| Title: | Advanced Factor Manipulation Utilities |
|---|---|
| Description: | Provides a collection of utility functions for manipulating and analyzing factor vectors in R. It offers tools for filtering, splitting, combining, and reordering factor levels based on various criteria. The package is designed to simplify common tasks in categorical data analysis, making it easier to work with factors in a flexible and efficient manner. |
| Authors: | Kai Guo [aut, cre] |
| Maintainer: | Kai Guo <[email protected]> |
| License: | GPL-3 |
| Version: | 0.0.8 |
| Built: | 2025-01-07 05:15:18 UTC |
| Source: | https://github.com/guokai8/fctutils |
Transforms factor levels by applying a function to each level.
ft_apply(factor_vec, apply_func)ft_apply(factor_vec, apply_func)
factor_vec |
A factor vector to transform. |
apply_func |
A function to apply to each level. |
A factor vector with transformed levels.
Kai Guo
# Example factor vector factor_vec <- factor(c('apple', 'banana', 'cherry')) # Append '_fruit' to each level ft_apply(factor_vec, function(x) paste0(x, '_fruit'))# Example factor vector factor_vec <- factor(c('apple', 'banana', 'cherry')) # Append '_fruit' to each level ft_apply(factor_vec, function(x) paste0(x, '_fruit'))
Reorders the levels of a factor vector based on the frequency of characters at specified positions within the data.
ft_char_freq( factor_vec, positions, case = FALSE, decreasing = TRUE, inplace = TRUE )ft_char_freq( factor_vec, positions, case = FALSE, decreasing = TRUE, inplace = TRUE )
factor_vec |
A factor vector whose levels are to be reordered. |
positions |
A vector of positive integers specifying the character positions to consider. |
case |
Logical. Should the character comparison be case-sensitive? Default is |
decreasing |
Logical. Should the ordering be decreasing by frequency? Default is |
inplace |
Logical. If |
A factor vector with levels reordered based on the frequency of characters at specified positions.
Kai Guo
# Example factor vector factor_vec <- factor(c('apple', 'banana', 'apricot', 'cherry', 'banana', 'banana', 'date')) # Reorder based on characters at positions 1 and 2 ft_char_freq(factor_vec, positions = 1:2) # Reorder, case-sensitive, decreasing order ft_char_freq(factor_vec, positions = c(1, 3), case = TRUE)# Example factor vector factor_vec <- factor(c('apple', 'banana', 'apricot', 'cherry', 'banana', 'banana', 'date')) # Reorder based on characters at positions 1 and 2 ft_char_freq(factor_vec, positions = 1:2) # Reorder, case-sensitive, decreasing order ft_char_freq(factor_vec, positions = c(1, 3), case = TRUE)
Collapses specified levels of a factor into new levels based on a grouping list.
ft_collapse_lev(factor_vec, groups)ft_collapse_lev(factor_vec, groups)
factor_vec |
A factor vector to modify. |
groups |
A named list where each element contains levels to be collapsed into a new level named after the list element's name. |
A factor vector with collapsed levels.
Kai Guo
# Example factor vector factor_vec <- factor(c('apple', 'banana', 'cherry', 'date', 'elderberry')) # Define groups groups <- list( 'Group1' = c('apple', 'banana'), 'Group2' = c('cherry', 'date') ) # Collapse levels ft_collapse_lev(factor_vec, groups)# Example factor vector factor_vec <- factor(c('apple', 'banana', 'cherry', 'date', 'elderberry')) # Define groups groups <- list( 'Group1' = c('apple', 'banana'), 'Group2' = c('cherry', 'date') ) # Collapse levels ft_collapse_lev(factor_vec, groups)
Combines two vectors, which may be of unequal lengths, into a factor vector and sorts based on the levels of either the first or second vector.
ft_combine(vector1, vector2, sort_by = 1, decreasing = FALSE)ft_combine(vector1, vector2, sort_by = 1, decreasing = FALSE)
vector1 |
The first vector to combine. |
vector2 |
The second vector to combine. |
sort_by |
An integer (1 or 2) indicating which vector's levels to use for sorting. Default is |
decreasing |
Logical. Should the sorting be in decreasing order? Default is |
A factor vector combining both vectors and sorted based on specified levels.
# Example vectors of unequal lengths vector1 <- c('apple', 'banana', 'cherry') vector2 <- c('date', 'fig', 'grape', 'honeydew') # Combine and sort based on vector1 levels combined_factor1 <- ft_combine(vector1, vector2, sort_by = 1) print(combined_factor1) # Combine and sort based on vector2 levels combined_factor2 <- ft_combine(vector1, vector2, sort_by = 2) print(combined_factor2) # Combine with decreasing order based on vector1 combined_factor3 <- ft_combine(vector1, vector2, sort_by = 1, decreasing = TRUE) print(combined_factor3)# Example vectors of unequal lengths vector1 <- c('apple', 'banana', 'cherry') vector2 <- c('date', 'fig', 'grape', 'honeydew') # Combine and sort based on vector1 levels combined_factor1 <- ft_combine(vector1, vector2, sort_by = 1) print(combined_factor1) # Combine and sort based on vector2 levels combined_factor2 <- ft_combine(vector1, vector2, sort_by = 2) print(combined_factor2) # Combine with decreasing order based on vector1 combined_factor3 <- ft_combine(vector1, vector2, sort_by = 1, decreasing = TRUE) print(combined_factor3)
Combines multiple factor vectors into a single factor, unifying the levels.
ft_concat(...)ft_concat(...)
... |
Factor vectors to concatenate. |
A single factor vector containing all elements and unified levels.
Kai Guo
# Example factor vectors factor_vec1 <- factor(c('apple', 'banana')) factor_vec2 <- factor(c('cherry', 'date')) # Concatenate factors concatenated_factor <- ft_concat(factor_vec1, factor_vec2) levels(concatenated_factor)# Example factor vectors factor_vec1 <- factor(c('apple', 'banana')) factor_vec2 <- factor(c('cherry', 'date')) # Concatenate factors concatenated_factor <- ft_concat(factor_vec1, factor_vec2) levels(concatenated_factor)
Reorders the levels of a factor vector based on the count of each level in the data.
ft_count(factor_vec, decreasing = TRUE, inplace = FALSE)ft_count(factor_vec, decreasing = TRUE, inplace = FALSE)
factor_vec |
A factor vector whose levels are to be reordered. |
decreasing |
Logical. Should the ordering be decreasing by count? Default is |
inplace |
Logical. If |
A factor vector with levels reordered based on their count.
Kai Guo
# Example factor vector factor_vec <- factor(c('apple', 'banana', 'apple', 'cherry', 'banana', 'banana', 'date')) # Reorder levels by decreasing count ft_count(factor_vec) # Reorder levels by increasing count ft_count(factor_vec, decreasing = FALSE)# Example factor vector factor_vec <- factor(c('apple', 'banana', 'apple', 'cherry', 'banana', 'banana', 'date')) # Reorder levels by decreasing count ft_count(factor_vec) # Reorder levels by increasing count ft_count(factor_vec, decreasing = FALSE)
Converts numeric codes back into factor levels using a provided mapping.
ft_decode(codes, mapping)ft_decode(codes, mapping)
codes |
A numeric vector of codes to decode. |
mapping |
A named vector where names are levels and values are codes. |
A factor vector with decoded levels.
Kai Guo
# Numeric codes codes <- c(1, 2, 3, 2) # Mapping from levels to codes mapping <- c('low' = 1, 'medium' = 2, 'high' = 3) # Decode codes into factor levels ft_decode(codes, mapping = mapping)# Numeric codes codes <- c(1, 2, 3, 2) # Mapping from levels to codes mapping <- c('low' = 1, 'medium' = 2, 'high' = 3) # Decode codes into factor levels ft_decode(codes, mapping = mapping)
Generates a data frame of dummy variables (one-hot encoded) from a factor vector.
ft_dummy(factor_vec)ft_dummy(factor_vec)
factor_vec |
A factor vector. |
A data frame where each column represents a level of the factor, containing 1s and 0s.
Kai Guo
# Example factor vector factor_vec <- factor(c('apple', 'banana', 'apple', 'cherry')) # Create dummy variables ft_dummy(factor_vec)# Example factor vector factor_vec <- factor(c('apple', 'banana', 'apple', 'cherry')) # Create dummy variables ft_dummy(factor_vec)
Identifies duplicate levels in a factor vector and returns a logical vector indicating which elements are duplicates.
ft_duplicates(factor_vec)ft_duplicates(factor_vec)
factor_vec |
A factor vector. |
A logical vector where TRUE indicates a duplicate level.
Kai Guo
# Example factor vector factor_vec <- factor(c('apple', 'banana', 'apple', 'cherry', 'banana')) # Flag duplicates ft_duplicates(factor_vec)# Example factor vector factor_vec <- factor(c('apple', 'banana', 'apple', 'cherry', 'banana')) # Flag duplicates ft_duplicates(factor_vec)
Converts the levels of a factor vector into numeric codes, optionally using a provided mapping.
ft_encode(factor_vec, mapping = NULL)ft_encode(factor_vec, mapping = NULL)
factor_vec |
A factor vector to encode. |
mapping |
An optional named vector providing the numeric code for each level. |
A numeric vector with encoded values.
Kai Guo
# Example factor vector factor_vec <- factor(c('low', 'medium', 'high', 'medium')) # Encode without mapping ft_encode(factor_vec) # Encode with custom mapping custom_mapping <- c('low' = 1, 'medium' = 2, 'high' = 3) ft_encode(factor_vec, mapping = custom_mapping)# Example factor vector factor_vec <- factor(c('low', 'medium', 'high', 'medium')) # Encode without mapping ft_encode(factor_vec) # Encode with custom mapping custom_mapping <- c('low' = 1, 'medium' = 2, 'high' = 3) ft_encode(factor_vec, mapping = custom_mapping)
Extracts substrings from the levels of a factor vector based on a regular expression pattern and creates a new factor.
ft_extract(factor_vec, pattern, capture_group = 0)ft_extract(factor_vec, pattern, capture_group = 0)
factor_vec |
A factor vector from which substrings will be extracted. |
pattern |
A regular expression pattern to match. |
capture_group |
An integer specifying which capture group to extract if using capturing groups in the pattern. Default is |
A new factor vector containing the extracted substrings.
Kai Guo
# Example factor vector factor_vec <- factor(c('item123', 'item456', 'item789')) # Extract numeric part ft_extract(factor_vec, pattern = '\\d+') # Extract with capturing group factor_vec <- factor(c('apple: red', 'banana: yellow', 'cherry: red')) ft_extract(factor_vec, pattern = '^(\\w+):', capture_group = 1)# Example factor vector factor_vec <- factor(c('item123', 'item456', 'item789')) # Extract numeric part ft_extract(factor_vec, pattern = '\\d+') # Extract with capturing group factor_vec <- factor(c('apple: red', 'banana: yellow', 'cherry: red')) ft_extract(factor_vec, pattern = '^(\\w+):', capture_group = 1)
Converts one or more character vectors into factors, ensuring that they share the same levels.
ft_factorize(..., levels = NULL)ft_factorize(..., levels = NULL)
... |
Character vectors to factorize. |
levels |
An optional character vector specifying the levels. If |
A list of factor vectors with consistent levels.
Kai Guo
# Example character vectors vec1 <- c('apple', 'banana', 'cherry') vec2 <- c('banana', 'date', 'apple') # Factorize with consistent levels factors <- ft_factorize(vec1, vec2) levels(factors[[1]]) levels(factors[[2]])# Example character vectors vec1 <- c('apple', 'banana', 'cherry') vec2 <- c('banana', 'date', 'apple') # Factorize with consistent levels factors <- ft_factorize(vec1, vec2) levels(factors[[1]]) levels(factors[[2]])
Filters out factor levels that occur less than a specified frequency threshold and recalculates character frequencies excluding the removed levels. Offers options to handle NA values and returns additional information.
ft_filter_freq( factor_vec, min_freq = 1, na.rm = FALSE, case = FALSE, decreasing = TRUE, return_info = FALSE )ft_filter_freq( factor_vec, min_freq = 1, na.rm = FALSE, case = FALSE, decreasing = TRUE, return_info = FALSE )
factor_vec |
A factor vector to be filtered. |
min_freq |
A positive integer specifying the minimum frequency threshold. Factor levels occurring less than this number will be dropped. |
na.rm |
Logical. Should NA values be removed before filtering and frequency calculation? Default is |
case |
Logical. Should the character frequency count be case-sensitive? Default is |
decreasing |
Logical. Should the ordering of levels be decreasing by total character frequency? Default is |
return_info |
Logical. Should the function return additional information such as removed levels and character frequencies? Default is |
If return_info is FALSE, returns a factor vector with levels filtered by the specified frequency threshold and reordered based on recalculated total character frequency. If return_info is TRUE, returns a list containing the filtered factor vector, removed levels, and character frequency table.
Kai Guo
# Example factor vector factor_vec <- factor(c('apple', 'banana', 'cherry', 'date', 'banana', 'apple', 'fig', NA)) # Filter levels occurring less than 2 times and reorder by character frequency ft_filter_freq(factor_vec, min_freq = 2) # Filter levels, remove NA values, and return additional information result <- ft_filter_freq(factor_vec, min_freq = 2, na.rm = TRUE, return_info = TRUE) result$filtered_factor result$removed_levels result$char_freq_table# Example factor vector factor_vec <- factor(c('apple', 'banana', 'cherry', 'date', 'banana', 'apple', 'fig', NA)) # Filter levels occurring less than 2 times and reorder by character frequency ft_filter_freq(factor_vec, min_freq = 2) # Filter levels, remove NA values, and return additional information result <- ft_filter_freq(factor_vec, min_freq = 2, na.rm = TRUE, return_info = TRUE) result$filtered_factor result$removed_levels result$char_freq_table
Removes levels from a factor vector based on a user-defined function.
ft_filter_func(factor_vec, func)ft_filter_func(factor_vec, func)
factor_vec |
A factor vector to filter. |
func |
A function that takes a character vector of levels and returns a logical vector. |
A factor vector with levels filtered according to the function.
Kai Guo
# Example factor vector factor_vec <- factor(c('apple', 'banana', 'cherry', 'date')) # Remove levels that start with 'b' ft_filter_func(factor_vec, function(x) !grepl('^b', x))# Example factor vector factor_vec <- factor(c('apple', 'banana', 'cherry', 'date')) # Remove levels that start with 'b' ft_filter_func(factor_vec, function(x) !grepl('^b', x))
Removes factor levels where a specified character appears at specified positions within the levels.
ft_filter_pos( factor_vec, positions = NULL, char, case = FALSE, remove_na = TRUE, invert = FALSE, .return = FALSE )ft_filter_pos( factor_vec, positions = NULL, char, case = FALSE, remove_na = TRUE, invert = FALSE, .return = FALSE )
factor_vec |
A factor vector from which levels will be removed. |
positions |
A vector of positive integers indicating the character positions to check. |
char |
A single character string specifying the character to look for. |
case |
Logical. Should the character matching be case-sensitive? Default is |
remove_na |
remove NA from the output? Default is |
invert |
logical. If TRUE return indices or values for elements that do not match. |
.return |
logical. If TRUE return TRUE or FALSE instead of element. |
A factor vector with levels removed where the specified character appears at the specified positions.
Kai Guo
# Example factor vector factor_vec <- factor(c('apple', 'banana', 'apricot', 'cherry', 'date', 'fig', 'grape')) # Remove levels where 'a' appears at position 1 ft_filter_pos(factor_vec, positions = 1, char = 'a') # Remove levels where 'e' appears at positions 2 or 3 ft_filter_pos(factor_vec, positions = c(2, 3), char = 'e') # Case-sensitive removal factor_vec_case <- factor(c('Apple', 'banana', 'Apricot', 'Cherry', 'Date', 'Fig', 'grape')) ft_filter_pos(factor_vec_case, positions = 1, char = 'A', case = TRUE)# Example factor vector factor_vec <- factor(c('apple', 'banana', 'apricot', 'cherry', 'date', 'fig', 'grape')) # Remove levels where 'a' appears at position 1 ft_filter_pos(factor_vec, positions = 1, char = 'a') # Remove levels where 'e' appears at positions 2 or 3 ft_filter_pos(factor_vec, positions = c(2, 3), char = 'e') # Case-sensitive removal factor_vec_case <- factor(c('Apple', 'banana', 'Apricot', 'Cherry', 'Date', 'Fig', 'grape')) ft_filter_pos(factor_vec_case, positions = 1, char = 'A', case = TRUE)
Reorders the levels of a factor vector based on the frequency of characters in each level's name. Supports case sensitivity, descending order, and optionally reorders the data vector's elements to align with the new levels' order.
ft_freq(factor_vec, case = FALSE, decreasing = TRUE, inplace = FALSE)ft_freq(factor_vec, case = FALSE, decreasing = TRUE, inplace = FALSE)
factor_vec |
A factor vector whose levels will be reordered. |
case |
Logical. If |
decreasing |
Logical. If |
inplace |
Logical. If |
A new factor vector with reordered levels. Depending on the inplace parameter, the data vector's elements may also be reordered.
Kai Guo
# Example 1: Reorder levels based on character frequency without reordering data elements factor_vec <- factor(c('apple', 'banana', 'cherry', 'date', 'fig', 'grape')) new <- ft_freq( factor_vec, case = FALSE, decreasing = TRUE, inplace = FALSE ) print(new) # [1] apple banana cherry date fig grape # Levels: apple banana date cherry fig grape # Example 2: Reorder levels based on character frequency and reorder data elements new_inplace <- ft_freq( factor_vec, case = FALSE, decreasing = TRUE, inplace = TRUE ) print(new_inplace) # [1] apple banana date cherry fig grape # Levels: apple banana date cherry fig grape # Example 3: Reorder levels in decreasing order based on character frequency # without reordering data elements new_dec <- ft_freq( factor_vec, case = FALSE, decreasing = TRUE, inplace = FALSE ) print(new_dec) # [1] apple banana cherry date fig grape # Levels: apple banana date cherry fig grape # Example 4: Reorder levels with case sensitivity and reorder data elements factor_vec_case <- factor(c('Apple', 'banana', 'Cherry', 'date', 'Fig', 'grape')) new_case <- ft_freq( factor_vec_case, case = TRUE, decreasing = TRUE, inplace = TRUE ) print(new_case) # [1] Apple banana Cherry date Fig grape # Levels: cherry Apple banana grape Fig date # Example 5: Reorder levels based on character frequency, allowing insertion beyond string length factor_vec_short <- factor(c('go', 'dog', 'cat', 'bird')) new_short <- ft_freq( factor_vec_short, case = FALSE, decreasing = TRUE, inplace = FALSE ) print(new_short) # [1] go dog cat bird # Levels: cat dog bird go# Example 1: Reorder levels based on character frequency without reordering data elements factor_vec <- factor(c('apple', 'banana', 'cherry', 'date', 'fig', 'grape')) new <- ft_freq( factor_vec, case = FALSE, decreasing = TRUE, inplace = FALSE ) print(new) # [1] apple banana cherry date fig grape # Levels: apple banana date cherry fig grape # Example 2: Reorder levels based on character frequency and reorder data elements new_inplace <- ft_freq( factor_vec, case = FALSE, decreasing = TRUE, inplace = TRUE ) print(new_inplace) # [1] apple banana date cherry fig grape # Levels: apple banana date cherry fig grape # Example 3: Reorder levels in decreasing order based on character frequency # without reordering data elements new_dec <- ft_freq( factor_vec, case = FALSE, decreasing = TRUE, inplace = FALSE ) print(new_dec) # [1] apple banana cherry date fig grape # Levels: apple banana date cherry fig grape # Example 4: Reorder levels with case sensitivity and reorder data elements factor_vec_case <- factor(c('Apple', 'banana', 'Cherry', 'date', 'Fig', 'grape')) new_case <- ft_freq( factor_vec_case, case = TRUE, decreasing = TRUE, inplace = TRUE ) print(new_case) # [1] Apple banana Cherry date Fig grape # Levels: cherry Apple banana grape Fig date # Example 5: Reorder levels based on character frequency, allowing insertion beyond string length factor_vec_short <- factor(c('go', 'dog', 'cat', 'bird')) new_short <- ft_freq( factor_vec_short, case = FALSE, decreasing = TRUE, inplace = FALSE ) print(new_short) # [1] go dog cat bird # Levels: cat dog bird go
Groups factor levels by a common prefix of specified length.
ft_group_by_prefix(factor_vec, prefix_length)ft_group_by_prefix(factor_vec, prefix_length)
factor_vec |
A factor vector to be grouped. |
prefix_length |
An integer specifying the number of characters in the prefix. |
A factor vector with levels grouped by the common prefix.
Kai Guo
# Example factor vector factor_vec <- factor(c('apple_red', 'apple_green', 'banana_yellow', 'banana_green', 'cherry_red')) # Group by first 5 characters (common prefix) ft_group_by_prefix(factor_vec, prefix_length = 5)# Example factor vector factor_vec <- factor(c('apple_red', 'apple_green', 'banana_yellow', 'banana_green', 'cherry_red')) # Group by first 5 characters (common prefix) ft_group_by_prefix(factor_vec, prefix_length = 5)
Replaces NA values in a factor vector using specified imputation methods.
ft_impute(factor_vec, method = "mode")ft_impute(factor_vec, method = "mode")
factor_vec |
A factor vector with potential |
method |
The imputation method: |
A factor vector with NA values imputed.
Kai Guo
# Example factor vector with NAs factor_vec <- factor(c('apple', NA, 'banana', 'apple', NA)) # Impute using mode ft_impute(factor_vec, method = 'mode') # Impute using random selection ft_impute(factor_vec, method = 'random')# Example factor vector with NAs factor_vec <- factor(c('apple', NA, 'banana', 'apple', NA)) # Impute using mode ft_impute(factor_vec, method = 'mode') # Impute using random selection ft_impute(factor_vec, method = 'random')
Inserts one or more new levels into a factor vector immediately before or after specified target levels or
positions. Each new level corresponds to its respective target level or position. If positions or target
has a single element, it will be repeated to match the length of insert.
Supports exact matches, position-based targeting, and pattern-based matching with optional case sensitivity.
Can handle multiple insertions, manage duplicates, and optionally reorder the data vector's elements to
align with the new levels.
If any position in positions exceeds the number of levels in factor_vec, the new level(s) will be
appended at the end.
ft_insert( factor_vec, insert, target = NULL, positions = NULL, pattern = NULL, case = FALSE, insert_after_na = FALSE, allow_duplicates = FALSE, position = "after", inplace = FALSE )ft_insert( factor_vec, insert, target = NULL, positions = NULL, pattern = NULL, case = FALSE, insert_after_na = FALSE, allow_duplicates = FALSE, position = "after", inplace = FALSE )
factor_vec |
A factor vector into which new levels will be inserted. |
insert |
A character vector of new levels to insert. Each new level corresponds to the respective target level or position. |
target |
A character vector specifying the levels before or after which the new levels will be inserted. If length 1 and |
positions |
An integer vector specifying the positions of levels before or after which the new levels will be inserted. If length 1 and |
pattern |
A regular expression pattern to identify target levels for insertion. Overrides both |
case |
Logical. Should pattern matching be case-sensitive? Defaults to |
insert_after_na |
Logical. Should |
allow_duplicates |
Logical. If |
position |
Character. Where to insert the new levels relative to the target: |
inplace |
Logical. If |
A new factor vector with the new levels inserted at the specified positions. If inplace = TRUE, the data vector's elements are reordered to match the new levels' order. If inplace = FALSE, only the levels' order is adjusted without changing the data vector's elements' order.
Kai Guo
# Example 1: Insert 'date' after position 2 and 'grape' after position 4 # without allowing duplicates, returning a new factor vector factor_vec <- factor(c('apple', 'banana', 'cherry', 'date', 'fig', 'grape')) new_factor <- ft_insert( factor_vec, insert = c('date', 'grape'), positions = c(2, 4), inplace = FALSE ) print(new_factor) # [1] apple banana date cherry fig grape # Levels: apple banana date cherry fig grape # Example 2: Insert 'date' after position 2 and 'grape' after position 4, # allowing duplicates, returning a new factor vector new_factor_dup <- ft_insert( factor_vec, insert = c('date', 'grape'), positions = c(2, 4), allow_duplicates = TRUE, inplace = FALSE ) print(new_factor_dup) # [1] apple banana date cherry fig grape.1 # Levels: apple banana date cherry fig grape.1 # Example 3: Insert 'date' after position 2 and 'grape' after position 4, # and reorder data elements new_factor_inplace <- ft_insert( factor_vec, insert = c('date', 'grape'), positions = c(2, 4), inplace = TRUE ) print(new_factor_inplace) # [1] apple banana date cherry fig grape # Levels: apple banana date cherry fig grape # Example 4: Insert 'kiwi' after 'banana' and 'grape', case-sensitive, # allowing duplicates, returning a new factor vector factor_vec_case <- factor(c('Apple', 'banana', 'Cherry', 'date', 'Fig', 'grape')) new_factor_case <- ft_insert( factor_vec_case, insert = c('kiwi', 'kiwi'), target = c('banana', 'grape'), case = TRUE, allow_duplicates = TRUE, inplace = FALSE ) print(new_factor_case) # [1] Apple banana Cherry date Fig grape kiwi kiwi.1 # Example 5: Insert 'date' and 'elderberry' after position 2 factor_vec <- factor(c('apple', 'banana', 'cherry', 'fig', 'grape')) new_factor <- ft_insert( factor_vec, insert = c('date', 'elderberry'), positions = 2, position = "after", inplace = FALSE ) print(levels(new_factor)) # [1] "apple" "banana" "date" "elderberry" "cherry" "fig" "grape" # Example 6: Insert 'kiwi' at position exceeding the number of levels new_factor_exceed <- ft_insert( factor_vec, insert = 'kiwi', positions = 10, # Position exceeds number of levels position = "after", inplace = FALSE ) print(levels(new_factor_exceed)) # [1] "apple" "banana" "cherry" "fig" "grape" "kiwi" # Example 7: Insert multiple levels with positions exceeding the number of levels new_factor_multi_exceed <- ft_insert( factor_vec, insert = c('lemon', 'mango'), positions = c(5, 10), # Second position exceeds number of levels position = "after", inplace = FALSE ) print(levels(new_factor_multi_exceed)) # [1] "apple" "banana" "cherry" "fig" "grape" "lemon" "mango" # Example 8: Insert multiple levels after a single position (positions repeated) new_factor_repeat <- ft_insert( factor_vec, insert = c('kiwi', 'lemon', 'mango'), positions = 2, position = "after", inplace = FALSE ) print(levels(new_factor_repeat)) # [1] "apple" "banana" "kiwi" "lemon" "mango" "cherry" "fig" "grape" # Example 9: Insert multiple levels before a single target (target repeated) new_factor_target_repeat <- ft_insert( factor_vec, insert = c('kiwi', 'lemon', 'mango'), target = 'cherry', position = "before", inplace = FALSE ) print(levels(new_factor_target_repeat)) # [1] "apple" "banana" "kiwi" "lemon" "mango" "cherry" "fig" "grape"# Example 1: Insert 'date' after position 2 and 'grape' after position 4 # without allowing duplicates, returning a new factor vector factor_vec <- factor(c('apple', 'banana', 'cherry', 'date', 'fig', 'grape')) new_factor <- ft_insert( factor_vec, insert = c('date', 'grape'), positions = c(2, 4), inplace = FALSE ) print(new_factor) # [1] apple banana date cherry fig grape # Levels: apple banana date cherry fig grape # Example 2: Insert 'date' after position 2 and 'grape' after position 4, # allowing duplicates, returning a new factor vector new_factor_dup <- ft_insert( factor_vec, insert = c('date', 'grape'), positions = c(2, 4), allow_duplicates = TRUE, inplace = FALSE ) print(new_factor_dup) # [1] apple banana date cherry fig grape.1 # Levels: apple banana date cherry fig grape.1 # Example 3: Insert 'date' after position 2 and 'grape' after position 4, # and reorder data elements new_factor_inplace <- ft_insert( factor_vec, insert = c('date', 'grape'), positions = c(2, 4), inplace = TRUE ) print(new_factor_inplace) # [1] apple banana date cherry fig grape # Levels: apple banana date cherry fig grape # Example 4: Insert 'kiwi' after 'banana' and 'grape', case-sensitive, # allowing duplicates, returning a new factor vector factor_vec_case <- factor(c('Apple', 'banana', 'Cherry', 'date', 'Fig', 'grape')) new_factor_case <- ft_insert( factor_vec_case, insert = c('kiwi', 'kiwi'), target = c('banana', 'grape'), case = TRUE, allow_duplicates = TRUE, inplace = FALSE ) print(new_factor_case) # [1] Apple banana Cherry date Fig grape kiwi kiwi.1 # Example 5: Insert 'date' and 'elderberry' after position 2 factor_vec <- factor(c('apple', 'banana', 'cherry', 'fig', 'grape')) new_factor <- ft_insert( factor_vec, insert = c('date', 'elderberry'), positions = 2, position = "after", inplace = FALSE ) print(levels(new_factor)) # [1] "apple" "banana" "date" "elderberry" "cherry" "fig" "grape" # Example 6: Insert 'kiwi' at position exceeding the number of levels new_factor_exceed <- ft_insert( factor_vec, insert = 'kiwi', positions = 10, # Position exceeds number of levels position = "after", inplace = FALSE ) print(levels(new_factor_exceed)) # [1] "apple" "banana" "cherry" "fig" "grape" "kiwi" # Example 7: Insert multiple levels with positions exceeding the number of levels new_factor_multi_exceed <- ft_insert( factor_vec, insert = c('lemon', 'mango'), positions = c(5, 10), # Second position exceeds number of levels position = "after", inplace = FALSE ) print(levels(new_factor_multi_exceed)) # [1] "apple" "banana" "cherry" "fig" "grape" "lemon" "mango" # Example 8: Insert multiple levels after a single position (positions repeated) new_factor_repeat <- ft_insert( factor_vec, insert = c('kiwi', 'lemon', 'mango'), positions = 2, position = "after", inplace = FALSE ) print(levels(new_factor_repeat)) # [1] "apple" "banana" "kiwi" "lemon" "mango" "cherry" "fig" "grape" # Example 9: Insert multiple levels before a single target (target repeated) new_factor_target_repeat <- ft_insert( factor_vec, insert = c('kiwi', 'lemon', 'mango'), target = 'cherry', position = "before", inplace = FALSE ) print(levels(new_factor_target_repeat)) # [1] "apple" "banana" "kiwi" "lemon" "mango" "cherry" "fig" "grape"
Combines multiple factor vectors and returns a factor vector containing only the levels common to all.
ft_intersect(...)ft_intersect(...)
... |
Factor vectors to be intersected. |
A factor vector containing the intersection of levels from all provided factors.
Kai Guo
# Example factor vectors factor_vec1 <- factor(c('apple', 'banana', 'cherry')) factor_vec2 <- factor(c('banana', 'date', 'cherry')) factor_vec3 <- factor(c('banana', 'cherry', 'fig')) # Get intersection of levels ft_intersect(factor_vec1, factor_vec2, factor_vec3)# Example factor vectors factor_vec1 <- factor(c('apple', 'banana', 'cherry')) factor_vec2 <- factor(c('banana', 'date', 'cherry')) factor_vec3 <- factor(c('banana', 'cherry', 'fig')) # Get intersection of levels ft_intersect(factor_vec1, factor_vec2, factor_vec3)
Reorders the levels of a factor vector based on the character length of each level. Optionally reorders the data vector's elements to align with the new levels' order.
ft_len(factor_vec, decreasing = FALSE, inplace = FALSE)ft_len(factor_vec, decreasing = FALSE, inplace = FALSE)
factor_vec |
A factor vector to be sorted. |
decreasing |
Logical. Should the ordering be decreasing by length? Default is |
inplace |
Logical. If |
A factor vector with levels reordered based on their length. Depending on the inplace parameter, the data vector's elements may also be reordered.
Kai Guo
# Example factor vector factor_vec <- factor(c('apple', 'banana', 'cherry', 'date')) # Sort levels by length without reordering data elements sorted_factor <- ft_len(factor_vec) print(sorted_factor) # [1] apple banana cherry date # Levels: apple date banana cherry # Sort levels by length and reorder data elements sorted_factor_inplace <- ft_len(factor_vec, inplace = TRUE) print(sorted_factor_inplace) # [1] date apple banana cherry # Levels: apple date banana cherry# Example factor vector factor_vec <- factor(c('apple', 'banana', 'cherry', 'date')) # Sort levels by length without reordering data elements sorted_factor <- ft_len(factor_vec) print(sorted_factor) # [1] apple banana cherry date # Levels: apple date banana cherry # Sort levels by length and reorder data elements sorted_factor_inplace <- ft_len(factor_vec, inplace = TRUE) print(sorted_factor_inplace) # [1] date apple banana cherry # Levels: apple date banana cherry
Calculates the number of characters in each level of a factor vector.
ft_level_lengths(factor_vec)ft_level_lengths(factor_vec)
factor_vec |
A factor vector. |
A named numeric vector with the length of each level.
Kai Guo
# Example factor vector factor_vec <- factor(c('apple', 'banana', 'cherry')) # Get level lengths ft_level_lengths(factor_vec)# Example factor vector factor_vec <- factor(c('apple', 'banana', 'cherry')) # Get level lengths ft_level_lengths(factor_vec)
Returns a vector indicating the order in which factor levels appear in the data.
ft_level_order(factor_vec)ft_level_order(factor_vec)
factor_vec |
A factor vector. |
A numeric vector representing the order of levels.
Kai Guo
# Example factor vector factor_vec <- factor(c('banana', 'apple', 'cherry', 'apple', 'banana')) # Get level order ft_level_order(factor_vec)# Example factor vector factor_vec <- factor(c('banana', 'apple', 'cherry', 'apple', 'banana')) # Get level order ft_level_order(factor_vec)
Computes statistical summaries for each level of a factor vector based on associated numeric data.
ft_level_stats(factor_vec, numeric_vec, stat_func)ft_level_stats(factor_vec, numeric_vec, stat_func)
factor_vec |
A factor vector. |
numeric_vec |
A numeric vector of the same length as |
stat_func |
A function to compute the statistic (e.g., mean, median). |
A data frame with factor levels and their corresponding statistics.
Kai Guo
# Example data factor_vec <- factor(c('A', 'B', 'A', 'B', 'C')) numeric_vec <- c(10, 20, 15, 25, 30) # Calculate mean for each level ft_level_stats(factor_vec, numeric_vec, stat_func = mean)# Example data factor_vec <- factor(c('A', 'B', 'A', 'B', 'C')) numeric_vec <- c(10, 20, 15, 25, 30) # Calculate mean for each level ft_level_stats(factor_vec, numeric_vec, stat_func = mean)
Transforms factor levels by applying a function that can include complex logic.
ft_map_func(factor_vec, map_func)ft_map_func(factor_vec, map_func)
factor_vec |
A factor vector to map. |
map_func |
A function that takes a character vector of levels and returns a character vector of new levels. |
A factor vector with levels mapped according to the function.
Kai Guo
# Example factor vector factor_vec <- factor(c('apple', 'banana', 'cherry')) # Map levels to uppercase if they start with 'a' ft_map_func(factor_vec, function(x) { ifelse(grepl('^a', x), toupper(x), x) })# Example factor vector factor_vec <- factor(c('apple', 'banana', 'cherry')) # Map levels to uppercase if they start with 'a' ft_map_func(factor_vec, function(x) { ifelse(grepl('^a', x), toupper(x), x) })
Creates a data frame mapping the original factor levels to the modified levels.
ft_mapping(original_factor, modified_factor)ft_mapping(original_factor, modified_factor)
original_factor |
The original factor vector before modification. |
modified_factor |
The modified factor vector after modification. |
A data frame containing the mapping of original to modified levels.
Kai Guo
# Original and modified factor vectors original_factor <- factor(c('apple', 'banana', 'cherry')) modified_factor <- factor(c('apple_fruit', 'banana_fruit', 'cherry_fruit')) # Create mapping table ft_mapping(original_factor, modified_factor)# Original and modified factor vectors original_factor <- factor(c('apple', 'banana', 'cherry')) modified_factor <- factor(c('apple_fruit', 'banana_fruit', 'cherry_fruit')) # Create mapping table ft_mapping(original_factor, modified_factor)
Merges two factor vectors into one, retaining unique levels from both factors.
ft_merge(factor_vec1, factor_vec2, level_order = NULL)ft_merge(factor_vec1, factor_vec2, level_order = NULL)
factor_vec1 |
The first factor vector. |
factor_vec2 |
The second factor vector. |
level_order |
A character vector specifying the desired order of levels. If NULL, levels are ordered by their first appearance. |
A factor vector containing the combined data from both factors with unique levels.
Kai Guo
# Example factor vectors factor_vec1 <- factor(c('apple', 'banana', 'cherry')) factor_vec2 <- factor(c('banana', 'date', 'fig', 'grape')) # Merge factors and retain unique levels ft_merge(factor_vec1, factor_vec2)# Example factor vectors factor_vec1 <- factor(c('apple', 'banana', 'cherry')) factor_vec2 <- factor(c('banana', 'date', 'fig', 'grape')) # Merge factors and retain unique levels ft_merge(factor_vec1, factor_vec2)
Merges levels of a factor that are similar based on string distance.
ft_merge_similar(factor_vec, max_distance = 1, method = "lv")ft_merge_similar(factor_vec, max_distance = 1, method = "lv")
factor_vec |
A factor vector to modify. |
max_distance |
A numeric value specifying the maximum string distance for merging levels. |
method |
The method for computing string distance (default is 'lv' for Levenshtein distance). |
A factor vector with similar levels merged.
Kai Guo
# Example factor vector factor_vec <- factor(c('apple', 'appel', 'banana', 'bananna', 'cherry')) # Merge similar levels ft_merge_similar(factor_vec, max_distance = 1)# Example factor vector factor_vec <- factor(c('apple', 'appel', 'banana', 'bananna', 'cherry')) # Merge similar levels ft_merge_similar(factor_vec, max_distance = 1)
Handles NA values in a factor vector by either keeping NA as a level or removing levels and characters corresponding to NA values.
ft_na(factor_vec, keep_na = TRUE)ft_na(factor_vec, keep_na = TRUE)
factor_vec |
A factor vector to be processed. |
keep_na |
Logical. Should NA values be kept as a level in the factor? Default is |
A factor vector with NA values handled as specified.
Kai Guo
# Example factor vector with NA values factor_vec <- factor(c('apple', NA, 'banana', 'cherry', NA, 'date')) # Keep NA as a level ft_na(factor_vec, keep_na = TRUE) # Remove NA values ft_na(factor_vec, keep_na = FALSE)# Example factor vector with NA values factor_vec <- factor(c('apple', NA, 'banana', 'cherry', NA, 'date')) # Keep NA as a level ft_na(factor_vec, keep_na = TRUE) # Remove NA values ft_na(factor_vec, keep_na = FALSE)
Pads each level of a factor vector with leading characters to reach a specified width.
ft_pad_levels(factor_vec, width, pad_char)ft_pad_levels(factor_vec, width, pad_char)
factor_vec |
A factor vector whose levels will be padded. |
width |
An integer specifying the desired total width for each level after padding. |
pad_char |
A character string used for padding. Can be of length one or more characters. |
A factor vector with padded levels.
Kai Guo
# Example factor vector factor_vec <- factor(c('A', 'B', 'C', 'D')) # Pad levels to width 4 using '0' as padding character padded_factor <- ft_pad_levels(factor_vec, width = 4, pad_char = '0') print(levels(padded_factor)) # Output: "000A" "000B" "000C" "000D" # Pad levels to width 6 using '%A' as padding string padded_factor <- ft_pad_levels(factor_vec, width = 6, pad_char = '%A') print(levels(padded_factor)) # Output: "%%A%A" "%%A%B" "%%A%C" "%%A%D"# Example factor vector factor_vec <- factor(c('A', 'B', 'C', 'D')) # Pad levels to width 4 using '0' as padding character padded_factor <- ft_pad_levels(factor_vec, width = 4, pad_char = '0') print(levels(padded_factor)) # Output: "000A" "000B" "000C" "000D" # Pad levels to width 6 using '%A' as padding string padded_factor <- ft_pad_levels(factor_vec, width = 6, pad_char = '%A') print(levels(padded_factor)) # Output: "%%A%A" "%%A%B" "%%A%C" "%%A%D"
Creates all unique pairwise combinations between factor_vec of a vector, with options for references, symmetry, NA handling, custom filtering, and output formats. Automatically handles factors by converting them to vectors and removes extra spaces from factor_vec before processing.
ft_pairs( factor_vec, ref = NULL, symmetric = TRUE, include_na = FALSE, include_self = FALSE, filter_fn = NULL, pre_fn = trimws, sort_by = "none", output_format = "data.frame" )ft_pairs( factor_vec, ref = NULL, symmetric = TRUE, include_na = FALSE, include_self = FALSE, filter_fn = NULL, pre_fn = trimws, sort_by = "none", output_format = "data.frame" )
factor_vec |
A vector containing the factor_vec to compare. Can be of any type (character, numeric, factor, etc.). |
ref |
Optional. A vector containing the reference factor_vec. If NULL (default), comparisons are made within the |
symmetric |
Logical. If |
include_na |
Logical. If |
include_self |
Logical. If |
filter_fn |
Optional. A custom function to filter the pairs. Should accept a data frame and return a logical vector. |
pre_fn |
Optional. A function to preprocess the factor_vec before comparison (e.g., |
sort_by |
Character string specifying how to sort the output. Options are |
output_format |
Character string specifying the output format. Options are |
A data frame, list, matrix, or tibble containing pairwise comparisons between factor_vec.
# Example vector with extra spaces and mixed case vec <- c(' A', 'b ', ' C ', 'D') # Generate pairwise comparisons within vec ft_pairs(vec) # Use a custom preprocessing function to convert factor_vec to lower case ft_pairs(vec, pre_fn = function(x) tolower(trimws(x))) ft_pairs(vec, ref = c("A","C"))# Example vector with extra spaces and mixed case vec <- c(' A', 'b ', ' C ', 'D') # Generate pairwise comparisons within vec ft_pairs(vec) # Use a custom preprocessing function to convert factor_vec to lower case ft_pairs(vec, pre_fn = function(x) tolower(trimws(x))) ft_pairs(vec, ref = c("A","C"))
Reorders the levels of a factor vector based on characters extracted from specified positions within each level's name. Supports case sensitivity, descending order, and optionally reorders the data vector's elements to align with the new levels' order.
ft_pos( factor_vec, positions, case = FALSE, decreasing = FALSE, inplace = FALSE )ft_pos( factor_vec, positions, case = FALSE, decreasing = FALSE, inplace = FALSE )
factor_vec |
A factor vector whose levels will be reordered. |
positions |
An integer vector specifying the character positions to extract from each level's name for ordering. |
case |
Logical. If |
decreasing |
Logical. If |
inplace |
Logical. If |
A new factor vector with reordered levels. Depending on the inplace parameter, the data vector's elements may also be reordered.
Kai Guo
# Example 1: Reorder levels based on characters at positions 2 and 4 # without reordering data elements factor_vec <- factor(c('apple', 'banana', 'cherry', 'date', 'fig', 'grape')) new <- ft_pos( factor_vec, positions = c(2, 4), case = FALSE, decreasing = FALSE, inplace = FALSE ) print(new) # [1] apple banana cherry date fig grape # Levels: apple banana date cherry fig grape # Example 2: Reorder levels based on characters at positions 2 and 4 # and reorder data elements new_inplace <- ft_pos( factor_vec, positions = c(2, 4), case = FALSE, decreasing = FALSE, inplace = TRUE ) print(new_inplace) # [1] apple banana date cherry fig grape # Levels: apple banana date cherry fig grape # Example 3: Reorder levels in decreasing order based on characters at # positions 1 and 3 without reordering data elements new_dec <- ft_pos( factor_vec, positions = c(1, 3), case = FALSE, decreasing = TRUE, inplace = FALSE ) print(new_dec) # [1] apple banana cherry date fig grape # Levels: grape fig date cherry banana apple # Example 4: Reorder levels with case sensitivity and reorder data elements factor_vec_case <- factor(c('Apple', 'banana', 'Cherry', 'date', 'Fig', 'grape')) new_case <- ft_pos( factor_vec_case, positions = c(1, 2), case = TRUE, decreasing = FALSE, inplace = TRUE ) print(new_case) # [1] Apple banana Cherry date Fig grape # Levels: Apple banana Cherry date Fig grape # Example 5: Reorder levels based on characters at positions 3, allowing # insertion at positions beyond string length factor_vec_short <- factor(c('go', 'dog', 'cat', 'bird')) new_short <- ft_pos( factor_vec_short, positions = c(3), case = FALSE, decreasing = FALSE, inplace = FALSE ) print(new_short) # [1] go dog cat bird # Levels: cat dog bird go# Example 1: Reorder levels based on characters at positions 2 and 4 # without reordering data elements factor_vec <- factor(c('apple', 'banana', 'cherry', 'date', 'fig', 'grape')) new <- ft_pos( factor_vec, positions = c(2, 4), case = FALSE, decreasing = FALSE, inplace = FALSE ) print(new) # [1] apple banana cherry date fig grape # Levels: apple banana date cherry fig grape # Example 2: Reorder levels based on characters at positions 2 and 4 # and reorder data elements new_inplace <- ft_pos( factor_vec, positions = c(2, 4), case = FALSE, decreasing = FALSE, inplace = TRUE ) print(new_inplace) # [1] apple banana date cherry fig grape # Levels: apple banana date cherry fig grape # Example 3: Reorder levels in decreasing order based on characters at # positions 1 and 3 without reordering data elements new_dec <- ft_pos( factor_vec, positions = c(1, 3), case = FALSE, decreasing = TRUE, inplace = FALSE ) print(new_dec) # [1] apple banana cherry date fig grape # Levels: grape fig date cherry banana apple # Example 4: Reorder levels with case sensitivity and reorder data elements factor_vec_case <- factor(c('Apple', 'banana', 'Cherry', 'date', 'Fig', 'grape')) new_case <- ft_pos( factor_vec_case, positions = c(1, 2), case = TRUE, decreasing = FALSE, inplace = TRUE ) print(new_case) # [1] Apple banana Cherry date Fig grape # Levels: Apple banana Cherry date Fig grape # Example 5: Reorder levels based on characters at positions 3, allowing # insertion at positions beyond string length factor_vec_short <- factor(c('go', 'dog', 'cat', 'bird')) new_short <- ft_pos( factor_vec_short, positions = c(3), case = FALSE, decreasing = FALSE, inplace = FALSE ) print(new_short) # [1] go dog cat bird # Levels: cat dog bird go
Reorders the levels of a factor vector based on the frequency of substrings matching a regular expression.
ft_regex_freq( factor_vec, pattern, case = FALSE, decreasing = TRUE, inplace = TRUE )ft_regex_freq( factor_vec, pattern, case = FALSE, decreasing = TRUE, inplace = TRUE )
factor_vec |
A factor vector whose levels are to be reordered. |
pattern |
A string representing the regular expression pattern to match. |
case |
Logical. Should the pattern matching be case-sensitive? Default is |
decreasing |
Logical. Should the ordering be decreasing by frequency? Default is |
inplace |
Logical. If |
A factor vector with levels reordered based on the frequency of matched substrings.
Kai Guo
# Example factor vector factor_vec <- factor(c('apple', 'banana', 'apricot', 'cherry', 'blueberry', 'blackberry', 'date')) # Reorder based on pattern matching 'a' ft_regex_freq(factor_vec, pattern = 'a') # Reorder with case-sensitive matching ft_regex_freq(factor_vec, pattern = '^[A-Z]', case = TRUE)# Example factor vector factor_vec <- factor(c('apple', 'banana', 'apricot', 'cherry', 'blueberry', 'blackberry', 'date')) # Reorder based on pattern matching 'a' ft_regex_freq(factor_vec, pattern = 'a') # Reorder with case-sensitive matching ft_regex_freq(factor_vec, pattern = '^[A-Z]', case = TRUE)
Removes specified levels from a factor vector, keeping the remaining levels and their order unchanged.
ft_remove_levels(factor_vec, levels_to_remove, remove_na = TRUE)ft_remove_levels(factor_vec, levels_to_remove, remove_na = TRUE)
factor_vec |
A factor vector from which levels will be removed. |
levels_to_remove |
A character vector of levels to be removed from the factor. |
remove_na |
remove NA from the output? Default is |
A factor vector with specified levels removed and remaining levels unchanged.
Kai Guo
# Example factor vector factor_vec <- factor(c('apple', 'banana', 'cherry', 'date', 'fig', 'grape')) # Remove levels 'banana' and 'date' ft_remove_levels(factor_vec, levels_to_remove = c('banana', 'date'))# Example factor vector factor_vec <- factor(c('apple', 'banana', 'cherry', 'date', 'fig', 'grape')) # Remove levels 'banana' and 'date' ft_remove_levels(factor_vec, levels_to_remove = c('banana', 'date'))
Renames the levels of a factor vector based on a mapping provided in a data frame.
ft_rename_levels(factor_vec, mapping_df)ft_rename_levels(factor_vec, mapping_df)
factor_vec |
A factor vector to modify. |
mapping_df |
A data frame with two columns: 'old' and 'new', representing old and new level names. |
A factor vector with levels renamed.
Kai Guo
# Example factor vector factor_vec <- factor(c('A', 'B', 'C')) # Mapping data frame mapping_df <- data.frame(old = c('A', 'B'), new = c('Alpha', 'Beta')) # Rename levels ft_rename_levels(factor_vec, mapping_df)# Example factor vector factor_vec <- factor(c('A', 'B', 'C')) # Mapping data frame mapping_df <- data.frame(old = c('A', 'B'), new = c('Alpha', 'Beta')) # Rename levels ft_rename_levels(factor_vec, mapping_df)
Reorders the levels of a factor vector within groups defined by another factor vector.
ft_reorder_within(factor_vec, group_vec, by, fun = mean, decreasing = FALSE)ft_reorder_within(factor_vec, group_vec, by, fun = mean, decreasing = FALSE)
factor_vec |
A factor vector to be reordered. |
group_vec |
A factor vector defining the groups. |
by |
A numeric vector to order by. |
fun |
A function to summarize within groups (e.g., mean, median). |
decreasing |
Logical. Should the ordering be decreasing? Default is |
A factor vector with levels reordered within groups.
Kai Guo
# Example data data <- data.frame( item = factor(c('A', 'B', 'C', 'D', 'E', 'F')), group = factor(c('G1', 'G1', 'G1', 'G2', 'G2', 'G2')), value = c(10, 15, 5, 20, 25, 15) ) data <- rbind(data, data) # Reorder 'item' within 'group' by 'value' data$item <- ft_reorder_within(data$item, data$group, data$value, mean)# Example data data <- data.frame( item = factor(c('A', 'B', 'C', 'D', 'E', 'F')), group = factor(c('G1', 'G1', 'G1', 'G2', 'G2', 'G2')), value = c(10, 15, 5, 20, 25, 15) ) data <- rbind(data, data) # Reorder 'item' within 'group' by 'value' data$item <- ft_reorder_within(data$item, data$group, data$value, mean)
Replaces a specified level in a factor vector with a new level. If a position is provided, the new level is inserted at the specified position among the levels; otherwise, the original level order is preserved.
ft_replace(factor_vec, old_level, new_level, position = NULL)ft_replace(factor_vec, old_level, new_level, position = NULL)
factor_vec |
A factor vector in which a level will be replaced. |
old_level |
A character string specifying the level to be replaced. |
new_level |
A character string specifying the new level to replace the old level. |
position |
Optional. A positive integer specifying the position to insert the new level in the levels vector. If |
A factor vector with the level replaced and the new level optionally inserted at the specified position.
Kai Guo
# factor_vec <- factor(c('apple', 'banana', 'cherry', 'date', 'fig', 'grape')) # replace 'banana' as 'blueberry', and keep original order ft_replace(factor_vec, old_level = 'banana', new_level = 'blueberry') # replace 'banana' as 'blueberry' ft_replace(factor_vec, old_level = 'banana', new_level = 'blueberry', position = 2)# factor_vec <- factor(c('apple', 'banana', 'cherry', 'date', 'fig', 'grape')) # replace 'banana' as 'blueberry', and keep original order ft_replace(factor_vec, old_level = 'banana', new_level = 'blueberry') # replace 'banana' as 'blueberry' ft_replace(factor_vec, old_level = 'banana', new_level = 'blueberry', position = 2)
Replaces NA values in a factor vector with a specified level.
ft_replace_na(factor_vec, replacement_level)ft_replace_na(factor_vec, replacement_level)
factor_vec |
A factor vector. |
replacement_level |
A string specifying the level to replace |
A factor vector with NA values replaced.
Kai Guo
# Example factor vector factor_vec <- factor(c('apple', NA, 'banana', 'cherry', NA)) # Replace NAs with 'Unknown' ft_replace_na(factor_vec, replacement_level = 'Unknown')# Example factor vector factor_vec <- factor(c('apple', NA, 'banana', 'cherry', NA)) # Replace NAs with 'Unknown' ft_replace_na(factor_vec, replacement_level = 'Unknown')
Replaces parts of the factor levels that match a specified pattern with a new string.
ft_replace_pattern(factor_vec, pattern, replacement, replace_all = TRUE)ft_replace_pattern(factor_vec, pattern, replacement, replace_all = TRUE)
factor_vec |
A factor vector to be modified. |
pattern |
A regular expression pattern to match. |
replacement |
A string to replace the matched parts. |
replace_all |
Logical. If |
A factor vector with levels modified.
Kai Guo
# Example factor vector factor_vec <- factor(c('apple_pie', 'banana_bread', 'cherry_cake')) # Replace '_pie', '_bread', '_cake' with '_dessert' (all occurrences) ft_replace_pattern(factor_vec, pattern = '_.*', replacement = '_dessert') # Replace only the first occurrence of '_' with '-' ft_replace_pattern(factor_vec, pattern = '_', replacement = '-', replace_all = FALSE)# Example factor vector factor_vec <- factor(c('apple_pie', 'banana_bread', 'cherry_cake')) # Replace '_pie', '_bread', '_cake' with '_dessert' (all occurrences) ft_replace_pattern(factor_vec, pattern = '_.*', replacement = '_dessert') # Replace only the first occurrence of '_' with '-' ft_replace_pattern(factor_vec, pattern = '_', replacement = '-', replace_all = FALSE)
Reverses the order of the levels in a factor vector. Optionally reorders the data vector's elements to align with the reversed levels' order.
ft_reverse(factor_vec, inplace = FALSE)ft_reverse(factor_vec, inplace = FALSE)
factor_vec |
A factor vector whose levels will be reversed. |
inplace |
Logical. If |
A factor vector with levels in reversed order. Depending on the inplace parameter, the data vector's elements may also be reordered.
Kai Guo
# Example factor vector factor_vec <- factor(c('low', 'medium', 'high')) # Reverse the levels without reordering data elements reversed_factor <- ft_reverse(factor_vec) print(reversed_factor) # [1] low medium high # Levels: high medium low # Reverse the levels and reorder data elements reversed_factor_inplace <- ft_reverse(factor_vec, inplace = TRUE) print(reversed_factor_inplace) # [1] high medium low # Levels: high medium low# Example factor vector factor_vec <- factor(c('low', 'medium', 'high')) # Reverse the levels without reordering data elements reversed_factor <- ft_reverse(factor_vec) print(reversed_factor) # [1] low medium high # Levels: high medium low # Reverse the levels and reorder data elements reversed_factor_inplace <- ft_reverse(factor_vec, inplace = TRUE) print(reversed_factor_inplace) # [1] high medium low # Levels: high medium low
Aggregates the levels of a factor vector based on another grouping vector.
ft_rollup(factor_vec, groups)ft_rollup(factor_vec, groups)
factor_vec |
A factor vector to aggregate. |
groups |
A vector of the same length as |
A factor vector with aggregated levels.
Kai Guo
# Example factor vector and groups factor_vec <- factor(c('apple', 'banana', 'cherry', 'date', 'fig')) groups <- c('fruit', 'fruit', 'fruit', 'dry fruit', 'dry fruit') # Aggregate levels based on groups ft_rollup(factor_vec, groups)# Example factor vector and groups factor_vec <- factor(c('apple', 'banana', 'cherry', 'date', 'fig')) groups <- c('fruit', 'fruit', 'fruit', 'dry fruit', 'dry fruit') # Aggregate levels based on groups ft_rollup(factor_vec, groups)
Randomly selects a specified number of levels from a factor vector.
ft_sample_levels(factor_vec, size, seed = NULL)ft_sample_levels(factor_vec, size, seed = NULL)
factor_vec |
A factor vector. |
size |
An integer specifying the number of levels to sample. |
seed |
An optional integer for setting the random seed. |
A factor vector containing only the sampled levels.
Kai Guo
# Example factor vector factor_vec <- factor(letters[1:10]) # Sample 5 levels ft_sample_levels(factor_vec, size = 5, seed = 123)# Example factor vector factor_vec <- factor(letters[1:10]) # Sample 5 levels ft_sample_levels(factor_vec, size = 5, seed = 123)
Sorts the levels of a factor vector based on the values of another vector or a column from a data frame. Handles cases where the sorting vector may contain ‘NA's. Optionally reorders the data vector’s elements to align with the new levels' order.
ft_sort(factor_vec, by, decreasing = FALSE, na_last = TRUE, inplace = FALSE)ft_sort(factor_vec, by, decreasing = FALSE, na_last = TRUE, inplace = FALSE)
factor_vec |
A factor vector whose levels are to be sorted. |
by |
A vector or data frame column used as the basis for sorting. Must be the same length as 'factor_vec'. |
decreasing |
Logical. Should the sorting be in decreasing order? Default is |
na_last |
Logical. Should 'NA' values be put last? Default is |
inplace |
Logical. If |
A factor vector with levels sorted based on 'by'. Depending on the inplace parameter, the data vector's elements may also be reordered.
# Example using a vector without reordering data elements factor_vec <- factor(c('apple', 'banana', 'cherry', 'date')) by_vec <- c(2, 3, 1, NA) sorted_factor <- ft_sort(factor_vec, by = by_vec) print(sorted_factor) # [1] apple banana cherry date # Levels: cherry apple banana date # Example using a vector and reordering data elements sorted_factor_inplace <- ft_sort(factor_vec, by = by_vec, inplace = TRUE) print(sorted_factor_inplace) # [1] cherry apple banana date # Levels: cherry apple banana date # Example using a data frame column without reordering data elements data <- data.frame( Category = factor(c('apple', 'banana', 'cherry', 'date')), Value = c(2, 3, 1, NA) ) sorted_factor_df <- ft_sort(data$Category, by = data$Value) print(sorted_factor_df) # [1] apple banana cherry date # Levels: cherry apple banana date # Example using a data frame column and reordering data elements sorted_factor_df_inplace <- ft_sort(data$Category, by = data$Value, inplace = TRUE) print(sorted_factor_df_inplace) # [1] cherry apple banana date # Levels: cherry apple banana date# Example using a vector without reordering data elements factor_vec <- factor(c('apple', 'banana', 'cherry', 'date')) by_vec <- c(2, 3, 1, NA) sorted_factor <- ft_sort(factor_vec, by = by_vec) print(sorted_factor) # [1] apple banana cherry date # Levels: cherry apple banana date # Example using a vector and reordering data elements sorted_factor_inplace <- ft_sort(factor_vec, by = by_vec, inplace = TRUE) print(sorted_factor_inplace) # [1] cherry apple banana date # Levels: cherry apple banana date # Example using a data frame column without reordering data elements data <- data.frame( Category = factor(c('apple', 'banana', 'cherry', 'date')), Value = c(2, 3, 1, NA) ) sorted_factor_df <- ft_sort(data$Category, by = data$Value) print(sorted_factor_df) # [1] apple banana cherry date # Levels: cherry apple banana date # Example using a data frame column and reordering data elements sorted_factor_df_inplace <- ft_sort(data$Category, by = data$Value, inplace = TRUE) print(sorted_factor_df_inplace) # [1] cherry apple banana date # Levels: cherry apple banana date
Reorders the levels of a factor vector based on a custom function applied to each level. Optionally reorders the data vector's elements to align with the new levels' order.
ft_sort_custom(factor_vec, sort_func, decreasing = FALSE, inplace = FALSE)ft_sort_custom(factor_vec, sort_func, decreasing = FALSE, inplace = FALSE)
factor_vec |
A factor vector to sort. |
sort_func |
A function that takes a character vector (the levels) and returns a vector of the same length to sort by. |
decreasing |
Logical. Should the sort be decreasing? Default is |
inplace |
Logical. If |
A factor vector with levels reordered according to the custom function. Depending on the inplace parameter, the data vector's elements may also be reordered.
Kai Guo
# Example factor vector factor_vec <- factor(c('apple', 'banana', 'cherry')) # Sort levels by reverse alphabetical order without reordering data elements sorted_custom <- ft_sort_custom(factor_vec, function(x) -rank(x)) print(sorted_custom) # [1] apple banana cherry # Levels: cherry banana apple # Sort levels by reverse alphabetical order and reorder data elements sorted_custom_inplace <- ft_sort_custom(factor_vec, function(x) -rank(x), inplace = TRUE) print(sorted_custom_inplace) # [1] cherry banana apple # Levels: cherry banana apple # Sort levels by length of the level name without reordering data elements sorted_custom_length <- ft_sort_custom(factor_vec, function(x) nchar(x)) print(sorted_custom_length) # [1] apple banana cherry # Levels: apple cherry banana # Sort levels by length of the level name and reorder data elements sorted_custom_length_inplace <- ft_sort_custom(factor_vec, function(x) nchar(x), inplace = TRUE) print(sorted_custom_length_inplace) # [1] apple cherry banana # Levels: apple cherry banana# Example factor vector factor_vec <- factor(c('apple', 'banana', 'cherry')) # Sort levels by reverse alphabetical order without reordering data elements sorted_custom <- ft_sort_custom(factor_vec, function(x) -rank(x)) print(sorted_custom) # [1] apple banana cherry # Levels: cherry banana apple # Sort levels by reverse alphabetical order and reorder data elements sorted_custom_inplace <- ft_sort_custom(factor_vec, function(x) -rank(x), inplace = TRUE) print(sorted_custom_inplace) # [1] cherry banana apple # Levels: cherry banana apple # Sort levels by length of the level name without reordering data elements sorted_custom_length <- ft_sort_custom(factor_vec, function(x) nchar(x)) print(sorted_custom_length) # [1] apple banana cherry # Levels: apple cherry banana # Sort levels by length of the level name and reorder data elements sorted_custom_length_inplace <- ft_sort_custom(factor_vec, function(x) nchar(x), inplace = TRUE) print(sorted_custom_length_inplace) # [1] apple cherry banana # Levels: apple cherry banana
Splits the levels of a factor vector using specified patterns or positions and reorders based on specified parts or criteria. Optionally reorders the data vector's elements to align with the new levels' order.
ft_split( factor_vec, split_pattern, use_pattern = NULL, part = 1, position = NULL, char_freq = FALSE, decreasing = FALSE, inplace = FALSE )ft_split( factor_vec, split_pattern, use_pattern = NULL, part = 1, position = NULL, char_freq = FALSE, decreasing = FALSE, inplace = FALSE )
factor_vec |
A factor vector to be processed. |
split_pattern |
A character vector specifying the pattern(s) or position(s) to use for splitting. Can be regular expressions or integer positions. |
use_pattern |
An integer specifying which pattern to use if multiple patterns are provided. Default is |
part |
An integer or integer vector specifying which part(s) to use after splitting (e.g., 1 for the first part). Can be a range or specific indices. |
position |
An integer or integer vector specifying the character positions within the part(s) to consider. |
char_freq |
Logical. Should the sorting be based on character frequencies within the specified part(s)? Default is |
decreasing |
Logical. Should the ordering be decreasing? Default is |
inplace |
Logical. If |
A factor vector with levels reordered based on the specified conditions. Depending on the inplace parameter, the data vector's elements may also be reordered.
Kai Guo
# Example 1: Split by patterns '-', '_', or '|' and reorder based on the # first part without reordering data elements factor_vec <- factor(c('item1-sub1', 'item2_sub2', 'item3|sub3', 'item1-sub4')) ft_split(factor_vec, split_pattern = c('-', '_', '\\|'), part = 1, inplace = FALSE) # Example 2: Use the second pattern '_' for splitting and reorder # data elements ft_split(factor_vec, split_pattern = c('-', '_', '\\|'), use_pattern = 2, part = 2, inplace = TRUE) # Example 3: Reorder based on character frequencies in the specified part # without reordering data elements ft_split(factor_vec, split_pattern = '-', part = 2, char_freq = TRUE, inplace = FALSE) # Example 4: Split by pattern '-' and reorder both levels and data # elements based on the first part ft_split(factor_vec, split_pattern = '-', part = 1, inplace = TRUE)# Example 1: Split by patterns '-', '_', or '|' and reorder based on the # first part without reordering data elements factor_vec <- factor(c('item1-sub1', 'item2_sub2', 'item3|sub3', 'item1-sub4')) ft_split(factor_vec, split_pattern = c('-', '_', '\\|'), part = 1, inplace = FALSE) # Example 2: Use the second pattern '_' for splitting and reorder # data elements ft_split(factor_vec, split_pattern = c('-', '_', '\\|'), use_pattern = 2, part = 2, inplace = TRUE) # Example 3: Reorder based on character frequencies in the specified part # without reordering data elements ft_split(factor_vec, split_pattern = '-', part = 2, char_freq = TRUE, inplace = FALSE) # Example 4: Split by pattern '-' and reorder both levels and data # elements based on the first part ft_split(factor_vec, split_pattern = '-', part = 1, inplace = TRUE)
Splits the levels of a factor vector into multiple factors based on a specified delimiter.
ft_split_levels(factor_vec, delimiter, names = NULL)ft_split_levels(factor_vec, delimiter, names = NULL)
factor_vec |
A factor vector to split. |
delimiter |
A character string used to split the factor levels. |
names |
A character vector specifying names for the resulting factors. Default is |
A data frame containing the resulting factors.
Kai Guo
# Example factor vector factor_vec <- factor(c('red_large', 'blue_small', 'green_medium')) # Split levels into two factors ft_split_levels(factor_vec, delimiter = '_')# Example factor vector factor_vec <- factor(c('red_large', 'blue_small', 'green_medium')) # Split levels into two factors ft_split_levels(factor_vec, delimiter = '_')
Reorders the levels of a factor vector based on substrings extracted from the factor levels.
ft_sub( factor_vec, start_pos = NULL, end_pos = NULL, case = FALSE, decreasing = FALSE, inplace = TRUE )ft_sub( factor_vec, start_pos = NULL, end_pos = NULL, case = FALSE, decreasing = FALSE, inplace = TRUE )
factor_vec |
A factor vector whose levels are to be reordered. |
start_pos |
Positive integer. The starting position of the substring. If |
end_pos |
Positive integer. The ending position of the substring. If |
case |
Logical. Should the substring comparison be case-sensitive? Default is |
decreasing |
Logical. Should the ordering be decreasing? Default is |
inplace |
Logical. If |
A factor vector with levels reordered based on the specified substring.
Kai Guo
# Example factor vector factor_vec <- factor(c('Apple', 'banana', 'Cherry', 'date', 'Fig', 'grape')) # Reorder based on substring from position 2 to 4 ft_sub(factor_vec, start_pos = 2, end_pos = 4) # Reorder from position 3 to end, case-sensitive ft_sub(factor_vec, start_pos = 3, case = TRUE)# Example factor vector factor_vec <- factor(c('Apple', 'banana', 'Cherry', 'date', 'Fig', 'grape')) # Reorder based on substring from position 2 to 4 ft_sub(factor_vec, start_pos = 2, end_pos = 4) # Reorder from position 3 to end, case-sensitive ft_sub(factor_vec, start_pos = 3, case = TRUE)
Reorders the levels of a factor vector based on the frequency of substrings extracted from the data.
ft_substr_freq( factor_vec, start_pos = NULL, end_pos = NULL, case = FALSE, decreasing = TRUE, inplace = TRUE )ft_substr_freq( factor_vec, start_pos = NULL, end_pos = NULL, case = FALSE, decreasing = TRUE, inplace = TRUE )
factor_vec |
A factor vector whose levels are to be reordered. |
start_pos |
Positive integer. The starting position of the substring. If |
end_pos |
Positive integer. The ending position of the substring. If |
case |
Logical. Should the substring comparison be case-sensitive? Default is |
decreasing |
Logical. Should the ordering be decreasing by frequency? Default is |
inplace |
Logical. If |
A factor vector with levels reordered based on the frequency of substrings.
Kai Guo
# Example factor vector with multi-byte characters factor_vec <- factor(c('apple', 'banana', 'apricot', 'cherry', 'banana', 'banana', 'date')) # Reorder from position 2 to end ft_substr_freq(factor_vec, start_pos = 2) factor_vec <- factor(c('apple', 'banana', 'apricot', 'cherry', 'banana', 'banana', 'date')) ft_substr_freq(factor_vec, start_pos = 2, end_pos=3)# Example factor vector with multi-byte characters factor_vec <- factor(c('apple', 'banana', 'apricot', 'cherry', 'banana', 'banana', 'date')) # Reorder from position 2 to end ft_substr_freq(factor_vec, start_pos = 2) factor_vec <- factor(c('apple', 'banana', 'apricot', 'cherry', 'banana', 'banana', 'date')) ft_substr_freq(factor_vec, start_pos = 2, end_pos=3)
Counts the frequency of each character appearing in the levels of a factor vector, optionally including NA values, and returns a table or vector.
ft_table(factor_vec, case = FALSE, include_na = FALSE, as_table = TRUE)ft_table(factor_vec, case = FALSE, include_na = FALSE, as_table = TRUE)
factor_vec |
A factor vector whose levels will be analyzed. |
case |
Logical. Should the character count be case-sensitive? Default is |
include_na |
Logical. Should NA levels be included in the character count? Default is |
as_table |
Logical. Should the result be returned as a table? If |
A table or named vector of character frequencies.
Kai Guo
# Example factor vector with NA levels factor_vec <- factor(c('apple', 'banana', NA, 'cherry', 'date', NA, 'fig', 'grape'), exclude = NULL) # Get character frequencies (case-insensitive), excluding NA levels ft_table(factor_vec) # Include NA levels in the character frequencies ft_table(factor_vec, include_na = TRUE)# Example factor vector with NA levels factor_vec <- factor(c('apple', 'banana', NA, 'cherry', 'date', NA, 'fig', 'grape'), exclude = NULL) # Get character frequencies (case-insensitive), excluding NA levels ft_table(factor_vec) # Include NA levels in the character frequencies ft_table(factor_vec, include_na = TRUE)
Combines multiple factor vectors and returns a factor vector containing all unique levels.
ft_union(...)ft_union(...)
... |
Factor vectors to be united. |
A factor vector containing all unique levels from all provided factors.
Kai Guo
# Example factor vectors factor_vec1 <- factor(c('apple', 'banana')) factor_vec2 <- factor(c('banana', 'cherry')) factor_vec3 <- factor(c('date', 'fig')) # Get union of levels ft_union(factor_vec1, factor_vec2, factor_vec3)# Example factor vectors factor_vec1 <- factor(c('apple', 'banana')) factor_vec2 <- factor(c('banana', 'cherry')) factor_vec3 <- factor(c('date', 'fig')) # Get union of levels ft_union(factor_vec1, factor_vec2, factor_vec3)
Generates a new factor where each level represents a unique combination of levels from the input factors.
ft_unique_comb(..., sep = "_")ft_unique_comb(..., sep = "_")
... |
Factor vectors to combine. |
sep |
A string to separate levels in the combined factor. Default is |
A factor vector representing unique combinations.
Kai Guo
# Example factors factor_vec1 <- factor(c('A', 'A', 'B', 'B')) factor_vec2 <- factor(c('X', 'Y', 'X', 'Y')) # Create unique combinations combined_factor <- ft_unique_comb(factor_vec1, factor_vec2) levels(combined_factor)# Example factors factor_vec1 <- factor(c('A', 'A', 'B', 'B')) factor_vec2 <- factor(c('X', 'Y', 'X', 'Y')) # Create unique combinations combined_factor <- ft_unique_comb(factor_vec1, factor_vec2) levels(combined_factor)