Week 8: Apply it to your data 7

Import your data

# csv file
data <- readr::read_csv("../00_data/myData.csv")

## Rows: 882 Columns: 69
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr  (22): EXPID, PEAKID, SEASON_FACTOR, HOST_FACTOR, ROUTE1, ROUTE2, NATION...
## dbl  (17): YEAR, SEASON, HOST, SMTDAYS, TOTDAYS, TERMREASON, HIGHPOINT, CAMP...
## lgl  (27): ROUTE3, ROUTE4, SUCCESS1, SUCCESS2, SUCCESS3, SUCCESS4, ASCENT3, ...
## date  (3): BCDATE, SMTDATE, TERMDATE
## 
## 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: 882 × 69
##    EXPID     PEAKID  YEAR SEASON SEASON_FACTOR  HOST HOST_FACTOR ROUTE1   ROUTE2
##    <chr>     <chr>  <dbl>  <dbl> <chr>         <dbl> <chr>       <chr>    <chr> 
##  1 EVER20101 EVER    2020      1 Spring            2 China       N Col-N… <NA>  
##  2 EVER20102 EVER    2020      1 Spring            2 China       N Col-N… <NA>  
##  3 EVER20103 EVER    2020      1 Spring            2 China       N Col-N… <NA>  
##  4 AMAD20301 AMAD    2020      3 Autumn            1 Nepal       SW Ridge <NA>  
##  5 AMAD20302 AMAD    2020      3 Autumn            1 Nepal       SW Ridge <NA>  
##  6 AMAD20303 AMAD    2020      3 Autumn            1 Nepal       SW Ridge <NA>  
##  7 AMAD20304 AMAD    2020      3 Autumn            1 Nepal       SW Ridge <NA>  
##  8 AMAD20305 AMAD    2020      3 Autumn            1 Nepal       SW Ridge <NA>  
##  9 AMAD20306 AMAD    2020      3 Autumn            1 Nepal       SW Ridge <NA>  
## 10 AMAD20307 AMAD    2020      3 Autumn            1 Nepal       SW Ridge <NA>  
## # ℹ 872 more rows
## # ℹ 60 more variables: ROUTE3 <lgl>, ROUTE4 <lgl>, NATION <chr>, LEADERS <chr>,
## #   SPONSOR <chr>, SUCCESS1 <lgl>, SUCCESS2 <lgl>, SUCCESS3 <lgl>,
## #   SUCCESS4 <lgl>, ASCENT1 <chr>, ASCENT2 <chr>, ASCENT3 <lgl>, ASCENT4 <lgl>,
## #   CLAIMED <lgl>, DISPUTED <lgl>, COUNTRIES <chr>, APPROACH <chr>,
## #   BCDATE <date>, SMTDATE <date>, SMTTIME <chr>, SMTDAYS <dbl>, TOTDAYS <dbl>,
## #   TERMDATE <date>, TERMREASON <dbl>, TERMREASON_FACTOR <chr>, …

Pivoting

long to wide form

data_long <- data %>%
        pivot_longer(cols = c("ROUTE1"), names_to = "ROUTE_NUMBER", values_to = "ROUTE_NAME")
data_long

## # A tibble: 882 × 70
##    EXPID     PEAKID  YEAR SEASON SEASON_FACTOR  HOST HOST_FACTOR ROUTE2 ROUTE3
##    <chr>     <chr>  <dbl>  <dbl> <chr>         <dbl> <chr>       <chr>  <lgl> 
##  1 EVER20101 EVER    2020      1 Spring            2 China       <NA>   NA    
##  2 EVER20102 EVER    2020      1 Spring            2 China       <NA>   NA    
##  3 EVER20103 EVER    2020      1 Spring            2 China       <NA>   NA    
##  4 AMAD20301 AMAD    2020      3 Autumn            1 Nepal       <NA>   NA    
##  5 AMAD20302 AMAD    2020      3 Autumn            1 Nepal       <NA>   NA    
##  6 AMAD20303 AMAD    2020      3 Autumn            1 Nepal       <NA>   NA    
##  7 AMAD20304 AMAD    2020      3 Autumn            1 Nepal       <NA>   NA    
##  8 AMAD20305 AMAD    2020      3 Autumn            1 Nepal       <NA>   NA    
##  9 AMAD20306 AMAD    2020      3 Autumn            1 Nepal       <NA>   NA    
## 10 AMAD20307 AMAD    2020      3 Autumn            1 Nepal       <NA>   NA    
## # ℹ 872 more rows
## # ℹ 61 more variables: ROUTE4 <lgl>, NATION <chr>, LEADERS <chr>,
## #   SPONSOR <chr>, SUCCESS1 <lgl>, SUCCESS2 <lgl>, SUCCESS3 <lgl>,
## #   SUCCESS4 <lgl>, ASCENT1 <chr>, ASCENT2 <chr>, ASCENT3 <lgl>, ASCENT4 <lgl>,
## #   CLAIMED <lgl>, DISPUTED <lgl>, COUNTRIES <chr>, APPROACH <chr>,
## #   BCDATE <date>, SMTDATE <date>, SMTTIME <chr>, SMTDAYS <dbl>, TOTDAYS <dbl>,
## #   TERMDATE <date>, TERMREASON <dbl>, TERMREASON_FACTOR <chr>, …

wide to long form

data_wide <- data_long %>%
    pivot_wider(names_from = "ROUTE_NUMBER", values_from = "ROUTE_NAME")
data_wide

## # A tibble: 882 × 69
##    EXPID     PEAKID  YEAR SEASON SEASON_FACTOR  HOST HOST_FACTOR ROUTE2 ROUTE3
##    <chr>     <chr>  <dbl>  <dbl> <chr>         <dbl> <chr>       <chr>  <lgl> 
##  1 EVER20101 EVER    2020      1 Spring            2 China       <NA>   NA    
##  2 EVER20102 EVER    2020      1 Spring            2 China       <NA>   NA    
##  3 EVER20103 EVER    2020      1 Spring            2 China       <NA>   NA    
##  4 AMAD20301 AMAD    2020      3 Autumn            1 Nepal       <NA>   NA    
##  5 AMAD20302 AMAD    2020      3 Autumn            1 Nepal       <NA>   NA    
##  6 AMAD20303 AMAD    2020      3 Autumn            1 Nepal       <NA>   NA    
##  7 AMAD20304 AMAD    2020      3 Autumn            1 Nepal       <NA>   NA    
##  8 AMAD20305 AMAD    2020      3 Autumn            1 Nepal       <NA>   NA    
##  9 AMAD20306 AMAD    2020      3 Autumn            1 Nepal       <NA>   NA    
## 10 AMAD20307 AMAD    2020      3 Autumn            1 Nepal       <NA>   NA    
## # ℹ 872 more rows
## # ℹ 60 more variables: ROUTE4 <lgl>, NATION <chr>, LEADERS <chr>,
## #   SPONSOR <chr>, SUCCESS1 <lgl>, SUCCESS2 <lgl>, SUCCESS3 <lgl>,
## #   SUCCESS4 <lgl>, ASCENT1 <chr>, ASCENT2 <chr>, ASCENT3 <lgl>, ASCENT4 <lgl>,
## #   CLAIMED <lgl>, DISPUTED <lgl>, COUNTRIES <chr>, APPROACH <chr>,
## #   BCDATE <date>, SMTDATE <date>, SMTTIME <chr>, SMTDAYS <dbl>, TOTDAYS <dbl>,
## #   TERMDATE <date>, TERMREASON <dbl>, TERMREASON_FACTOR <chr>, …

Separating and Uniting

Separate a column

data_sep <- data %>%
    separate(col = EXPID, into = c("EVER", "AMAD"))

## Warning: Expected 2 pieces. Missing pieces filled with `NA` in 882 rows [1, 2, 3, 4, 5,
## 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, ...].

data_sep

## # A tibble: 882 × 70
##    EVER  AMAD  PEAKID  YEAR SEASON SEASON_FACTOR  HOST HOST_FACTOR ROUTE1 ROUTE2
##    <chr> <chr> <chr>  <dbl>  <dbl> <chr>         <dbl> <chr>       <chr>  <chr> 
##  1 EVER… <NA>  EVER    2020      1 Spring            2 China       N Col… <NA>  
##  2 EVER… <NA>  EVER    2020      1 Spring            2 China       N Col… <NA>  
##  3 EVER… <NA>  EVER    2020      1 Spring            2 China       N Col… <NA>  
##  4 AMAD… <NA>  AMAD    2020      3 Autumn            1 Nepal       SW Ri… <NA>  
##  5 AMAD… <NA>  AMAD    2020      3 Autumn            1 Nepal       SW Ri… <NA>  
##  6 AMAD… <NA>  AMAD    2020      3 Autumn            1 Nepal       SW Ri… <NA>  
##  7 AMAD… <NA>  AMAD    2020      3 Autumn            1 Nepal       SW Ri… <NA>  
##  8 AMAD… <NA>  AMAD    2020      3 Autumn            1 Nepal       SW Ri… <NA>  
##  9 AMAD… <NA>  AMAD    2020      3 Autumn            1 Nepal       SW Ri… <NA>  
## 10 AMAD… <NA>  AMAD    2020      3 Autumn            1 Nepal       SW Ri… <NA>  
## # ℹ 872 more rows
## # ℹ 60 more variables: ROUTE3 <lgl>, ROUTE4 <lgl>, NATION <chr>, LEADERS <chr>,
## #   SPONSOR <chr>, SUCCESS1 <lgl>, SUCCESS2 <lgl>, SUCCESS3 <lgl>,
## #   SUCCESS4 <lgl>, ASCENT1 <chr>, ASCENT2 <chr>, ASCENT3 <lgl>, ASCENT4 <lgl>,
## #   CLAIMED <lgl>, DISPUTED <lgl>, COUNTRIES <chr>, APPROACH <chr>,
## #   BCDATE <date>, SMTDATE <date>, SMTTIME <chr>, SMTDAYS <dbl>, TOTDAYS <dbl>,
## #   TERMDATE <date>, TERMREASON <dbl>, TERMREASON_FACTOR <chr>, …

Unite two columns

data_unite <- data_sep %>%
    unite(col = "EXPID", EVER:AMAD, sep = "/")
data_unite

## # A tibble: 882 × 69
##    EXPID       PEAKID  YEAR SEASON SEASON_FACTOR  HOST HOST_FACTOR ROUTE1 ROUTE2
##    <chr>       <chr>  <dbl>  <dbl> <chr>         <dbl> <chr>       <chr>  <chr> 
##  1 EVER20101/… EVER    2020      1 Spring            2 China       N Col… <NA>  
##  2 EVER20102/… EVER    2020      1 Spring            2 China       N Col… <NA>  
##  3 EVER20103/… EVER    2020      1 Spring            2 China       N Col… <NA>  
##  4 AMAD20301/… AMAD    2020      3 Autumn            1 Nepal       SW Ri… <NA>  
##  5 AMAD20302/… AMAD    2020      3 Autumn            1 Nepal       SW Ri… <NA>  
##  6 AMAD20303/… AMAD    2020      3 Autumn            1 Nepal       SW Ri… <NA>  
##  7 AMAD20304/… AMAD    2020      3 Autumn            1 Nepal       SW Ri… <NA>  
##  8 AMAD20305/… AMAD    2020      3 Autumn            1 Nepal       SW Ri… <NA>  
##  9 AMAD20306/… AMAD    2020      3 Autumn            1 Nepal       SW Ri… <NA>  
## 10 AMAD20307/… AMAD    2020      3 Autumn            1 Nepal       SW Ri… <NA>  
## # ℹ 872 more rows
## # ℹ 60 more variables: ROUTE3 <lgl>, ROUTE4 <lgl>, NATION <chr>, LEADERS <chr>,
## #   SPONSOR <chr>, SUCCESS1 <lgl>, SUCCESS2 <lgl>, SUCCESS3 <lgl>,
## #   SUCCESS4 <lgl>, ASCENT1 <chr>, ASCENT2 <chr>, ASCENT3 <lgl>, ASCENT4 <lgl>,
## #   CLAIMED <lgl>, DISPUTED <lgl>, COUNTRIES <chr>, APPROACH <chr>,
## #   BCDATE <date>, SMTDATE <date>, SMTTIME <chr>, SMTDAYS <dbl>, TOTDAYS <dbl>,
## #   TERMDATE <date>, TERMREASON <dbl>, TERMREASON_FACTOR <chr>, …

Missing Values

data %>% 
  complete(YEAR, SEASON)

## # A tibble: 886 × 69
##     YEAR SEASON EXPID     PEAKID SEASON_FACTOR  HOST HOST_FACTOR ROUTE1   ROUTE2
##    <dbl>  <dbl> <chr>     <chr>  <chr>         <dbl> <chr>       <chr>    <chr> 
##  1  2020      1 EVER20101 EVER   Spring            2 China       N Col-N… <NA>  
##  2  2020      1 EVER20102 EVER   Spring            2 China       N Col-N… <NA>  
##  3  2020      1 EVER20103 EVER   Spring            2 China       N Col-N… <NA>  
##  4  2020      2 <NA>      <NA>   <NA>             NA <NA>        <NA>     <NA>  
##  5  2020      3 AMAD20301 AMAD   Autumn            1 Nepal       SW Ridge <NA>  
##  6  2020      3 AMAD20302 AMAD   Autumn            1 Nepal       SW Ridge <NA>  
##  7  2020      3 AMAD20303 AMAD   Autumn            1 Nepal       SW Ridge <NA>  
##  8  2020      3 AMAD20304 AMAD   Autumn            1 Nepal       SW Ridge <NA>  
##  9  2020      3 AMAD20305 AMAD   Autumn            1 Nepal       SW Ridge <NA>  
## 10  2020      3 AMAD20306 AMAD   Autumn            1 Nepal       SW Ridge <NA>  
## # ℹ 876 more rows
## # ℹ 60 more variables: ROUTE3 <lgl>, ROUTE4 <lgl>, NATION <chr>, LEADERS <chr>,
## #   SPONSOR <chr>, SUCCESS1 <lgl>, SUCCESS2 <lgl>, SUCCESS3 <lgl>,
## #   SUCCESS4 <lgl>, ASCENT1 <chr>, ASCENT2 <chr>, ASCENT3 <lgl>, ASCENT4 <lgl>,
## #   CLAIMED <lgl>, DISPUTED <lgl>, COUNTRIES <chr>, APPROACH <chr>,
## #   BCDATE <date>, SMTDATE <date>, SMTTIME <chr>, SMTDAYS <dbl>, TOTDAYS <dbl>,
## #   TERMDATE <date>, TERMREASON <dbl>, TERMREASON_FACTOR <chr>, …