Reshape and nest
In mintyr: Grouped and Nested Data Pipelines Built on 'data.table'

knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>"
)

library(mintyr)

These functions turn a wide table (one column per trait) into pieces that can be analysed one at a time: by trait and group (w2l_nest(), w2l_split()), by pairs of traits (c2p_nest()), or with the levels of one column side by side (r2p_nest()).

Wide to long, nested: `w2l_nest()`

# Example: Wide to long format nesting demonstrations

# Example 1: Basic nesting by group
w2l_nest(
  data = iris,                    # Input dataset
  by = "Species"                  # Group by Species column
)

# Example 2: Nest specific columns with numeric indices
w2l_nest(
  data = iris,                    # Input dataset
  cols = 1:4,                   # Select first 4 columns to nest
  by = "Species"                  # Group by Species column
)

# Example 3: Nest specific columns with column names
w2l_nest(
  data = iris,                    # Input dataset
  cols = c("Sepal.Length",        # Select columns by name
           "Sepal.Width",
           "Petal.Length"),
  by = 5                          # Group by column index 5 (Species)
)
# Returns similar structure to Example 2

Wide to long, split into a list: `w2l_split()`

# Example: Wide to long format splitting demonstrations

# Example 1: Basic splitting by Species
w2l_split(
  data = iris,                    # Input dataset
  by = "Species"                  # Split by Species column
) |> 
  lapply(head)                    # Show first 6 rows of each split

# Example 2: Split specific columns using numeric indices
w2l_split(
  data = iris,                    # Input dataset
  cols = 1:3,                   # Select first 3 columns to split
  by = 5                          # Split by column index 5 (Species)
) |> 
  lapply(head)                    # Show first 6 rows of each split

# Example 3: Split specific columns using column names
list_res <- w2l_split(
  data = iris,                    # Input dataset
  cols = c("Sepal.Length",        # Select columns by name
           "Sepal.Width"),
  by = "Species"                  # Split by Species column
)
lapply(list_res, head)            # Show first 6 rows of each split
# Returns similar structure to Example 2

All pairs of columns: `c2p_nest()`

# Example data preparation: Define column names for combination
col_names <- c("Sepal.Length", "Sepal.Width", "Petal.Length")

# Example 1: Basic column-to-pairs nesting with custom separator
c2p_nest(
  iris,                   # Input iris dataset
  cols = col_names,       # Columns to be combined as pairs
  pairs_n = 2,            # Create pairs of 2 columns
  sep = "&"               # Custom separator for pair names
)
# Returns a nested data.table where:
# - pairs: combined column names (e.g., "Sepal.Length&Sepal.Width")
# - data: list column containing data.tables with value1, value2 columns

# Example 2: Column-to-pairs nesting with numeric indices and grouping
c2p_nest(
  iris,                   # Input iris dataset
  cols = 1:3,             # First 3 columns to be combined
  pairs_n = 2,            # Create pairs of 2 columns
  by = 5                  # Group by 5th column (Species)
)
# Returns a nested data.table where:
# - pairs: combined column names
# - Species: grouping variable
# - data: list column containing data.tables grouped by Species

Levels of a column side by side: `r2p_nest()`

# Example: the same traits recorded on the same animals in two farms
set.seed(1)
growth <- data.frame(
  animal = rep(sprintf("A%02d", 1:6), each = 2),
  farm   = rep(c("farm1", "farm2"), times = 6),
  adg    = round(rnorm(12, 900, 50)),     # average daily gain
  bf     = round(rnorm(12, 11, 1.5), 1)   # backfat
)

# Example 1: column names
r2p_nest(
  growth,
  names_from = "farm",           # levels become columns: farm1, farm2
  cols      = c("adg", "bf"),    # traits to pivot
  id        = "animal"           # aligns records of the same animal
)
# Returns a nested data.table where:
# - name: trait names (adg, bf)
# - data: one row per animal with columns animal, farm1, farm2

# Example 2: numeric indices
r2p_nest(growth, names_from = 2, cols = 3:4, id = 1)