| Type: | Package |
| Title: | Tidy Statistical Summaries for Exploratory Data Analysis |
| Version: | 0.1.0 |
| Description: | Provides a tidy set of functions for summarising data, including descriptive statistics, frequency tables with normality testing, and group-wise significance testing. Designed for fast, readable, and easy exploration of both numeric and categorical data. |
| Maintainer: | Kleanthis Koupidis <kleanthis.koupidis@gmail.com> |
| URL: | https://github.com/kleanthisk10/tidySummaries |
| BugReports: | https://github.com/kleanthisk10/tidySummaries/issues |
| License: | MIT + file LICENSE |
| Encoding: | UTF-8 |
| Depends: | R (≥ 4.1.0) |
| Imports: | magrittr, tidyr, dplyr, tibble, purrr, stats, crayon, rlang |
| RoxygenNote: | 7.3.2 |
| Suggests: | ggplot2, testthat, knitr, rmarkdown |
| NeedsCompilation: | no |
| Packaged: | 2025-05-01 19:58:17 UTC; Akis |
| Author: | Kleanthis Koupidis [aut, cre], Nikolaos Koupidis [aut] |
| Repository: | CRAN |
| Date/Publication: | 2025-05-05 10:10:02 UTC |
Select Non-Numeric Columns
Description
Returns a tibble with only the non-numeric columns of the input, and optionally drops rows with NAs.
Usage
select_non_numeric_cols(dataset, remove_na = FALSE)
Arguments
dataset |
A vector, matrix, data frame, or tibble. |
remove_na |
Logical. If TRUE, rows with any NA values will be dropped. Default is FALSE. |
Value
A tibble with only non-numeric columns.
Examples
select_non_numeric_cols(iris)
df <- tibble::tibble(a = 1:6, b = c("x", "y", NA, NA, "z", NA))
select_non_numeric_cols(df, remove_na = TRUE)
Select Numeric Columns
Description
Returns a tibble with only the numeric columns of the input, and optionally drops rows with NAs.
Usage
select_numeric_cols(dataset, remove_na = FALSE)
Arguments
dataset |
A vector, matrix, data frame, or tibble. |
remove_na |
Logical. If TRUE, rows with any NA values will be dropped. Default is FALSE. |
Value
A tibble with only numeric columns.
Examples
select_numeric_cols(iris)
Multiple Pattern-Replacement Substitutions
Description
Applies multiple regular expression substitutions to a character vector or a specific column of a data frame. Performs replacements sequentially
Usage
str_replace_many(x, pattern, replacement, column = NULL, ...)
Arguments
x |
A character vector or a data frame containing the text to modify. |
pattern |
A character vector of regular expressions to match. |
replacement |
A character vector of replacement strings, same length as 'pattern'. |
column |
Optional. If 'x' is a data frame, the name of the character column to apply the replacements to. |
... |
Additional arguments passed to 'gsub()', such as 'ignore.case = TRUE'. |
Value
- If 'x' is a character vector, returns a modified character vector. - If 'x' is a data frame, returns the data frame with the specified column modified.
Examples
# Example on a character vector
text <- c("The cat and the dog", "dog runs fast", "no animals")
str_replace_many(text, pattern = c("cat", "dog"), replacement = c("lion", "wolf"))
# Example on a data frame
library(tibble)
df <- tibble(id = 1:3, text = c("The cat sleeps", "dog runs fast", "no pets"))
str_replace_many(df, pattern = c("cat", "dog"), replacement = c("lion", "wolf"), column = "text")
Summarise Boxplot Statistics with Outliers
Description
Computes the five-number summary (min, Q1, median, Q3, max), interquartile range (IQR), range, and outliers for each numeric variable in a data frame or a numeric vector.
Usage
summarise_boxplot_stats(x)
Arguments
x |
A numeric vector, matrix, data frame, or tibble. |
Value
A tibble with columns: 'variable', 'min', 'q1', 'median', 'q3', 'max', 'iqr', 'range', 'n_outliers', 'outliers'.
Examples
summarise_boxplot_stats(iris)
summarise_boxplot_stats(iris$Sepal.Width)
summarise_boxplot_stats(data.frame(a = c(rnorm(98), 10, NA)))
Summarise Coefficient of Variation
Description
Calculates the coefficient of variation (CV = sd / mean) for numeric vectors, matrices, data frames, or tibbles.
Usage
summarise_coef_of_variation(x)
Arguments
x |
A numeric vector, matrix, data frame, or tibble. |
Value
A tibble: - If input has one numeric column or is a numeric vector: a tibble with a single value. - If input has multiple numeric columns: a tibble with variable names and coefficient of variation values.
Examples
summarise_coef_of_variation(iris)
summarise_coef_of_variation(iris$Petal.Length)
summarise_coef_of_variation(data.frame(a = rnorm(100), b = runif(100)))
Summarise Correlation Matrix with Optional Significance Tests
Description
Computes correlations between numeric variables of a data frame, or between two vectors. Optionally tests statistical significance (p-value)
Usage
summarise_correlation(
x,
y = NULL,
method = c("pearson", "kendall", "spearman"),
cor_test = FALSE
)
Arguments
x |
A numeric vector, matrix, data frame, or tibble. |
y |
Optional. A second numeric vector, matrix, or data frame (same dimensions as 'x'). |
method |
Character. One of "pearson" (default), "kendall", or "spearman". |
cor_test |
Logical. If TRUE, uses 'cor.test()' and includes p-values. If FALSE, uses 'cor()' only. |
Value
A tibble with variables, correlations, and optionally p-values. Significant results (p < 0.05) are printed in red in the console.
Examples
summarise_correlation(iris)
summarise_correlation(iris$Sepal.Length, iris$Petal.Length, cor_test = TRUE)
Summarise Frequency Table
Description
Computes the frequency and relative frequency (or percentage) of factor or character variables in a data frame or vector.
Usage
summarise_frequency(
data,
select = NULL,
as_percent = FALSE,
sort_by = NULL,
top_n = Inf
)
Arguments
data |
A character/factor vector, or a data frame/tibble. |
select |
Optional. One or more variable names to compute frequencies for. If NULL, all factor/character columns are used. |
as_percent |
Logical. If TRUE, relative frequencies are returned as percentages (%). Default is FALSE (proportions). |
sort_by |
Optional. If "N", sorts by frequency; if "group", sorts alphabetically; or "%N" (if as_percent = TRUE). Default is no sorting. |
top_n |
Integer. Show only the top N values |
Value
A tibble with the following columns:
- variable
The name of the variable.
- group
The group/category values of the variable.
- N
The count (frequency) of each group.
- %N
The proportion or percentage of each group.
Examples
summarise_frequency(iris, select = "Species")
summarise_frequency(iris, as_percent = TRUE, sort_by = "N", top_n = 2)
summarise_frequency(data.frame(group = c("A", "A", "B", "C", "A")), as_percent = TRUE)
Summarize Grouped Statistics
Description
Groups a data frame by one or more variables and summarizes the selected numeric columns using basic statistic functions. Handles missing values by replacement with zero or removal of rows.
Usage
summarise_group_stats(
df,
group_var,
values,
m_functions = c("mean", "sd", "length"),
replace_na = FALSE,
remove_na = FALSE
)
Arguments
df |
A data frame or tibble containing the data. |
group_var |
A character vector of column names to group by. |
values |
A character vector of numeric column names to summarize. |
m_functions |
A character vector of functions to apply (e.g., "mean", "sd", "length"). Default is c("mean", "sd", "length"). |
replace_na |
Logical. If TRUE, missing values in numeric columns are replaced with 0. Default is FALSE. |
remove_na |
Logical. If TRUE, rows with missing values in group or value columns are removed. Default is FALSE. |
Value
A tibble with grouped and summarized results.
Examples
summarise_group_stats(iris, group_var = "Species",
values = c("Sepal.Length", "Petal.Width"))
summarise_group_stats(mtcars,
group_var = c("cyl", "gear"),
values = c("mpg", "hp"), remove_na = TRUE)
Summarise Kurtosis
Description
Calculates the kurtosis (default: **excess kurtosis**) of numeric vectors, matrices, data frames, or tibbles. Supports both the "standard" and "unbiased" methods and optionally returns **raw kurtosis**.
Usage
summarise_kurtosis(x, method = c("standard", "unbiased"), excess = TRUE)
Arguments
x |
A numeric vector, matrix, data frame, or tibble. |
method |
Character. Method for kurtosis calculation: '"standard"' (default) or '"unbiased"'. |
excess |
Logical. If TRUE (default), returns **excess kurtosis** (minus 3); if FALSE, returns **raw kurtosis**. |
Value
A tibble: - If input has one numeric column (or is a vector), a single-row tibble. - If input has multiple numeric columns, a tibble with variable names and kurtosis values.
Examples
summarise_kurtosis(iris)
summarise_kurtosis(iris, method = "unbiased")
summarise_kurtosis(iris, excess = FALSE) # Raw kurtosis
summarise_kurtosis(iris$Sepal.Width)
Summarise Skewness
Description
Calculates skewness for numeric vectors, matrices, data frames, or tibbles using Pearson’s moment coefficient.
Usage
summarise_skewness(x)
Arguments
x |
A numeric vector, matrix, data frame, or tibble. |
Value
A tibble: - If input has one numeric column or is a numeric vector: a tibble with a single value. - If input has multiple numeric columns: a tibble with variable names and skewness values.
Examples
summarise_skewness(iris)
summarise_skewness(as.vector(iris$Sepal.Width))
summarise_skewness(data.frame(a = rnorm(100), b = rgamma(100, 2)))
Summarise Descriptive Statistics with Optional Testing
Description
Computes descriptive statistics for numeric data. Optionally groups by a variable and includes Shapiro-Wilk and group significance testing. Can color console output for significant differences.
Usage
summarise_statistics(
data,
group_var = NULL,
normality_test = FALSE,
group_test = FALSE,
show_colors = TRUE
)
Arguments
data |
A numeric vector, matrix, or data frame. |
group_var |
Optional. A character name of a grouping variable. |
normality_test |
Logical. If TRUE, performs Shapiro-Wilk test for normality. |
group_test |
Logical. If TRUE and 'group_var' is set, performs group-wise significance tests (t-test, ANOVA, etc.). |
show_colors |
Logical. If TRUE and 'group_test' is TRUE, prints colored console output for significant group results. Default is TRUE. |
Value
A tibble with descriptive statistics and optional test results per numeric variable.
Examples
summarise_statistics(iris, group_var = "Species", group_test = TRUE)