Count summary for a Binary Row

Description

Summarizes a binary row using counts.

Usage

binary_count(dt, ...)

Arguments

Details

This is an internal function of tangram.pipe. Additional arguments should be supplied for this function to work properly.

reference : the name of the row category to use as the reference. Default will use alphabetical first category

ref.label : choice of whether you want the reference label to be in the table. Default is on and includes reference label; off switches it off.

rowlabel : the label for the table row name, if different from row_var.

compact : if TRUE, data displayed in one row.

missing : if TRUE, missing data is considered; FALSE only uses complete cases.

digits : significant digits to use.

Value

A dataframe with summary statistics for a binary variable.

See Also

Possible summary functions for binary data:binary_default, binary_pct, binary_jama

Default summary for a Binary Row

Description

Summarizes a binary row using counts and column proportions.

Usage

binary_default(dt, ...)

Arguments

Details

This is an internal function of tangram.pipe. Additional arguments should be supplied for this function to work properly.

reference : the name of the row category to use as the reference. Default will use alphabetical first category

ref.label : choice of whether you want the reference label to be in the table. Default is on and includes reference label; off switches it off.

rowlabel : the label for the table row name, if different from row_var.

compact : if TRUE, data displayed in one row.

missing : if TRUE, missing data is considered; FALSE only uses complete cases.

digits : significant digits to use.

Value

A dataframe with summary statistics for a binary variable.

See Also

Additional prewritten summary functions for binary data: binary_pct, binary_count, binary_jama

Binary Difference in Proportions

Description

Default comparison function for binary data.

Usage

binary_diff(dt, num_col, reference, digits)

Arguments

Value

A dataframe with difference in proportions test results between pairs of columns for binary data, as well as an overall chi-squared test across all groups.

JAMA-style summary for a Binary Row

Description

Summarizes a binary row using column percentages and the total number in each cell divided by the column total. This is the style used by the Journal of the American Medical Association.

Usage

binary_jama(dt, ...)

Arguments

Details

This is an internal function of tangram.pipe. Additional arguments should be supplied for this function to work properly.

reference : the name of the row category to use as the reference. Default will use alphabetical first category

ref.label : choice of whether you want the reference label to be in the table. Default is on and includes reference label; off switches it off.

rowlabel : the label for the table row name, if different from row_var.

compact : if TRUE, data displayed in one row.

missing : if TRUE, missing data is considered; FALSE only uses complete cases.

digits : significant digits to use.

Value

A dataframe with summary statistics for a binary variable.

See Also

Possible summary functions for binary data:binary_default, binary_pct, binary_count

Binary Odds Ratio

Description

Calculates odds ratio across categories for binary data.

Usage

binary_or(dt, num_col, reference, digits)

Arguments

Value

A dataframe with computed odds ratios between pairs of columns for binary data, as well as an overall chi-squared test across all groups.

Percentage summary for a Binary Row

Description

Summarizes a binary row using counts and column percentages.

Usage

binary_pct(dt, ...)

Arguments

Details

This is an internal function of tangram.pipe. Additional arguments should be supplied for this function to work properly.

reference : the name of the row category to use as the reference. Default will use alphabetical first category

ref.label : choice of whether you want the reference label to be in the table. Default is on and includes reference label; off switches it off.

rowlabel : the label for the table row name, if different from row_var.

compact : if TRUE, data displayed in one row.

missing : if TRUE, missing data is considered; FALSE only uses complete cases.

digits : significant digits to use.

Value

A dataframe with summary statistics for a binary variable.

See Also

Possible summary functions for binary data:binary_default, binary_count, binary_jama

Binary Row

Description

Adds in a binary row to a tangram.pipe table.

Usage

binary_row(
  list_obj,
  row_var,
  col_var = NULL,
  newdata = FALSE,
  ref.label = "on",
  rowlabel = NULL,
  summary = NULL,
  reference = NULL,
  compact = TRUE,
  missing = NULL,
  overall = NULL,
  comparison = NULL,
  digits = NULL,
  indent = 5
)

Arguments

Value

A list with the binary row's table information added as a new element to list_obj.

See Also

Possible summary functions for binary data:binary_default, binary_pct, binary_count, binary_jama

Other related row-building functions: num_row, cat_row, n_row, empty_row

Starting a tangram.pipe table: tbl_start

Examples

iris$color <- sample(c("Blue", "Purple"), size=150, replace=TRUE)
x <- tbl_start(iris, "Species", missing=TRUE, overall=TRUE, comparison=TRUE) %>%
  binary_row("color", rowlabel="Color")

Binary Risk Ratio

Description

Calculates risk ratio across categories for binary data.

Usage

binary_rr(dt, num_col, reference, digits)

Arguments

Value

A dataframe with computed risk ratios between pairs of columns for binary data, as well as an overall chi-squared test across all groups.

Chi-Squared Test for Categorical Variables

Description

Default comparison function for categorical data.

Usage

cat_comp_default(dt, digits)

Arguments

Value

A dataframe calculating relative entropy between column pairs, as well as an overall chi-squared test across all groups.

Count summary for a Categorical Row

Description

Summarizes a categorical row using counts.

Usage

cat_count(dt, ...)

Arguments

Details

This is an internal function of tangram.pipe. Additional arguments should be supplied for this function to work properly.

rowlabel : the label for the table row name, if different from row_var.

missing : if TRUE, missing data is considered; FALSE only uses complete cases.

ordering : Sorts the row variable: options are "ascending" or "descending"

sortvar : Column to sort row on. Requires ordering to be ascending or descending. By default, will sort based on overall statistics.

digits : significant digits to use.

Value

A dataframe with summary statistics for a categorical variable.

See Also

Additional prewritten summary functions for categorical data: cat_default, cat_pct, cat_jama

Default summary for a Categorical Row

Description

Summarizes a categorical row using counts and column proportions.

Usage

cat_default(dt, ...)

Arguments

Details

This is an internal function of tangram.pipe. Additional arguments should be supplied for this function to work properly.

rowlabel : the label for the table row name, if different from row_var.

missing : if TRUE, missing data is considered; FALSE only uses complete cases.

ordering : Sorts the row variable: options are "ascending" or "descending"

sortvar : Column to sort row on. Requires ordering to be ascending or descending. By default, will sort based on overall statistics.

digits : significant digits to use.

Value

A dataframe with summary statistics for a categorical variable.

See Also

Additional prewritten summary functions for categorical data: cat_pct, cat_count, cat_jama

JAMA-style summary for a Categorical Row

Description

Summarizes a categorical row using column percentages and the total number in each cell divided by the column total. This is the style used by the Journal of the American Medical Association.

Usage

cat_jama(dt, ...)

Arguments

Details

This is an internal function of tangram.pipe. Additional arguments should be supplied for this function to work properly.

rowlabel : the label for the table row name, if different from row_var.

missing : if TRUE, missing data is considered; FALSE only uses complete cases.

ordering : Sorts the row variable: options are "ascending" or "descending"

sortvar : Column to sort row on. Requires ordering to be ascending or descending. By default, will sort based on overall statistics.

digits : significant digits to use.

Value

A dataframe with summary statistics for a categorical variable.

See Also

Additional prewritten summary functions for categorical data: cat_default, cat_pct, cat_count

Percentage summary for a Categorical Row

Description

Summarizes a categorical row using counts and column percentages.

Usage

cat_pct(dt, ...)

Arguments

Details

This is an internal function of tangram.pipe. Additional arguments should be supplied for this function to work properly.

rowlabel : the label for the table row name, if different from row_var.

missing : if TRUE, missing data is considered; FALSE only uses complete cases.

ordering : Sorts the row variable: options are "ascending" or "descending"

sortvar : Column to sort row on. Requires ordering to be ascending or descending. By default, will sort based on overall statistics.

digits : significant digits to use.

Value

A dataframe with summary statistics for a categorical variable.

See Also

Additional prewritten summary functions for categorical data: cat_default, cat_count, cat_jama

Categorical Row

Description

Adds in a categorical row to a tangram.pipe table.

Usage

cat_row(
  list_obj,
  row_var,
  col_var = NULL,
  newdata = FALSE,
  rowlabel = NULL,
  summary = NULL,
  missing = NULL,
  overall = NULL,
  comparison = NULL,
  digits = NULL,
  ordering = "none",
  sortcol = NULL,
  indent = 5
)

Arguments

Value

A list with the categorical row's table information added as a new element to list_obj.

See Also

Possible summary functions for categorical data:cat_default, cat_pct, cat_count, cat_jama

Other related row-building functions: num_row, binary_row, n_row, empty_row

Starting a tangram.pipe table: tbl_start

Examples

iris$Stem.Size <- sample(c("Small", "Medium", "Medium", "Large"), size=150, replace=TRUE)
x <- tbl_start(iris, "Species", missing=TRUE, overall=TRUE, comparison=TRUE) %>%
  cat_row("Stem.Size", rowlabel="Stem Size")

Empty Row

Description

Produces a empty dividing row in a tangram.pipe table. May have a row header.

Usage

empty_row(list_obj, header = NULL)

Arguments

Value

If a header is included, a list object is returned with a one-element dataframe containing the header as the most recent entry to list_obj. Otherwise, a list is returned containing a blank character as the last element of list_obj.

See Also

Other related row-building functions: num_row, cat_row, binary_row, n_row

Starting a tangram.pipe table: tbl_start

Row counter

Description

Counts the instances of each column variable of the dataframe to be used in a tangram.pipe table (if applicable), and gives an overall row count.

Usage

n_row(
  list_obj,
  col_var = NULL,
  newdata = FALSE,
  missing = NULL,
  overall = NULL
)

Arguments

Value

A list with the row counts added as a new element to list_obj.

See Also

Other related row-building functions: num_row, cat_row, binary_row, empty_row

Starting a tangram.pipe table: tbl_start

Examples

x <- tbl_start(iris, "Species", missing=TRUE, overall=TRUE, comparison=TRUE) %>%
  n_row()

Date summary for a Numeric Row

Description

Summarizes a numeric row using the five-number summary for a date object.

Usage

num_date(dt, ...)

Arguments

Details

This is an internal function of tangram.pipe. Additional arguments should be supplied for this function to work properly.

rowlabel : the label for the table row name, if different from row_var.

missing : if TRUE, missing data is considered; FALSE only uses complete cases.

Value

A dataframe with summary statistics for a numeric variable.

See Also

Additional prewritten summary functions for numeric data: num_default, num_mean_sd, num_medianiqr, num_minmax

Default summary for a Numeric Row

Description

Summarizes a numeric row using the five-number summary, mean, and standard deviation.

Usage

num_default(dt, ...)

Arguments

Details

This is an internal function of tangram.pipe. Additional arguments should be supplied for this function to work properly.

rowlabel : the label for the table row name, if different from row_var.

missing : if TRUE, missing data is considered; FALSE only uses complete cases.

digits : significant digits to use.

Value

A dataframe with summary statistics for a numeric variable.

See Also

Additional prewritten summary functions for numeric data: num_mean_sd, num_medianiqr, num_minmax, num_date

Numeric Difference in Means

Description

Default comparison function for numeric data.

Usage

num_diff(dt, num_col, row_var, digits)

Arguments

Value

A dataframe calculating the difference in means between column pairs, as well as an overall one-way ANOVA across all groups.

Mean/SD summary for a Numeric Row

Description

Summarizes a numeric row using the mean and standard deviation.

Usage

num_mean_sd(dt, ...)

Arguments

Details

This is an internal function of tangram.pipe. Additional arguments should be supplied for this function to work properly.

rowlabel : the label for the table row name, if different from row_var.

missing : if TRUE, missing data is considered; FALSE only uses complete cases.

digits : significant digits to use.

Value

A dataframe with summary statistics for a numeric variable.

See Also

Additional prewritten summary functions for numeric data: num_default, num_medianiqr, num_minmax, num_date

Median/IQR summary for a Numeric Row

Description

Summarizes a numeric row using the median and interquartile range.

Usage

num_medianiqr(dt, ...)

Arguments

Details

This is an internal function of tangram.pipe. Additional arguments should be supplied for this function to work properly.

rowlabel : the label for the table row name, if different from row_var.

missing : if TRUE, missing data is considered; FALSE only uses complete cases.

digits : significant digits to use.

Value

A dataframe with summary statistics for a numeric variable.

See Also

Additional prewritten summary functions for numeric data: num_default, num_mean_sd, num_minmax, num_date

Min-Max summary for a Numeric Row

Description

Summarizes a numeric row using the minimum and maximum values.

Usage

num_minmax(dt, ...)

Arguments

Details

This is an internal function of tangram.pipe. Additional arguments should be supplied for this function to work properly.

rowlabel : the label for the table row name, if different from row_var.

missing : if TRUE, missing data is considered; FALSE only uses complete cases.

digits : significant digits to use.

Value

A dataframe with summary statistics for a numeric variable.

See Also

Additional prewritten summary functions for numeric data: num_default, num_mean_sd, num_medianiqr, num_date

Numeric Row

Description

Adds in a numeric row to a tangram.pipe table.

Usage

num_row(
  list_obj,
  row_var,
  col_var = NULL,
  newdata = FALSE,
  rowlabel = NULL,
  summary = NULL,
  missing = NULL,
  overall = NULL,
  comparison = NULL,
  digits = NULL
)

Arguments

Value

A list with the numeric row's table information added as a new element to list_obj.

See Also

Possible summary functions for numeric data: num_default, num_mean_sd, num_medianiqr, num_minmax, num_date

Other related row-building functions: cat_row, binary_row, n_row, empty_row

Starting a tangram.pipe table: tbl_start

Examples

x <- tbl_start(iris, "Species", missing=TRUE, overall=TRUE, comparison=TRUE) %>%
  num_row("Sepal.Length", rowlabel="Sepal Length")

Printing a Table

Description

Prints a finished table created from tangram.pipe.

Usage

## S3 method for class 'tangram.pipe'
print(x, ...)

Arguments

Value

A dataframe object containing the information from the last element of a tangram.pipe class object created using tbl_out(). This is the finalized table object.

Examples

iris$color <- sample(c("Blue", "Purple"), size=150, replace=TRUE)
iris$Stem.Size <- sample(c("Small", "Medium", "Medium", "Large"), size=150, replace=TRUE)
iris$Leaf.Color <- "Green"
x <- tbl_start(iris, "Species", missing=TRUE, overall=TRUE, comparison=TRUE) %>%
  num_row("Sepal.Length", rowlabel="Sepal Length") %>%
  empty_row() %>%
  num_row("Sepal.Width", rowlabel="Sepal Width") %>%
  empty_row() %>%
  num_row("Petal.Length", rowlabel="Petal Length") %>%
  empty_row() %>%
  num_row("Petal.Width", rowlabel="Petal Width") %>%
  empty_row() %>%
  cat_row("Stem.Size", rowlabel="Stem Size") %>%
  empty_row() %>%
  binary_row("color", rowlabel="Color") %>%
  tbl_out() %>%
  print()

Tangram Styling

Description

Used to preprocess a tangram.pipe table for HTML formatting.

Usage

tangram_styling(df)

Arguments

Value

A dataframe containing HTML formatting code where applicable.

Output Table

Description

Produces a finalized tangram.pipe table.

Usage

tbl_out(list_obj)

Arguments

Value

A tangram.pipe class object with the finalized table as a dataframe added as the most recent element of list_obj.

Examples

iris$color <- sample(c("Blue", "Purple"), size=150, replace=TRUE)
iris$Stem.Size <- sample(c("Small", "Medium", "Medium", "Large"), size=150, replace=TRUE)
iris$Leaf.Color <- "Green"
x <- tbl_start(iris, "Species", missing=TRUE, overall=TRUE, comparison=TRUE) %>%
  num_row("Sepal.Length", rowlabel="Sepal Length") %>%
  empty_row() %>%
  num_row("Sepal.Width", rowlabel="Sepal Width") %>%
  empty_row() %>%
  num_row("Petal.Length", rowlabel="Petal Length") %>%
  empty_row() %>%
  num_row("Petal.Width", rowlabel="Petal Width") %>%
  empty_row() %>%
  cat_row("Stem.Size", rowlabel="Stem Size") %>%
  empty_row() %>%
  binary_row("color", rowlabel="Color") %>%
  tbl_out()

Table Initialization

Description

Initializes a tangram.pipe table by specifying the desired elements and data components.

Usage

tbl_start(
  data,
  col_var,
  missing = FALSE,
  overall = TRUE,
  comparison = FALSE,
  digits = 2,
  default_num_summary = num_default,
  default_cat_summary = cat_default,
  default_binary_summary = binary_default
)

Arguments

Value

A list containing separate entries holding information provided in the function's arguments, as well as a calculated number of column categories to include for the initialized table.

Examples

x <- tbl_start(iris, "Species", missing=TRUE, overall=TRUE, comparison=TRUE)