Last active
December 5, 2021 10:44
-
-
Save thistleknot/38a91a1496e815d9b6ba9bfa522f8c0d to your computer and use it in GitHub Desktop.
Use ZCA (vs PCOR) to iterate from least significant correlations to most
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
sig_table = matrix(0, ncol=ncol(newDF_t)) | |
colnames(sig_table) <- colnames(newDF_t) | |
signs_table = matrix(0, ncol=ncol(newDF_t)) | |
colnames(signs_table) <- colnames(newDF_t) | |
p_threshold = .05 | |
New_Names = colnames(newDF_t)[2:length(colnames(newDF_t))] | |
iteration=0 | |
dat <- 1:10 | |
n=length(dat) | |
exclude <- c() | |
max_pvalue = 1 | |
subset = newDF_t[,c(colnames(newDF_t) %notin% c(exclude))] | |
subset_w <- cbind(subset[,var_of_int,drop=FALSE],as.data.frame(whiten(as.matrix(subset[,c(colnames(newDF_t) %notin% c(var_of_int))]), method=c("ZCA")))) | |
colnames(subset_w) <- colnames(subset) | |
rownames(subset_w) <- rownames(subset) | |
corrplot(cor(subset_w)) | |
set_ = subset_w[,c(colnames(newDF_t) %notin% c(var_of_int))] | |
while(max_pvalue>=p_threshold) | |
{ | |
p_values <- (2 * (1 - pnorm(abs(cor(subset_w)[,var_of_int,drop=FALSE]), mean = 0, sd = 1/sqrt(nrow(subset))))) | |
#p_values <- (2 * (1 - pnorm(abs(PCOR(subset)[,var_of_int,drop=FALSE]), mean = 0, sd = 1/sqrt(nrow(subset))))) | |
#p_values <- pcor(subset, method = c("spearman"))$p.value[,var_of_int,drop=FALSE] | |
max_pname = rownames(p_values)[which.max(p_values)] | |
max_pvalue = p_values[max_pname,] | |
if (max_pvalue >= p_threshold) | |
{ | |
print(max_pvalue) | |
print(max_pname) | |
temp <- dplyr::select(subset_w,-c(max_pname)) | |
temp_ <- cbind(subset_w[,var_of_int,drop=FALSE],as.data.frame(whiten(as.matrix(temp[,c(colnames(temp) %notin% c(var_of_int))]), method=c("ZCA")))) | |
colnames(temp_) <- colnames(temp) | |
rownames(temp_) <- rownames(temp) | |
subset_w <- temp_ | |
} | |
} | |
winners = rownames(p_values)[rownames(p_values) %notin% c(var_of_int)] | |
sig_table = sig_table + as.integer(colnames(newDF_t) %in% winners) | |
corrplot(pcor(subset[,c(var_of_int,winners)], method = c("pearson"))$estimate | |
corrplot(cor(subset_w[,c(var_of_int,winners)])) | |
corrplot(cor(subset[,c(var_of_int,winners)])) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment