Correlation matrix using factors r

require(tidyverse)
require(rcompanion)


# Calculate a pairwise association between all variables in a data-frame. In particular nominal vs nominal with Chi-square, numeric vs numeric with Pearson correlation, and nominal vs numeric with ANOVA.
# Adopted from https://stackoverflow.com/a/52557631/590437
mixed_assoc = function(df, cor_method="spearman", adjust_cramersv_bias=TRUE){
    df_comb = expand.grid(names(df), names(df),  stringsAsFactors = F) %>% set_names("X1", "X2")

    is_nominal = function(x) class(x) %in% c("factor", "character")
    # https://community.rstudio.com/t/why-is-purr-is-numeric-deprecated/3559
    # https://github.com/r-lib/rlang/issues/781
    is_numeric <- function(x) { is.integer(x) || is_double(x)}

    f = function(xName,yName) {
        x =  pull(df, xName)
        y =  pull(df, yName)

        result = if(is_nominal(x) && is_nominal(y)){
            # use bias corrected cramersV as described in https://rdrr.io/cran/rcompanion/man/cramerV.html
            cv = cramerV(as.character(x), as.character(y), bias.correct = adjust_cramersv_bias)
            data.frame(xName, yName, assoc=cv, type="cramersV")

        }else if(is_numeric(x) && is_numeric(y)){
            correlation = cor(x, y, method=cor_method, use="complete.obs")
            data.frame(xName, yName, assoc=correlation, type="correlation")

        }else if(is_numeric(x) && is_nominal(y)){
            # from https://stats.stackexchange.com/questions/119835/correlation-between-a-nominal-iv-and-a-continuous-dv-variable/124618#124618
            r_squared = summary(lm(x ~ y))$r.squared
            data.frame(xName, yName, assoc=sqrt(r_squared), type="anova")

        }else if(is_nominal(x) && is_numeric(y)){
            r_squared = summary(lm(y ~x))$r.squared
            data.frame(xName, yName, assoc=sqrt(r_squared), type="anova")

        }else {
            warning(paste("unmatched column type combination: ", class(x), class(y)))
        }

        # finally add complete obs number and ratio to table
        result %>% mutate(complete_obs_pairs=sum(!is.na(x) & !is.na(y)), complete_obs_ratio=complete_obs_pairs/length(x)) %>% rename(x=xName, y=yName)
    }

    # apply function to each variable combination
    map2_df(df_comb$X1, df_comb$X2, f)
}

Source: stackoverflow.com

Similar codes

0 vote253 views1 answer
Disable the y axis in plot r
R
0 vote280 views1 answer
Remove_all_labels(x)
R
7 votes382 views2 answers
How to remove nas in r
R
0 vote309 views1 answer
R find n largest
R
1 vote246 views1 answer
Delete first three lines dataframe R
R
0 vote271 views2 answers
Linear regression r text label coefficient ggplot
R
1 vote287 views1 answer
R print concatenate
R
0 vote284 views1 answer
Detect rank deficient in r
R
0 vote298 views1 answer
How to get the r2 value in r
R
-1 vote279 views2 answers
Export csv file in r
R