Reshape correlation analysis results. Key functions:
cor_gather(): takes a correlation matrix and collapses (i.e. melt) it into a paired list
(long format).
cor_spread(): spread a long correlation data format across
multiple columns. Particularly, it takes the results of cor_test
and transforms it into a correlation matrix.
cor_gather(data, drop.na = TRUE)
cor_spread(data, value = "cor")a data frame or matrix.
logical. If TRUE, drop rows containing missing values after gathering the data.
column name containing the value to spread.
cor_gather(): takes a correlation matrix and collapses (or melt) it into long
format data frame (paired list)
cor_spread(): spread a long correlation data frame into wide
format. Expects the columns "var1", "var2" and "cor" in the data.
(correlation matrix).
cor_mat(), cor_reorder()
# Data preparation
#::::::::::::::::::::::::::::::::::::::::::
mydata <- mtcars %>%
select(mpg, disp, hp, drat, wt, qsec)
head(mydata, 3)
#> mpg disp hp drat wt qsec
#> Mazda RX4 21.0 160 110 3.90 2.620 16.46
#> Mazda RX4 Wag 21.0 160 110 3.90 2.875 17.02
#> Datsun 710 22.8 108 93 3.85 2.320 18.61
# Reshape a correlation matrix
#::::::::::::::::::::::::::::::::::::::::::
# Compute a correlation matrix
cor.mat <- mydata %>% cor_mat()
cor.mat
#> # A tibble: 6 × 7
#> rowname mpg disp hp drat wt qsec
#> * <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
#> 1 mpg 1 -0.85 -0.78 0.68 -0.87 0.42
#> 2 disp -0.85 1 0.79 -0.71 0.89 -0.43
#> 3 hp -0.78 0.79 1 -0.45 0.66 -0.71
#> 4 drat 0.68 -0.71 -0.45 1 -0.71 0.091
#> 5 wt -0.87 0.89 0.66 -0.71 1 -0.17
#> 6 qsec 0.42 -0.43 -0.71 0.091 -0.17 1
# Collapse the correlation matrix into long format
# paired list data frame
long.format <- cor.mat %>% cor_gather()
long.format
#> # A tibble: 36 × 4
#> var1 var2 cor p
#> <chr> <chr> <dbl> <dbl>
#> 1 mpg mpg 1 0
#> 2 disp mpg -0.85 9.38e-10
#> 3 hp mpg -0.78 1.79e- 7
#> 4 drat mpg 0.68 1.78e- 5
#> 5 wt mpg -0.87 1.29e-10
#> 6 qsec mpg 0.42 1.71e- 2
#> 7 mpg disp -0.85 9.38e-10
#> 8 disp disp 1 0
#> 9 hp disp 0.79 7.14e- 8
#> 10 drat disp -0.71 5.28e- 6
#> # … with 26 more rows
# Spread a correlation data format
#::::::::::::::::::::::::::::::::::::::::::
# Spread the correlation coefficient value
long.format %>% cor_spread(value = "cor")
#> # A tibble: 6 × 7
#> rowname mpg disp hp drat wt qsec
#> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
#> 1 mpg 1 -0.85 -0.78 0.68 -0.87 0.42
#> 2 disp -0.85 1 0.79 -0.71 0.89 -0.43
#> 3 hp -0.78 0.79 1 -0.45 0.66 -0.71
#> 4 drat 0.68 -0.71 -0.45 1 -0.71 0.091
#> 5 wt -0.87 0.89 0.66 -0.71 1 -0.17
#> 6 qsec 0.42 -0.43 -0.71 0.091 -0.17 1
# Spread the p-value
long.format %>% cor_spread(value = "p")
#> # A tibble: 6 × 7
#> rowname mpg disp hp drat wt qsec
#> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
#> 1 mpg 0 9.38e-10 0.000000179 0.0000178 1.29e- 10 0.0171
#> 2 disp 9.38e-10 0 0.0000000714 0.00000528 1.22e- 11 0.0131
#> 3 hp 1.79e- 7 7.14e- 8 0 0.00999 4.15e- 5 0.00000577
#> 4 drat 1.78e- 5 5.28e- 6 0.00999 0 4.78e- 6 0.62
#> 5 wt 1.29e-10 1.22e-11 0.0000415 0.00000478 2.27e-236 0.339
#> 6 qsec 1.71e- 2 1.31e- 2 0.00000577 0.62 3.39e- 1 0