# Example data frame
my_data <- dummy_data(100)

# Extract text from the left
my_data[["left"]] <- my_data |> sub_string(education, to = 2)

# Extract text from the right
my_data[["right"]] <- my_data |> sub_string(education, from = 2)

# Extract text from the middle
my_data[["middle"]] <- my_data |> sub_string(education, from = 2, to = 3)

# Find text and extract from the left
my_data[["left2"]] <- my_data |> sub_string(education, to = "l")

# Find text and extract from the right
my_data[["right2"]] <- my_data |> sub_string(education, from = "l")

# Find text and extract from the middle
my_data[["middle2"]] <- my_data |> sub_string(education, from = "i", to = "l")

# Resolving macro variable in single character
year <- 2026

text <- macro("The current year is &year")

# You can also combine multiple macro variables
some_variable <- "current"
current2026   <- "The current year is"

text_combi <- macro("&&some_variable&year &year")

# Resolving macro variable in character vector
char_vector <- c("The current year is &year",
                 "The &some_variable year is &year",
                 "&&some_variable&year &year")

text_vector <- apply_macro(char_vector)

# Example data frame
my_data <- dummy_data(1000)

# Get a quick filtered view
my_data |> where.(sex == 1 & age < 25,
                  c(sex, age, household_id, education))

# Example files
csv_file  <- system.file("extdata", "qol_example_data.csv",  package = "qol")
xlsx_file <- system.file("extdata", "qol_example_data.xlsx", package = "qol")

# Import multiple files at once
all_files <- import_multi(c(csv_file, xlsx_file))

# Example data frame list
my_list <- list(first  = dummy_data(10),
                second = dummy_data(10))

# Export multiple data frames into one xlsx file
# with multiple sheets
export_multi(my_list, tempdir())

# Export multiple data frames into multiple xlsx files
export_multi(my_list, tempdir(), into_sheets = FALSE)

# Export multiple data frames into multiple csv files
export_multi(my_list, tempdir(), separator = ";")

# Example formats
age. <- discrete_format(
    "Total"          = 0:100,
    "under 18"       = 0:17,
    "18 to under 25" = 18:24,
    "25 to under 55" = 25:54,
    "55 to under 65" = 55:64,
    "65 and older"   = 65:100)

sex. <- discrete_format(
    "Total"  = 1:2,
    "Male"   = 1,
    "Female" = 2)

sex2. <- discrete_format(
    "Total"  = c("Male", "Female"),
    "Male"   = "Male",
    "Female" = "Female")

income. <- interval_format(
    "Total"              = 0:99999,
    "below 500"          = 0:499,
    "500 to under 1000"  = 500:999,
    "1000 to under 2000" = 1000:1999,
    "2000 and more"      = 2000:99999)

# Example data frame
my_data <- dummy_data(1000)

# Transpose from long to wide and use a multilabel to generate additional categories
long_to_wide <- my_data |>
    transpose_plus(preserve = c(year, age),
                   pivot    = c("sex", "education"),
                   values   = income,
                   formats  = list(sex = sex., age = age.),
                   weight   = weight,
                   na.rm    = TRUE)

# Transpose back from wide to long
wide_to_long <- long_to_wide |>
    transpose_plus(preserve = c(year, age),
                   pivot    = list(sex       = c("Total", "Male", "Female"),
                                   education = c("low", "middle", "high")))

# Nesting variables in long to wide transposition
nested <- my_data |>
    transpose_plus(preserve = c(year, age),
                   pivot    = "sex + education",
                   values   = income,
                   formats  = list(sex = sex., age = age.),
                   weight   = weight,
                   na.rm    = TRUE)

# Or both, nested and un-nested, at the same time
both <- my_data |>
    transpose_plus(preserve = c(year, age),
                   pivot    = c("sex + education", "sex", "education"),
                   values   = income,
                   formats  = list(sex = sex., age = age.),
                   weight   = weight,
                   na.rm    = TRUE)

# Example formats
education. <- discrete_format(
    "1" = "low",
    "2" = "middle",
    "3" = "high")

# Example data frame
my_data <- dummy_data(1000)

# Simple sorting
sort_df1 <- my_data |> sort_plus(by = c(state, sex, age))
sort_df2 <- my_data |> sort_plus(by    = c(state, sex, age),
                                 order = c("ascending", "descending"))

# Character variables will normally be sorted alphabetically. With the help
# of a format this variable can be sorted in a completely different way.
sort_df3 <- my_data |> sort_plus(by      = education,
                                 formats = list(education = education.))

# Preserve the order of the character variable, otherwise it couldn't stay in
# it's current order.
sort_df4 <- sort_df3 |> sort_plus(by       = age,
                                  preserve = education)

set_print(): Set the print option globally for the tabulation and export to Excel functions.

get_print(): Get the globally stored print option.

set_monitor(): Set the monitor option globally for the heavier functions which are able to show how they work internally.

get_monitor(): Get the globally stored monitor option.

set_na.rm(): Set the na.rm option globally for each function which can remove NA values.

get_na.rm(): Get the globally stored na.rm option.

set_print_miss(): Set the print_miss option globally for each function which can display missing categories.

get_print_miss(): Get the globally stored print_miss option.

set_output(): Set the output option globally for each function that can output results to "console", "text", "excel" or "excel_nostyle".

get_output(): Get the globally stored output option.

set_titles(): Set the titles globally for each function that can print titles above the output table.

get_titles(): Get the globally stored titles.

set_footnotes(): Set the footnotes globally for each function that can print footnotes above the output table.

get_footnotes(): Get the globally stored footnotes.

# Example data frame
my_data <- dummy_data(100)

content_report(my_data)

# Example files
csv_file  <- system.file("extdata", "qol_example_data.csv",  package = "qol")
xlsx_file <- system.file("extdata", "qol_example_data.xlsx", package = "qol")

# Import: Provide full file path
my_csv  <- import_data(csv_file)
my_xlsx <- import_data(xlsx_file)

# Import specific regions
range_import <- import_data(xlsx_file, region = "B4:H32")
name_import  <- import_data(xlsx_file, region = "test_region")

# Import from another sheet
sheet_import <- import_data(xlsx_file, sheet = "Sheet 2")

# Example data frame
my_data <- dummy_data(100)

# Example export file paths
export_csv  <- tempfile(fileext = ".csv")
export_xlsx <- tempfile(fileext = ".xlsx")

# Export: Provide full file path
my_data |> export_data(export_csv)
my_data |> export_data(export_xlsx)

# Manual cleanup for example
unlink(c(export_csv, export_xlsx))

Data Work.NewDataSet;
    Set Work.MyData1
        Work.MyData2
        Work.MyData3;
Run;

NewDataSet <- set(MyData1,
                  MyData2,
                  MyData3)

Data Work.MyData_AgeGr;
    Set Work.MyData;

             If       Age < 18 Then AgeGr = 1;
        Else If 18 <= Age < 25 Then AgeGr = 2;
        Else If 25 <= Age < 55 Then AgeGr = 3;
        Else If 55 <= Age < 65 Then AgeGr = 4;
        Else                        AgeGr = 5;

Run;

MyData_AgeGr <- MyData |> 
         if.(Age < 18,             AgeGr = 1) |>
    else_if.(Age >= 18 & Age < 25, AgeGr = 2) |>
    else_if.(Age >= 25 & Age < 55, AgeGr = 3) |>
    else_if.(Age >= 55 & Age < 65, AgeGr = 4) |>
    else.   (                      AgeGr = 5)

Data Work.MyData_Do;
    Set Work.MyData;

        If a < 100 Then Do;

            b = 1;
            c = "Hello";
            d = 42;

        End;

Run;

MyData_Do <- MyData |> 
         if.(a < 100, b = 1,
                      c = "Hello",
                      d = 42)

Data Work.MyData_If;
    Set Work.MyData;

        /* Which means: only keep the observations,
           which are true on the following condition. */
        If Age > 65;

        /* Or you could just do this, which means: only
           keep observations, where weight is not missing. */
        If Weight;

Run;

MyData_If <- MyData |>
    if.(Age > 65) |>
    if.(weight)

Proc Format Library = Work;

    Value AgeGroup
        00 - 17 = 'under 18'
        18 - 24 = '18 to under 25'
        25 - 54 = '25 to under 55'
        55 - 64 = '55 to under 65'
        65 - 99 = '65 and older';

Run;

Data Work.MyData_Recode;
    Set Work.MyData;

        AgeGr = Put(Age, AgeGroup.);

Run;

AgeGroup. <- discrete_format(
    "under 18"       = 0:17,
    "18 to under 25" = 18:24,
    "25 to under 55" = 25:54,
    "55 to under 65" = 55:64,
    "65 and older"   = 65:99)

MyData[["AgeGr"]] <- MyData |> recode(Age = "AgeGroup.")

Data Work.MyData_Retain;
    Set Work.MyData;

        Retain RunningNr 0 CumulativeIncome 0;

        RunningNr        = RunningNr + 1;
        CumulativeIncome = CumulativeIncome + Income;

Run;

MyData[["run_nr"]]           <- MyData |> running_number() |> 
MyData[["CumulativeIncome"]] <- MyData |> retain_sum(values = income)

Data Work.MyData_Value;
    Set Work.MyData;

        Retain MyValue 0;

        If _n_ = 1 Then MyValue = Income;

Run;

MyData[["MyValue"]] <- MyData |> retain_value(values = income)

Data Work.MyData_FirstLast;
    Set Work.MyData;

        By AgeGr;
    
            If First.AgeGr Then FirstCase = 1;
            If Last.AgeGr  Then LastCase  = 1;

Run;

MyData[["FirstCase"]] <- MyData |> mark_case(by = AgeGr)
MyData[["LastCase"]]  <- MyData |> mark_case(by = AgeGr, first = FALSE)

Data Work.MyData_Merged;
    Merge Work.MyData_A (in = a)
          Work.MyData_B (in = b)
          Work.MyData_C;

        By a b c d e;
          
          /* Here are examples of how the different joins can be selected,
             making use of the above assigned in-variables. */
          If a;             /* left join */
          If b;             /* right join */
          If a And b;       /* inner join */
          If Not (a And b); /* outer join */
          If a and Not b;   /* left inner join */
          If Not a And b;   /* right inner join */
                            /* full join happens if no selection is specified */

Run;

MyData_Merged <- multi_join(data_frames = list(MyData_A, MyData_B, MyData_C),
                            on  = c("a", "b", "c", "d", "e")
                            how = "left")

# Instead of "left" you can assign any of the above join methods.
# To join on differently named variables, you can write the function like this:

MyData_Merged <- multi_join(list(MyData_A, MyData_B, MyData_C),
                            on = list(MyData_A = c("a", "b"),
                                      MyData_B = c("var1", "var2"),
                                      MyData_C = c("key1", "key2")))

Data Work.MyData_Male
     Work.MyData_Female;
    Set Work.MyData;

             If Sex = 1 Then Output Work.MyData_Male;
        Else If Sex = 2 Then Output Work.MyData_Female;

Run;

# Using just the expressions of a single variable
MyData_List <- MyData |> split_by(Sex)

# Or using conditions
MyData_List <- MyData |> split_by(Sex == 1 & Age <  18,
                                  Sex == 2 & Age >= 18)

Data Work.MyData_KeepDrop;
    Set Work.MyData;

        Keep a b c d;
        Drop a b c d;

        /* When you have to keep or drop many variables you can also define a range */
        Keep start_var -- end_var; /* Keep every variable between the two given ones (including them) */
        Drop start_var -- end_var; /* Drop every variable between the two given ones (including them) */

        /* You can also keep or drop variables based on what characters they start with */
        Keep var:; /* Keep every variable starting with "var" */
        Drop var:; /* Drop every variable starting with "var" */

Run;

MyData_KeepDrop <- MyData |> keep(a, b, c, d)
MyData_KeepDrop <- MyData |> dropp(a, b, c, d)

# Ranges can be used like this
MyData_KeepDrop <- MyData |> keep(start_var:end_var)
MyData_KeepDrop <- MyData |> dropp(start_var:end_var)

# The R version not only provides the option to select variables "starting with"
# certain characters but also "ending with" and "containing". The colon ":" acts
# as a placeholder.
MyData_KeepDrop <- MyData |> keep("var:")  # Start with
MyData_KeepDrop <- MyData |> keep(":var")  # End with
MyData_KeepDrop <- MyData |> keep(":var:") # Contains

MyData_KeepDrop <- MyData |> dropp("var:")  # Start with
MyData_KeepDrop <- MyData |> dropp(":var")  # End with
MyData_KeepDrop <- MyData |> dropp(":var:") # Contains

Proc Freq Data = Work.MyData;

    Table Age;

Run;

# You can just output a quick ASCII style table in the console
MyData |> frequencies(Age)

# Or a fully styled Excel table like this
MyData |> frequencies(Age, output = "excel")

Proc Freq Data = Work.MyData;

    Table Age * Sex;

Run;

# Again in ASCII style
MyData |> crosstabs(Age, Sex)

# Or in the fully styled Excel version
MyData |> crosstabs(Age, Sex, output = "excel")

# By the way: if you want to produce multiple structurally identical tables
# by the expressions of another variable, you can do so like this:
MyData |> frequencies(Age, by = Education)
MyData |> crosstabs(Age, Sex, by = Education)

Proc Format Library = Work;

    Value AgeGroup
        00 - 17 = 'under 18'
        18 - 24 = '18 to under 25'
        25 - 54 = '25 to under 55'
        55 - 64 = '55 to under 65'
        65 - 99 = '65 and older';

Run;

Title1    "This is a title";
Footnote1 "This is a footnote";
        
Proc Freq Data = Work.MyData;

    Table Age;
        
    Format Age AgeGroup.;

Run;

AgeGroup. <- discrete_format(
    "under 18"       = 0:17,
    "18 to under 25" = 18:24,
    "25 to under 55" = 25:54,
    "55 to under 65" = 55:64,
    "65 and older"   = 65:99)

MyData |> frequencies(Age,
                      formats   = list(Age = AgeGroup.),
                      titles    = "This is a title",
                      footnotes = "This is a footnote")

Proc Export Data = Work.MyData;

    Outfile = "C:\MyFile.xlsx";
    DBMS = xlsx;

Run;

MyData |> export_with_style(titles    = "This is a title",
                            footnotes = "This is a footnote",
                            style     = excel_output_style(header_back_color = "0000FF",
                                                           header_font_color = "FF0000",
                                                           font              = "Times New Roman",
                                                           title_font_size   = 20))

MyData <- wb_to_df(file  = "C:/MyFile.xlsx",
                   sheet = 1,
                   named_region = "data")

/* For CVS */
Proc Import

    Datafile = "C:\MyFile.csv"
    Out      = Work.MyData
    DBMS     = csv;

Run;

/* For XLSX */
Proc Import

    Datafile = "C:\MyFile.xlsx"
    Out      = Work.MyData
    DBMS     = xlsx;

Run;

csv_file  <- import_data("C:\MyFile.csv")
xlsx_file <- import_data("C:\MyFile.xlsx")

/* For CVS */
Proc Contents Data = Work.MyData;
Run;

MyData |> content_report()

/* Long to wide */
Proc Transpose Data = Work.Long
                Out = Work.Wide;

    By Age;

    Var Income;

    ID Sex;

Run;

/* Wide to long */
Proc Transpose Data = Work.Wide
                Out = Work.Long (Rename = (_NAME_ = Sex));

    By Age;

    Var Male Female;

Run;

# Wide to long
wide <- long |>
    transpose_plus(preserve = age,
                   pivot    = "sex",
                   values   = income)

# Long to wide
long <- wide |>
    transpose_plus(preserve = age,
                   pivot    = list(sex = c("Male", "Female")))

%Let year = 2026;

Title1 "The current year is &year";

year <- 2026

set_titles("The current year is &year")

Proc Format;

    Value Sex (Multilabel Notsorted)
        1,2 = 'Total'
          1 = 'Male'
          2 = 'Female';
          
    Value Age (Multilabel Notsorted)
        00 - 99 = 'Total'
        00 - 02 = 'under 3'
        00 - 05 = 'under 6'
        00 - 11 = 'under 12'
        00 - 17 = 'under 18'
        18 - 24 = '18 to under 25'
        25 - 54 = '25 to under 55'
        55 - 64 = '55 to under 65'
        65 - 99 = '65 and older'
        80 - 99 = '80 and older';

Run;

sex. <- discrete_format(
    "Total"  = 1:2,
    "Male"   = 1,
    "Female" = 2)
    
age. <- discrete_format(
    "Total"          = 0:99,
    "under 3"        = 0:2,
    "under 6"        = 0:5,
    "under 12"       = 0:11,
    "under 18"       = 0:17,
    "18 to under 25" = 18:24,
    "25 to under 55" = 25:54,
    "55 to under 65" = 55:64,
    "65 and older"   = 65:99,
    "80 and older"   = 80:99)

Proc Summary Data = Work.My_Data;

    Class Year;
    Class Sex Age /Order = Data Mlf Preloadfmt Missing;

    Var Weight;

    Format Sex Sex. Age Age.;

    Output Out  = Work.My_Data_Agg
           Sum  =
           Mean =;

Run;

my_data_agg <- my_data |>
    summarise_plus(class      = c(year, sex, age),
                   values     = weight,
                   statistics = c("sum", "mean", "freq"),
                   formats    = list(sex = sex.,
                                     age = age.),
                   nesting    = "all",
                   na.rm      = TRUE)

Proc Tabulate Data = Work.Armut;

    Class Year;
    Class Sex Age /Order = Data Mlf Preloadfmt;

    Var Weight;

    Table /* Rows */
          Sex = ''
          Sex = '' * Alter = '',

          /* Columns */
          Year = 'Percentage based on sex' * Weight = '' * PctSum<sex> = '%'
          Year = 'Population (weighted)'   * Weight = '' * Sum = '1000'
          Year = 'Unweighted'              * Weight = '' * N = 'Count'
          /Box = 'Variable';

    Format Sex Sex. Age Age.;

Run;

my_data |> any_table(rows       = c("sex", "sex + age"),
                     columns    = "year",
                     values     = weight,
                     statistics = c("pct_group", "sum", "freq"),
                     pct_group  = "sex",
                     formats    = list(sex = sex.,
                                       age = age.),
                     na.rm      = TRUE)

# Let's try it with the single states of Germany, Germany as a whole
# and eastern and western states.
state. <- discrete_format(
    "Germany"                       = 1:16,
    "Schleswig-Holstein"            = 1,
    "Hamburg"                       = 2,
    "Lower Saxony"                  = 3,
    "Bremen"                        = 4,
    "North Rhine-Westphalia"        = 5,
    "Hesse"                         = 6,
    "Rhineland-Palatinate"          = 7,
    "Baden-Württemberg"             = 8,
    "Bavaria"                       = 9,
    "Saarland"                      = 10,
    "West"                          = 1:10,
    "Berlin"                        = 11,
    "Brandenburg"                   = 12,
    "Mecklenburg-Western Pomerania" = 13,
    "Saxony"                        = 14,
    "Saxony-Anhalt"                 = 15,
    "Thuringia"                     = 16,
    "East"                          = 11:16)

# Now produce the same table as above for every expression of the format above.
# See the difference? There is nothing more to it.
my_data |> any_table(rows       = c("sex", "sex + age"),
                     columns    = "year",
                     by         = state,
                     values     = weight,
                     statistics = c("pct_group", "sum", "freq"),
                     pct_group  = "sex",
                     formats    = list(sex   = sex.,
                                       age   = age.,
                                       state = state.),
                     na.rm      = TRUE)

# Want a blue header color? Sure.
my_style <- excel_output_style(header_back_color = "0000FF")

# But with red font color? No problem.
my_style <- my_style |> modify_output_style(header_font_color = "FF0000")

# Another font and individual column width? Why not.
my_style <- my_style |> modify_output_style(font         = "Times New Roman",
                                            column_width = c(20, 12, 15, 9))

# Change the font size for the titles and remove borders around the row header? Absolutely.
my_style <- my_style |> modify_output_style(title_font_size = 20,
                                            cat_col_borders = FALSE)
                                            
# Now let's integrate this new style
my_data |> any_table(rows       = c("sex", "sex + age"),
                     columns    = "year",
                     by         = state,
                     values     = weight,
                     statistics = c("pct_group", "sum", "freq"),
                     pct_group  = "sex",
                     formats    = list(sex   = sex.,
                                       age   = age.,
                                       state = state.),
                     style      = my_style,
                     na.rm      = TRUE)
                     
# Done.

# Official release
install.packages("qol")

# Development version
devtools::install_github("s3rdia/qol")

install.packages('qol', repos = c('https://s3rdia.r-universe.dev', 'https://cloud.r-project.org'))

pak::pak("s3rdia/qol")

# Creating format containers
age. <- discrete_format(
    "Total"          = 0:100,
    "under 18"       = 0:17,
    "18 to under 25" = 18:24,
    "25 to under 55" = 25:54,
    "55 to under 65" = 55:64,
    "65 and older"   = 65:100)

sex. <- discrete_format(
    "Total"  = 1:2,
    "Male"   = 1,
    "Female" = 2)

library(qol)

# If you want to test the raw speed in combination with creating big outputs try this:
# Lets crank up the observations to 10 Millions
my_data <- dummy_data(10000000)

# Create format containers
age. <- discrete_format(
    "Total"          = 0:100,
    "under 18"       = 0:17,
    "18 to under 25" = 18:24,
    "25 to under 55" = 25:54,
    "55 to under 65" = 55:64,
    "65 and older"   = 65:100)

sex. <- discrete_format(
    "Total"  = 1:2,
    "Male"   = 1,
    "Female" = 2)

education. <- discrete_format(
    "Total"            = c("low", "middle", "high"),
    "low education"    = "low",
    "middle education" = "middle",
    "high education"   = "high")
    
# And now let's take a second and see what massive outputs we can get in no time
summary_df <- my_data |>
    summarise_plus(class      = c(year, sex, age, education),
                   values     = c(income, probability, weight),
                   statistics = c("freq", "sum", "sum_wgt", "pct_group", "pct_total", "missing"),
                   formats    = list(age = age.,
                                     sex = sex.,
                                     education = education.),
                   weight     = "weight",
                   nesting    = "all",
                   notes      = FALSE)

my_data <- dummy_data(100000)

# Create format containers
age. <- discrete_format(
    "Total"          = 0:100,
    "under 18"       = 0:17,
    "18 to under 25" = 18:24,
    "25 to under 55" = 25:54,
    "55 to under 65" = 55:64,
    "65 and older"   = 65:100)

sex. <- discrete_format(
    "Total"  = 1:2,
    "Male"   = 1,
    "Female" = 2)

education. <- discrete_format(
    "Total"            = c("low", "middle", "high"),
    "low education"    = "low",
    "middle education" = "middle",
    "high education"   = "high")
    
# Define style
set_style_options(column_widths = c(2, 15, 15, 15, 9))

# Define titles and footnotes. If you want to add hyperlinks you can do so by
# adding "link:" followed by the hyperlink to the main text.
set_titles("This is title number 1 link: https://cran.r-project.org/",
           "This is title number 2",
           "This is title number 3")

set_footnotes("This is footnote number 1",
              "This is footnote number 2",
              "This is footnote number 3 link: https://cran.r-project.org/")

# Output complex tables with different percentages
my_data |> any_table(rows       = c("sex + age", "sex", "age"),
                     columns    = c("year", "education + year"),
                     values     = weight,
                     statistics = c("sum", "pct_group"),
                     pct_group  = c("sex", "age"),
                     formats    = list(sex = sex., age = age.,
                                       education = education.),
                     na.rm      = TRUE)

reset_style_options()
reset_qol_options()

# Set output and style options globally
set_style_options(save_path  = "C:/My_folder/",
                  file       = "My_workbook.xlsx",
                  sheet_name = "age_sex")

# Capture the output of any_table() to get a list which contains the data frame
# as well as the formatted workbook.
# Note: Set print to FALSE to prevent the workbook from being saved to early.
result_list <- my_data |>
           any_table(rows       = c("age"),
                     columns    = c("sex"),
                     values     = weight,
                     statistics = c("sum"),
                     formats    = list(sex = sex., age = age.),
                     na.rm      = TRUE,
                     print      = FALSE)

# Set a new sheet name for the next table
set_style_options(sheet_name = "edu_year")

# Pass on the workbook from before to the next any_table()
# print is now TRUE so the workbook will be saved.
my_data |> any_table(workbook   = result_list[["workbook"]],
                     rows       = c("education"),
                     columns    = c("year"),
                     values     = weight,
                     statistics = c("pct_group"),
                     formats    = list(education = education.),
                     na.rm      = TRUE)
                     
# For safety set file back to NULL at the end. Otherwise the next any_table() will overwrite
# the existing file.
close_file()

# Set output and style options globally
set_style_options(sheet_name = "age_sex")

# Catch the output as shown before, but additionally use the option -> output = "excel_nostyle".
# This skips the styling part, so that the function runs faster. The styling is done later on.
tab1 <- my_data |>
       any_table(rows       = c("age"),
                 columns    = c("sex"),
                 values     = weight,
                 statistics = c("sum"),
                 formats    = list(sex = sex., age = age.),
                 na.rm      = TRUE,
                 print      = FALSE,
                 output     = "excel_nostyle")

# Now let's asume you create a bunch of different tables
my_style <- my_style |> set_style_options(sheet_name = "sheet2")
tab2     <- my_data  |> any_table(..., print = FALSE, output = "excel_nostyle")

my_style <- my_style |> set_style_options(sheet_name = "sheet3")
tab3     <- my_data  |> any_table(..., print = FALSE, output = "excel_nostyle")

my_style <- my_style |> set_style_options(sheet_name = "sheet4")
tab4     <- my_data  |> any_table(..., print = FALSE, output = "excel_nostyle")

...

# Every of the above tabs is a list, which contains the data table, an unstyled workbook and the meta
# information needed for the individual styling. These tabs can be input into the following function,
# which reads the meta information, styles each table individually and combines them as separate sheets
# into a single workbook.
combine_into_workbook(tab1, tab2, tab3, tab4, tab5, tab6, tab7, tab8,
                      file = "C:/My_folder/My_workbook.xlsx")

# Simple join
df1 <- data.frame(key = c(1, 1, 1, 2, 2, 2),
                  a   = c("a", "a", "a", "a", "a", "a"))

df2 <- data.frame(key = c(2, 3),
                  b   = c("b", "b"))

left_joined <- multi_join(list(df1, df2), on = "key")

# Joining more than two data frames on different variable names with different methods
df1b <- data.frame(key1 = c(1, 1, 1, 2, 2, 2),
                   key2 = c("a", "a", "a", "a", "a", "a"),
                   a    = c("a", "a", "a", "a", "a", "a"))

df2b <- data.frame(var1 = c(1, 2),
                   var2 = c("a", "a"),
                   c    = c("c", "c"))

df3b <- data.frame(any  = c(2, 3),
                   name = c("a", "a"),
                   b    = c("b", "b"))

multiple_joined3 <- multi_join(list(df1b, df2b, df3b),
                               on = list(df1b = c("key1", "key2"),
                                         df2b = c("var1", "var2"),
                                         df3b = c("any", "name")),
                               how = c("left", "right"))

# Transpose from long to wide and use a multilabel to generate additional categories
long_to_wide <- my_data |>
    transpose_plus(preserve = c(year, age),
                   pivot    = c("sex + education", "sex", "education"),
                   values   = income,
                   formats  = list(sex = sex., age = age.),
                   weight   = weight,
                   na.rm    = TRUE)

# Transpose back from wide to long
wide_to_long <- long_to_wide |>
    transpose_plus(preserve = c(year, age),
                   pivot    = list(sex       = c("Total", "Male", "Female"),
                                   education = c("low", "middle", "high")))

education. <- discrete_format(
    "1" = "low",
    "2" = "middle",
    "3" = "high")

# Simple sorting
sort_df1 <- my_data |> sort_plus(by = c(state, sex, age))
sort_df2 <- my_data |> sort_plus(by    = c(state, sex, age),
                                 order = c("ascending", "descending"))

# Character variables will normally be sorted alphabetically. With the help
# of a format this variable can be sorted in a completely different way.
sort_df3 <- my_data |> sort_plus(by      = education,
                                 formats = list(education = education.))

# Preserve the order of the character variable, otherwise it couldn't stay in
# it's current order.
sort_df4 <- sort_df3 |> sort_plus(by       = age,
                                  preserve = education)

# Example data frame
my_data <- dummy_data(1000)

# Call function
new_df <- my_data |>
         if.(age < 18,             age_group = "under 18") |>
    else_if.(age >= 18 & age < 65, age_group = "18 to under 65") |>
    else.   (                      age_group = "65 and older")

# Or with multiple variables
new_df <- my_data |>
         if.(age < 18,             age_group = "under 18"      , age_num = 1L) |>
    else_if.(age >= 18 & age < 65, age_group = "18 to under 65", age_num = 2L) |>
    else.   (                      age_group = "65 and older",   age_num = 3L)

# NOTE: As in other languages the following if blocks won't produce the same result.
#       if.() will overwrite existing values while else_if.() will not.
state_df <- my_data |>
         if.(state == 1, state_a = "State 1") |>
    else_if.(state < 11, state_a = "West") |>
    else.   (            state_a = "East")

state_df <- state_df |>
      if.(state == 1, state_b = "State 1") |>
      if.(state < 11, state_b = "West") |>
    else.(            state_b = "East")
    
# Use if.() as a do-over-loop. In this kind of loop all vectors will be
# advanced one iteration at a time in parallel.
money    <- c("income", "expenses", "balance", "probability")
new_vars <- c("var1", "var2", "var3", "var4")
result   <- c(1, 2, 3, 4)

do_over_df <- my_data |>
      if.(money > 0, new_vars = result) |>
    else.(           new_vars = 0)
    
# All these functions can be used in a do_if() situation and are aware of
# overarching conditions.
do_if_df <- my_data |>
    do_if(state < 11) |>
          if.(age < 18, age_cat = 1) |>
        else.(          age_cat = 2) |>
    else_do() |>
          if.(age < 18, age_cat = 3) |>
        else.(          age_cat = 4) |>
    end_do()