inst/doc/get-started.R

In mintyr: Streamlined Data Processing Tools for Genomic Selection

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

## -----------------------------------------------------------------------------
library(mintyr)

## ----example-split_cv---------------------------------------------------------
# Prepare example data: Convert first 3 columns of iris dataset to long format and split
dt_split <- w2l_split(data = iris, cols2l = 1:3)
# dt_split is now a list containing 3 data tables for Sepal.Length, Sepal.Width, and Petal.Length

# Example 1: Single cross-validation (no repeats)
split_cv(
  split_dt = dt_split,  # Input list of split data
  v = 3,                # Set 3-fold cross-validation
  repeats = 1           # Perform cross-validation once (no repeats)
)
# Returns a list where each element contains:
# - splits: rsample split objects
# - id: fold numbers (Fold1, Fold2, Fold3)
# - train: training set data
# - validate: validation set data

# Example 2: Repeated cross-validation
split_cv(
  split_dt = dt_split,  # Input list of split data
  v = 3,                # Set 3-fold cross-validation
  repeats = 2           # Perform cross-validation twice
)
# Returns a list where each element contains:
# - splits: rsample split objects
# - id: repeat numbers (Repeat1, Repeat2)
# - id2: fold numbers (Fold1, Fold2, Fold3)
# - train: training set data
# - validate: validation set data

## ----example-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
  cols2bind = 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
  cols2bind = 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

## ----example-r2p_nest---------------------------------------------------------
# Example 1: Row-to-pairs nesting with column names
r2p_nest(
  mtcars,                     # Input mtcars dataset
  rows2bind = "cyl",          # Column to be used as row values
  by = c("hp", "drat", "wt")  # Columns to be transformed into pairs
)
# Returns a nested data.table where:
# - name: variable names (hp, drat, wt)
# - data: list column containing data.tables with rows grouped by cyl values

# Example 2: Row-to-pairs nesting with numeric indices
r2p_nest(
  mtcars,                     # Input mtcars dataset
  rows2bind = 2,              # Use 2nd column (cyl) as row values
  by = 4:6                    # Use columns 4-6 (hp, drat, wt) for pairs
)
# Returns a nested data.table where:
# - name: variable names from columns 4-6
# - data: list column containing data.tables with rows grouped by cyl values

## ----example-export_nest------------------------------------------------------
# Example 1: Basic nested data export workflow
# Step 1: Create nested data structure
dt_nest <- w2l_nest(
  data = iris,              # Input iris dataset
  cols2l = 1:2,             # Columns to be nested
  by = "Species"            # Grouping variable
)

# Step 2: Export nested data to files
export_nest(
  nest_dt = dt_nest,        # Input nested data.table
  nest_col = "data",        # Column containing nested data
  group_cols = c("name", "Species")  # Columns to create directory structure
)
# Returns the number of files created
# Creates directory structure: tempdir()/name/Species/data.txt

# Check exported files
list.files(
  path = tempdir(),         # Default export directory
  pattern = "txt",          # File type pattern to search
  recursive = TRUE          # Search in subdirectories
)
# Returns list of created files and their paths

# Clean up exported files
files <- list.files(
  path = tempdir(),         # Default export directory
  pattern = "txt",          # File type pattern to search
  recursive = TRUE,         # Search in subdirectories
  full.names = TRUE         # Return full file paths
)
file.remove(files)          # Remove all exported files

## ----example-export_list------------------------------------------------------
# Example: Export split data to files

# Step 1: Create split data structure
dt_split <- w2l_split(
  data = iris,              # Input iris dataset
  cols2l = 1:2,             # Columns to be split
  by = "Species"            # Grouping variable
)

# Step 2: Export split data to files
export_list(
  split_dt = dt_split       # Input list of data.tables
)
# Returns the number of files created
# Files are saved in tempdir() with .txt extension

# Check exported files
list.files(
  path = tempdir(),         # Default export directory
  pattern = "txt",          # File type pattern to search
  recursive = TRUE          # Search in subdirectories
)

# Clean up exported files
files <- list.files(
  path = tempdir(),         # Default export directory
  pattern = "txt",          # File type pattern to search
  recursive = TRUE,         # Search in subdirectories
  full.names = TRUE         # Return full file paths
)
file.remove(files)          # Remove all exported files

## ----example-fires------------------------------------------------------------
head(fires())

## ----example-nedaps-----------------------------------------------------------
head(nedaps())

## ----example-convert_nest-----------------------------------------------------
# Example 1: Create nested data structures
# Create single nested column
df_nest1 <- iris |> 
  dplyr::group_nest(Species)     # Group and nest by Species

# Create multiple nested columns
df_nest2 <- iris |>
  dplyr::group_nest(Species) |>  # Group and nest by Species
  dplyr::mutate(
    data2 = purrr::map(          # Create second nested column
      data,
      dplyr::mutate, 
      c = 2
    )
  )

# Example 2: Convert nested structures
# Convert data frame to data table
convert_nest(
  df_nest1,                      # Input nested data frame
  to = "dt"                      # Convert to data.table
)

# Convert specific nested columns
convert_nest(
  df_nest2,                      # Input nested data frame
  to = "dt",                     # Convert to data.table
  nest_cols = "data"             # Only convert 'data' column
)

# Example 3: Convert data table to data frame
dt_nest <- mintyr::w2l_nest(
  data = iris,                   # Input dataset
  cols2l = 1:2                   # Columns to nest
)
convert_nest(
  dt_nest,                       # Input nested data table
  to = "df"                      # Convert to data frame
)

## ----example-get_path_segment-------------------------------------------------
# Example: Path segment extraction demonstrations

# Setup test paths
paths <- c(
  "C:/home/user/documents",   # Windows style path
  "/var/log/system",          # Unix system path
  "/usr/local/bin"            # Unix binary path
)

# Example 1: Extract first segment
get_path_segment(
  paths,                      # Input paths
  1                           # Get first segment
)
# Returns: c("home", "var", "usr")

# Example 2: Extract second-to-last segment
get_path_segment(
  paths,                      # Input paths
  -2                          # Get second-to-last segment
)
# Returns: c("user", "log", "local")

# Example 3: Extract from first to last segment
get_path_segment(
  paths,                      # Input paths
  c(1,-1)                     # Range from first to last
)
# Returns full paths without drive letters

# Example 4: Extract first three segments
get_path_segment(
  paths,                      # Input paths
  c(1,3)                      # Range from first to third
)
# Returns: c("home/user/documents", "var/log/system", "usr/local/bin")

# Example 5: Extract last two segments (reverse order)
get_path_segment(
  paths,                      # Input paths
  c(-1,-2)                    # Range from last to second-to-last
)
# Returns: c("documents/user", "system/log", "bin/local")

# Example 6: Extract first two segments
get_path_segment(
  paths,                      # Input paths
  c(1,2)                      # Range from first to second
)
# Returns: c("home/user", "var/log", "usr/local")

## ----example-format_digits----------------------------------------------------
# Example: Number formatting demonstrations

# Setup test data
dt <- data.table::data.table(
  a = c(0.1234, 0.5678),      # Numeric column 1
  b = c(0.2345, 0.6789),      # Numeric column 2
  c = c("text1", "text2")     # Text column
)

# Example 1: Format all numeric columns
format_digits(
  dt,                         # Input data table
  digits = 2                  # Round to 2 decimal places
)

# Example 2: Format specific column as percentage
format_digits(
  dt,                         # Input data table
  cols = c("a"),              # Only format column 'a'
  digits = 2,                 # Round to 2 decimal places
  percentage = TRUE           # Convert to percentage
)

## ----example-mintyr_example---------------------------------------------------
# Get path to an example file
mintyr_example("csv_test1.csv")

## ----example-mintyr_examples--------------------------------------------------
# List all example files
mintyr_examples()

## ----example-import_xlsx------------------------------------------------------
# Example: Excel file import demonstrations

# Setup test files
xlsx_files <- mintyr_example(
  mintyr_examples("xlsx_test")    # Get example Excel files
)

# Example 1: Import and combine all sheets from all files
import_xlsx(
  xlsx_files,                     # Input Excel file paths
  rbind = TRUE                    # Combine all sheets into one data.table
)

# Example 2: Import specific sheets separately
import_xlsx(
  xlsx_files,                     # Input Excel file paths
  rbind = FALSE,                  # Keep sheets as separate data.tables
  sheet = 2                       # Only import first sheet
)

## ----examples-import_csv------------------------------------------------------
# Example: CSV file import demonstrations

# Setup test files
csv_files <- mintyr_example(
  mintyr_examples("csv_test")     # Get example CSV files
)

# Example 1: Import and combine CSV files using data.table
import_csv(
  csv_files,                      # Input CSV file paths
  package = "data.table",         # Use data.table for reading
  rbind = TRUE,                   # Combine all files into one data.table
  rbind_label = "_file"           # Column name for file source
)

# Example 2: Import files separately using arrow
import_csv(
  csv_files,                      # Input CSV file paths
  package = "arrow",              # Use arrow for reading
  rbind = FALSE                   # Keep files as separate data.tables
)

## ----example-get_filename-----------------------------------------------------
# Example: File path processing demonstrations

# Setup test files
xlsx_files <- mintyr_example(
  mintyr_examples("xlsx_test")    # Get example Excel files
)

# Example 1: Extract filenames without extensions
get_filename(
  xlsx_files,                     # Input file paths
  rm_extension = TRUE,            # Remove file extensions
  rm_path = TRUE                  # Remove directory paths
)

# Example 2: Keep file extensions
get_filename(
  xlsx_files,                     # Input file paths
  rm_extension = FALSE,           # Keep file extensions
  rm_path = TRUE                  # Remove directory paths
)

# Example 3: Keep full paths without extensions
get_filename(
  xlsx_files,                     # Input file paths
  rm_extension = TRUE,            # Remove file extensions
  rm_path = FALSE                 # Keep directory paths
)

## ----example-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
  cols2l = 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
  cols2l = 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

## ----example-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
  cols2l = 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
  cols2l = 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

## ----example-nest_cv----------------------------------------------------------
# Example: Cross-validation for nested data.table demonstrations

# Setup test data
dt_nest <- w2l_nest(
  data = iris,                   # Input dataset
  cols2l = 1:2                   # Nest first 2 columns
)

# Example 1: Basic 2-fold cross-validation
nest_cv(
  nest_dt = dt_nest,             # Input nested data.table
  v = 2                          # Number of folds (2-fold CV)
)

# Example 2: Repeated 2-fold cross-validation
nest_cv(
  nest_dt = dt_nest,             # Input nested data.table
  v = 2,                         # Number of folds (2-fold CV)
  repeats = 2                    # Number of repetitions
)

## ----example-top_perc---------------------------------------------------------
# Example 1: Basic usage with single trait
# This example selects the top 10% of observations based on Petal.Width
# keep_data=TRUE returns both summary statistics and the filtered data
top_perc(iris, 
         perc = 0.1,                # Select top 10%
         trait = c("Petal.Width"),  # Column to analyze
         keep_data = TRUE)          # Return both stats and filtered data

# Example 2: Using grouping with 'by' parameter
# This example performs the same analysis but separately for each Species
# Returns nested list with stats and filtered data for each group
top_perc(iris, 
         perc = 0.1,                # Select top 10%
         trait = c("Petal.Width"),  # Column to analyze
         by = "Species")            # Group by Species

# Example 3: Complex example with multiple percentages and grouping variables
# Reshape data from wide to long format for Sepal.Length and Sepal.Width
iris |> 
  tidyr::pivot_longer(1:2,
                      names_to = "names", 
                      values_to = "values") |> 
  mintyr::top_perc(
    perc = c(0.1, -0.2),
    trait = "values",
    by = c("Species", "names"),
    type = "mean_sd")