Module 6: Apply 5

Import data

# csv file
data <- read_csv("https://raw.githubusercontent.com/rfordatascience/tidytuesday/main/data/2025/2025-01-21/peaks_tidy.csv")

## Rows: 480 Columns: 29
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (14): PEAKID, PKNAME, PKNAME2, LOCATION, HIMAL_FACTOR, REGION_FACTOR, RE...
## dbl (12): HEIGHTM, HEIGHTF, HIMAL, REGION, TREKYEAR, PHOST, PSTATUS, PEAKMEM...
## lgl  (3): OPEN, UNLISTED, TREKKING
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

data

## # A tibble: 480 × 29
##    PEAKID PKNAME      PKNAME2 LOCATION HEIGHTM HEIGHTF HIMAL HIMAL_FACTOR REGION
##    <chr>  <chr>       <chr>   <chr>      <dbl>   <dbl> <dbl> <chr>         <dbl>
##  1 AMAD   Ama Dablam  Amai D… Khumbu …    6814   22356    12 Khumbu            2
##  2 AMPG   Amphu Gyab… Amphu … Khumbu …    5630   18471    12 Khumbu            2
##  3 ANN1   Annapurna I <NA>    Annapur…    8091   26545     1 Annapurna         5
##  4 ANN2   Annapurna … <NA>    Annapur…    7937   26040     1 Annapurna         5
##  5 ANN3   Annapurna … <NA>    Annapur…    7555   24787     1 Annapurna         5
##  6 ANN4   Annapurna … <NA>    Annapur…    7525   24688     1 Annapurna         5
##  7 ANNE   Annapurna … <NA>    Annapur…    8026   26332     1 Annapurna         5
##  8 ANNM   Annapurna … <NA>    Annapur…    8051   26414     1 Annapurna         5
##  9 ANNS   Annapurna … Annapu… Annapur…    7219   23684     1 Annapurna         5
## 10 APIM   Api Main    <NA>    Api Him…    7132   23399     2 Api/Byas Ri…      7
## # ℹ 470 more rows
## # ℹ 20 more variables: REGION_FACTOR <chr>, OPEN <lgl>, UNLISTED <lgl>,
## #   TREKKING <lgl>, TREKYEAR <dbl>, RESTRICT <chr>, PHOST <dbl>,
## #   PHOST_FACTOR <chr>, PSTATUS <dbl>, PSTATUS_FACTOR <chr>, PEAKMEMO <dbl>,
## #   PYEAR <dbl>, PSEASON <dbl>, PEXPID <chr>, PSMTDATE <chr>, PCOUNTRY <chr>,
## #   PSUMMITERS <chr>, PSMTNOTE <chr>, REFERMEMO <dbl>, PHOTOMEMO <dbl>

Apply the following dplyr verbs to your data

Filter rows

filter(data, PEAKID == "AMAD")

## # A tibble: 1 × 29
##   PEAKID PKNAME     PKNAME2   LOCATION HEIGHTM HEIGHTF HIMAL HIMAL_FACTOR REGION
##   <chr>  <chr>      <chr>     <chr>      <dbl>   <dbl> <dbl> <chr>         <dbl>
## 1 AMAD   Ama Dablam Amai Dab… Khumbu …    6814   22356    12 Khumbu            2
## # ℹ 20 more variables: REGION_FACTOR <chr>, OPEN <lgl>, UNLISTED <lgl>,
## #   TREKKING <lgl>, TREKYEAR <dbl>, RESTRICT <chr>, PHOST <dbl>,
## #   PHOST_FACTOR <chr>, PSTATUS <dbl>, PSTATUS_FACTOR <chr>, PEAKMEMO <dbl>,
## #   PYEAR <dbl>, PSEASON <dbl>, PEXPID <chr>, PSMTDATE <chr>, PCOUNTRY <chr>,
## #   PSUMMITERS <chr>, PSMTNOTE <chr>, REFERMEMO <dbl>, PHOTOMEMO <dbl>

Arrange rows

arrange(data, desc(PEAKID))

## # A tibble: 480 × 29
##    PEAKID PKNAME      PKNAME2 LOCATION HEIGHTM HEIGHTF HIMAL HIMAL_FACTOR REGION
##    <chr>  <chr>       <chr>   <chr>      <dbl>   <dbl> <dbl> <chr>         <dbl>
##  1 YUBR   Yubra       <NA>    Langtan…    6264   20551    13 Langtang          3
##  2 YOKO   Yokopahar   Nampa … Guras H…    6423   21073     2 Api/Byas Ri…      7
##  3 YNGS   Yangra Kan… Yangra… Ganesh …    6863   22516     5 Ganesh/Shri…      4
##  4 YLNG   Yalung Peak <NA>    Kangche…    7590   24902     9 Kangchenjun…      1
##  5 YAUP   Yaupa       <NA>    Makalu …    6422   21070    14 Makalu            2
##  6 YARW   Yarwa       <NA>    Guras H…    6644   21798     2 Api/Byas Ri…      7
##  7 YARA   Yara Chuli  Yala C… Palchun…    6236   20459    11 Kanti/Palch…      7
##  8 YANS   Yansa Tsen… Dragpo… Langtan…    6567   21545    13 Langtang          3
##  9 YANK   Yanme Kang  Yanme … Ohmi Ka…    6206   20361     6 Janak/Ohmi …      1
## 10 YANG   Yangri      Jugal   Jugal H…    6535   21440     8 Jugal             3
## # ℹ 470 more rows
## # ℹ 20 more variables: REGION_FACTOR <chr>, OPEN <lgl>, UNLISTED <lgl>,
## #   TREKKING <lgl>, TREKYEAR <dbl>, RESTRICT <chr>, PHOST <dbl>,
## #   PHOST_FACTOR <chr>, PSTATUS <dbl>, PSTATUS_FACTOR <chr>, PEAKMEMO <dbl>,
## #   PYEAR <dbl>, PSEASON <dbl>, PEXPID <chr>, PSMTDATE <chr>, PCOUNTRY <chr>,
## #   PSUMMITERS <chr>, PSMTNOTE <chr>, REFERMEMO <dbl>, PHOTOMEMO <dbl>

Select columns

select(data, PEAKID)

## # A tibble: 480 × 1
##    PEAKID
##    <chr> 
##  1 AMAD  
##  2 AMPG  
##  3 ANN1  
##  4 ANN2  
##  5 ANN3  
##  6 ANN4  
##  7 ANNE  
##  8 ANNM  
##  9 ANNS  
## 10 APIM  
## # ℹ 470 more rows

Add columns

mutate(data,
       gain = paste0(PEAKID, "_", PKNAME))

## # A tibble: 480 × 30
##    PEAKID PKNAME      PKNAME2 LOCATION HEIGHTM HEIGHTF HIMAL HIMAL_FACTOR REGION
##    <chr>  <chr>       <chr>   <chr>      <dbl>   <dbl> <dbl> <chr>         <dbl>
##  1 AMAD   Ama Dablam  Amai D… Khumbu …    6814   22356    12 Khumbu            2
##  2 AMPG   Amphu Gyab… Amphu … Khumbu …    5630   18471    12 Khumbu            2
##  3 ANN1   Annapurna I <NA>    Annapur…    8091   26545     1 Annapurna         5
##  4 ANN2   Annapurna … <NA>    Annapur…    7937   26040     1 Annapurna         5
##  5 ANN3   Annapurna … <NA>    Annapur…    7555   24787     1 Annapurna         5
##  6 ANN4   Annapurna … <NA>    Annapur…    7525   24688     1 Annapurna         5
##  7 ANNE   Annapurna … <NA>    Annapur…    8026   26332     1 Annapurna         5
##  8 ANNM   Annapurna … <NA>    Annapur…    8051   26414     1 Annapurna         5
##  9 ANNS   Annapurna … Annapu… Annapur…    7219   23684     1 Annapurna         5
## 10 APIM   Api Main    <NA>    Api Him…    7132   23399     2 Api/Byas Ri…      7
## # ℹ 470 more rows
## # ℹ 21 more variables: REGION_FACTOR <chr>, OPEN <lgl>, UNLISTED <lgl>,
## #   TREKKING <lgl>, TREKYEAR <dbl>, RESTRICT <chr>, PHOST <dbl>,
## #   PHOST_FACTOR <chr>, PSTATUS <dbl>, PSTATUS_FACTOR <chr>, PEAKMEMO <dbl>,
## #   PYEAR <dbl>, PSEASON <dbl>, PEXPID <chr>, PSMTDATE <chr>, PCOUNTRY <chr>,
## #   PSUMMITERS <chr>, PSMTNOTE <chr>, REFERMEMO <dbl>, PHOTOMEMO <dbl>,
## #   gain <chr>

Summarize by groups