Correlations in R

A tool for exploring correlations. It makes it possible to easily perform routine tasks when exploring correlation matrices such as ignoring the diagonal, focusing on the correlations of certain variables against others, or rearranging and visualising the matrix in terms of the strength of the correlations.


Project Status: Active ? The project has reached a stable, usablestate and is being activelydeveloped. minimal Rversion CRAN_Status_Badge packageversion Last-changedate BuildStatus Downloads

corrr is a package for exploring correlations in R. It focuses on creating and working with data frames of correlations (instead of matrices) that can be easily explored via corrr functions or by leveraging tools like those in the tidyverse. This, along with the primary corrr functions, is represented below:

You can install:

  • the latest released version from CRAN with
install.packages("corrr")
  • the latest development version from github with
install.packages("devtools")  # run this line if devtools is not installed
devtools::install_github("drsimonj/corrr")

Using corrr

Using corrr typically starts with correlate(), which acts like the base correlation function cor(). It differs by defaulting to pairwise deletion, and returning a correlation data frame (cor_df) of the following structure:

  • A tbl with an additional class, cor_df
  • An extra “rowname” column
  • Standardised variances (the matrix diagonal) set to missing values (NA) so they can be ignored.

API

The corrr API is designed with data pipelines in mind (e.g., to use %>% from the magrittr package). After correlate(), the primary corrr functions take a cor_df as their first argument, and return a cor_df or tbl (or output like a plot). These functions serve one of three purposes:

Internal changes (cor_df out):

  • shave() the upper or lower triangle (set to NA).
  • rearrange() the columns and rows based on correlation strengths.

Reshape structure (tbl or cor_df out):

  • focus() on select columns and rows.
  • stretch() into a long format.

Output/visualisations (console/plot out):

  • fashion() the correlations for pretty printing.
  • rplot() the correlations with shapes in place of the values.
  • network_plot() the correlations in a network.

Examples

library(MASS)
library(corrr)
set.seed(1)
 
# Simulate three columns correlating about .7 with each other
mu <- rep(0, 3)
Sigma <- matrix(.7, nrow = 3, ncol = 3) + diag(3)*.3
seven <- mvrnorm(n = 1000, mu = mu, Sigma = Sigma)
 
# Simulate three columns correlating about .4 with each other
mu <- rep(0, 3)
Sigma <- matrix(.4, nrow = 3, ncol = 3) + diag(3)*.6
four <- mvrnorm(n = 1000, mu = mu, Sigma = Sigma)
 
# Bind together
d <- cbind(seven, four)
colnames(d) <- paste0("v", 1:ncol(d))
 
# Insert some missing values
d[sample(1:nrow(d), 100, replace = TRUE), 1] <- NA
d[sample(1:nrow(d), 200, replace = TRUE), 5] <- NA
 
# Correlate
x <- correlate(d)
class(x)
#> [1] "cor_df"     "tbl_df"     "tbl"        "data.frame"
x
#> # A tibble: 6 x 7
#>   rowname         v1        v2        v3         v4       v5       v6
#>   <chr>        <dbl>     <dbl>     <dbl>      <dbl>    <dbl>    <dbl>
#> 1 v1       NA          0.710     0.709     0.000195  0.0214   -0.0435
#> 2 v2        0.710     NA         0.697    -0.0133    0.00928  -0.0338
#> 3 v3        0.709      0.697    NA        -0.0253    0.00109  -0.0201
#> 4 v4        0.000195  -0.0133   -0.0253   NA         0.421     0.442 
#> 5 v5        0.0214     0.00928   0.00109   0.421    NA         0.425 
#> 6 v6       -0.0435    -0.0338   -0.0201    0.442     0.425    NA

As a tbl, we can use functions from data frame packages like dplyr, tidyr, ggplot2:

library(dplyr)
 
# Filter rows by correlation size
x %>% filter(v1 > .6)
#> # A tibble: 2 x 7
#>   rowname    v1     v2     v3      v4      v5      v6
#>   <chr>   <dbl>  <dbl>  <dbl>   <dbl>   <dbl>   <dbl>
#> 1 v2      0.710 NA      0.697 -0.0133 0.00928 -0.0338
#> 2 v3      0.709  0.697 NA     -0.0253 0.00109 -0.0201

corrr functions work in pipelines (cor_df in; cor_df or tbl out):

x <- datasets::mtcars %>%
       correlate() %>%    # Create correlation data frame (cor_df)
       focus(-cyl, -vs, mirror = TRUE) %>%  # Focus on cor_df without 'cyl' and 'vs'
       rearrange() %>%  # rearrange by correlations
       shave() # Shave off the upper triangle for a clean result
#> 
#> Correlation method: 'pearson'
#> Missing treated using: 'pairwise.complete.obs'
       
fashion(x)
#>   rowname   am drat gear   wt disp  mpg   hp qsec carb
#> 1      am                                             
#> 2    drat  .71                                        
#> 3    gear  .79  .70                                   
#> 4      wt -.69 -.71 -.58                              
#> 5    disp -.59 -.71 -.56  .89                         
#> 6     mpg  .60  .68  .48 -.87 -.85                    
#> 7      hp -.24 -.45 -.13  .66  .79 -.78               
#> 8    qsec -.23  .09 -.21 -.17 -.43  .42 -.71          
#> 9    carb  .06 -.09  .27  .43  .39 -.55  .75 -.66
rplot(x)

 
datasets::airquality %>% 
  correlate() %>% 
  network_plot(min_cor = .2)
#> 
#> Correlation method: 'pearson'
#> Missing treated using: 'pairwise.complete.obs'

News

corrr 0.3.0

Small breaking changes

The diagonal argument of as_matrix and as_matrix.cor_df is now an optional argument rather than set to 1 by default #52

New Functions

  • as_cordf will coerce lists or matrices into correlation data frames if possible.
  • focus_if enables conditional variable selection.

New Functionality

  • Can use arithmetic operators (e.g., + or -) with correlation data frames.
  • Plotting functions (rplot and network_plot) will attempt to coerce objects to a correlation data frame (via as_cordf) if needed, making it possible to directly use these functions with other square-matrix-like objects.
  • repel option added to network_plot (default = TRUE).
  • curved option added to network_plot (default = TRUE).
  • correlate() now prints a message about the method and use parameters. Can be silenced with quiet = TRUE.
  • correlate() now supports data frame with a SQL back-end (tbl_sql)

Fixes

  • When legend = TRUE (now the default setting), rplot and network_plot generate a single, unlabelled legend referring to the size of the correlations.

Other

  • correlate() is now an S3 method so that it can adapt to x's object type.

  • During the development of this version, ggplot v2.2.0 was released. Many changes in the plotting functions have been made to handle new features in the updated version of ggplot2.

  • Improvements to the package folder structure

corrr 0.2.1

New Functionality

  • Can keep leading zeros when using fashion() with new argument leading_zeros = TRUE.
  • New optional arguments added to plotting functions, network_plot() and rplot():
    • legend to display a legend mapping correlations to size and colour.
    • colours (or colors) to change colours in plot.

Fixes

  • network_plot() no longer plots wrong colours if only positive correlations are included.
  • Colour scheme for network_plot() changed to match rplot().
  • Other bug fixes.

corrr 0.2.0

New Functions

  • network_plot() the correlations.
  • focus_() for standard evaluation version of focus().

New Functionality

  • fashion() will now attempt to work on any object (not just cor_df), making it useful for printing any data frame, matrix, vector, etc.
  • print_cor argument added to rplot() to overlay the correlations as text.

Other

  • na_omit argument in stretch() changed to na.rm to match gather_().
  • Bug fixes.
  • Improvements.

corrr 0.1.0

  • First corrr release!

Reference manual

It appears you don't have a PDF plugin for this browser. You can click here to download the reference manual.

install.packages("corrr")

0.3.0 by Simon Jackson, 6 months ago


https://github.com/drsimonj/corrr


Report a bug at https://github.com/drsimonj/corrr/issues


Browse source code at https://github.com/cran/corrr


Authors: Simon Jackson [aut, cre] , Jorge Cimentada [ctb] , Edgar Ruiz [ctb]


Documentation:   PDF Manual  


MIT + file LICENSE license


Imports dplyr, magrittr, tidyr, ggplot2, seriation, lazyeval, purrr, tibble, ggrepel, methods, rlang

Suggests testthat, knitr, rmarkdown, dbplyr, DBI, RSQLite


See at CRAN