Module 12: Apply it to your data 11

Chapter 19 Functions

Import your data

data <- read_excel("CliffordSalmonidDataApply11.xlsx")
data

## # A tibble: 2,808 × 9
##    species date                geo_group region losses   dead discarded escaped
##    <chr>   <dttm>              <chr>     <chr>   <dbl>  <dbl>     <dbl>   <dbl>
##  1 salmon  2020-01-01 00:00:00 area      1       31425  28126      3299       0
##  2 salmon  2020-01-01 00:00:00 area      2      324116 277888     46113       0
##  3 salmon  2020-01-01 00:00:00 area      3      844829 776983     63770       0
##  4 salmon  2020-01-01 00:00:00 area      4      676852 623159     51823       0
##  5 salmon  2020-01-01 00:00:00 area      5      109269  97627     11424       0
##  6 salmon  2020-01-01 00:00:00 area      6      548921 531193     15710       0
##  7 salmon  2020-01-01 00:00:00 area      7      231487 228847      2640       0
##  8 salmon  2020-01-01 00:00:00 area      8      442659 431218     11228       0
##  9 salmon  2020-01-01 00:00:00 area      9      311127 308298      2212       0
## 10 salmon  2020-01-01 00:00:00 area      10     288849 281808      3120       0
## # ℹ 2,798 more rows
## # ℹ 1 more variable: other <dbl>

Create Data frame functions

Example 1: count columns

code snippets

ncol(data)

## [1] 9

colnames(data)

## [1] "species"   "date"      "geo_group" "region"    "losses"    "dead"     
## [7] "discarded" "escaped"   "other"

Turn them into a function

count_cols <- function(df) {
  num_cols <- ncol(df)
  return(num_cols)
}

data %>% count_cols()

## [1] 9

Adding arguments for details of operation

count_cols_checked <- function(df, expected_cols = 9, ...) {

actual_cols <- ncol(df, ...)
  
  if (actual_cols == expected_cols) {
    message("Column count matches expectations")
    print(actual_cols)
  } else if (actual_cols > expected_cols) {
    warning("Dataset has more columns than expected")
    print(actual_cols)
  } else {
    stop("Dataset has fewer columns than required. Function stopped")
  }
}

data %>% count_cols_checked(expected_cols = 9)

## Column count matches expectations

## [1] 9

Example 2: count rows

code snippets

nrow(data)

## [1] 2808

nrow(data %>% filter(species == "salmon"))

## [1] 1656

Turn them into a function

count_species_rows <- function(df, target_species = "salmon") {
  
  subset_df <- df %>% filter(species == target_species)
  total_rows <- nrow(subset_df)
  
  return(total_rows)
}

data %>% count_species_rows(target_species = "salmon")

## [1] 1656

Example 3: count rows

code snippets

nrow(data %>% filter(losses > 100000))

## [1] 1620

Turn them into a function

count_high_loss_rows <- function(df, threshold = 100000) {
  
  high_loss_df <- df %>% filter(losses > threshold)
  row_count <- nrow(high_loss_df)
  
  if (row_count > 500) {
    message("High volume of high losses")
    print(row_count)
  } else if (row_count > 0) {
    warning("High losses but not detrimental")
    print(row_count)
  } else {
    stop("Error in high losses value")
  }
  
  return(high_loss_df)
}

data %>% count_high_loss_rows(threshold = 100000)

## High volume of high losses

## [1] 1620

## # A tibble: 1,620 × 9
##    species date                geo_group region losses   dead discarded escaped
##    <chr>   <dttm>              <chr>     <chr>   <dbl>  <dbl>     <dbl>   <dbl>
##  1 salmon  2020-01-01 00:00:00 area      2      324116 277888     46113       0
##  2 salmon  2020-01-01 00:00:00 area      3      844829 776983     63770       0
##  3 salmon  2020-01-01 00:00:00 area      4      676852 623159     51823       0
##  4 salmon  2020-01-01 00:00:00 area      5      109269  97627     11424       0
##  5 salmon  2020-01-01 00:00:00 area      6      548921 531193     15710       0
##  6 salmon  2020-01-01 00:00:00 area      7      231487 228847      2640       0
##  7 salmon  2020-01-01 00:00:00 area      8      442659 431218     11228       0
##  8 salmon  2020-01-01 00:00:00 area      9      311127 308298      2212       0
##  9 salmon  2020-01-01 00:00:00 area      10     288849 281808      3120       0
## 10 salmon  2020-01-01 00:00:00 area      11     565676 516146      4761       0
## # ℹ 1,610 more rows
## # ℹ 1 more variable: other <dbl>