot2::theme(axis.text.x = ggplot2::element_text(angle = 90, vjust = 0.5, hjust=1))
Bob3