Import data
# csv file
data <- read_csv("../00_data/myData.csv")
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>, …
Apply the following dplyr verbs to your data
Filter rows
filter(data, HOST_FACTOR == "China")
## # A tibble: 25 × 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 CHOY20301 CHOY 2020 3 Autumn 2 China NW side <NA>
## 5 EVER21151 EVER 2021 1 Spring 2 China N Col-N… <NA>
## 6 EVER22141 EVER 2022 1 Spring 2 China N Col-N… <NA>
## 7 EVER22142 EVER 2022 1 Spring 2 China N Col-N… <NA>
## 8 CHOY22301 CHOY 2022 3 Autumn 2 China SW Ridge <NA>
## 9 CHOY22302 CHOY 2022 3 Autumn 2 China SW Ridge <NA>
## 10 CHOY23101 CHOY 2023 1 Spring 2 China NW side <NA>
## # ℹ 15 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>, …
Arrange rows
arrange(data, desc(HOST))
## # 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 KIRA22201 KIRA 2022 2 Summer 3 India N Face <NA>
## 2 LNPS22301 LNPS 2022 3 Autumn 3 India S Face-… <NA>
## 3 EVER20101 EVER 2020 1 Spring 2 China N Col-N… <NA>
## 4 EVER20102 EVER 2020 1 Spring 2 China N Col-N… <NA>
## 5 EVER20103 EVER 2020 1 Spring 2 China N Col-N… <NA>
## 6 CHOY20301 CHOY 2020 3 Autumn 2 China NW side <NA>
## 7 EVER21151 EVER 2021 1 Spring 2 China N Col-N… <NA>
## 8 EVER22141 EVER 2022 1 Spring 2 China N Col-N… <NA>
## 9 EVER22142 EVER 2022 1 Spring 2 China N Col-N… <NA>
## 10 CHOY22301 CHOY 2022 3 Autumn 2 China 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>, …
Select columns
select(data, SEASON:HOST)
## # A tibble: 882 × 3
## SEASON SEASON_FACTOR HOST
## <dbl> <chr> <dbl>
## 1 1 Spring 2
## 2 1 Spring 2
## 3 1 Spring 2
## 4 3 Autumn 1
## 5 3 Autumn 1
## 6 3 Autumn 1
## 7 3 Autumn 1
## 8 3 Autumn 1
## 9 3 Autumn 1
## 10 3 Autumn 1
## # ℹ 872 more rows
Add columns
mutate(data,
TOTMEMBERS = SMTMEMBERS - MDEATHS)
## # 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>, …
Summarize by groups
data %>%
# Remove missing values
filter(!is.na(MDEATHS))
## # 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>, …