added stats_unpaired.R for sam, serum and npa
This commit is contained in:
parent
0dab1d5097
commit
93973ed850
4 changed files with 897 additions and 26 deletions
|
|
@ -171,16 +171,22 @@ tail(colnames_check_f)
|
|||
# LF data
|
||||
##########################################################################
|
||||
|
||||
#=========
|
||||
#==============
|
||||
# lf data: sam
|
||||
#=========
|
||||
#==============
|
||||
str(sam_df)
|
||||
table(sam_df$obesity); table(sam_df$obese2)
|
||||
|
||||
sam_df_adults = sam_df[sam_df$adult == 1,]
|
||||
|
||||
cols_to_omit = c("adult", "flustat", "type", "obesity"
|
||||
, "height", "height_unit", "weight", "weight_unit","visual_est_bmi", "bmi_rating")
|
||||
cols_to_omit = c("flustat", "type", "obesity"
|
||||
, "height", "height_unit", "weight"
|
||||
, "weight_unit", "visual_est_bmi", "bmi_rating")
|
||||
|
||||
#sam_df_adults_clean = sam_df_adults[!cols_to_omit]
|
||||
|
||||
wf_cols = colnames(sam_df_adults)[!colnames(sam_df_adults)%in%cols_to_omit]
|
||||
sam_df_adults_clean = sam_df_adults[wf_cols]
|
||||
|
||||
pivot_cols = meta_data_cols
|
||||
pivot_cols = meta_data_cols[!meta_data_cols%in%cols_to_omit];pivot_cols
|
||||
|
|
@ -194,44 +200,144 @@ if (length(pivot_cols) == length(meta_data_cols) - length(cols_to_omit)){
|
|||
quit()
|
||||
}
|
||||
|
||||
expected_rows_sam_lf = nrow(sam_df_adults) * (length(sam_df_adults) - length(pivot_cols)); expected_rows_sam_lf
|
||||
expected_rows_sam_lf = nrow(sam_df_adults_clean) * (length(sam_df_adults_clean) - length(pivot_cols)); expected_rows_sam_lf
|
||||
|
||||
# using regex:
|
||||
sam_adults_lf = sam_df_adults %>%
|
||||
tidyr::pivot_longer(-all_of(pivot_cols), names_to = c("mediator", "sample_type", "timepoint"),
|
||||
names_pattern = "(.*)_(.*)([1-3]{1})",
|
||||
values_to = "value")
|
||||
sam_adults_lf = sam_df_adults_clean %>%
|
||||
tidyr::pivot_longer(-all_of(pivot_cols)
|
||||
, names_to = c("mediator", "sample_type", "timepoint")
|
||||
, names_pattern = "(.*)_(.*)([1-3]{1})"
|
||||
, values_to = "value")
|
||||
|
||||
if ((nrow(sam_lf) == expected_rows_sam_lf) & (sum(table(is.na(sam_adults_lf$mediator))) == expected_rows_sam_lf)) {
|
||||
if (
|
||||
(nrow(sam_adults_lf) == expected_rows_sam_lf) & (sum(table(is.na(sam_adults_lf$mediator))) == expected_rows_sam_lf)
|
||||
) {
|
||||
cat(paste0("PASS: long format data has correct no. of rows and NA in mediator:"
|
||||
, "\nNo. of rows: ", nrow(sam_lf)
|
||||
, "\nNo. of cols: ", ncol(sam_lf)))
|
||||
, "\nNo. of rows: ", nrow(sam_adults_lf)
|
||||
, "\nNo. of cols: ", ncol(sam_adults_lf)))
|
||||
} else{
|
||||
cat(paste0("FAIL:long format data has unexpected no. of rows or NAs in mediator"
|
||||
, "\nExpected no. of rows: ", expected_rows_sam_lf
|
||||
, "\nGot: ", nrow(sam_lf)
|
||||
, "\nGot: ", nrow(sam_adults_lf)
|
||||
, "\ncheck expected rows calculation!"))
|
||||
quit()
|
||||
}
|
||||
|
||||
#library(data.table)
|
||||
#foo = sam_df_adults[1:10]
|
||||
#long <- melt(setDT(sam_df_adults), id.vars = pivot_cols, variable.name = "levels")
|
||||
|
||||
#==============
|
||||
# lf data: serum
|
||||
#==============
|
||||
str(serum_df)
|
||||
table(serum_df$obesity); table(serum_df$obese2)
|
||||
|
||||
serum_df_adults = serum_df[serum_df$adult == 1,]
|
||||
|
||||
|
||||
cols_to_omit = c("flustat", "type", "obesity"
|
||||
, "height", "height_unit", "weight", "weight_unit","visual_est_bmi", "bmi_rating")
|
||||
|
||||
#serum_df_adults_clean = serum_df_adults[!cols_to_omit]
|
||||
|
||||
wf_cols = colnames(serum_df_adults)[!colnames(serum_df_adults)%in%cols_to_omit]
|
||||
serum_df_adults_clean = serum_df_adults[wf_cols]
|
||||
|
||||
pivot_cols = meta_data_cols
|
||||
pivot_cols = meta_data_cols[!meta_data_cols%in%cols_to_omit];pivot_cols
|
||||
|
||||
if (length(pivot_cols) == length(meta_data_cols) - length(cols_to_omit)){
|
||||
cat("PASS: pivot cols successfully extracted")
|
||||
}else{
|
||||
cat("FAIL: length mismatch! pivot cols could not be extracted"
|
||||
, "\nExpected length:", length(meta_data_cols) - length(cols_to_omit)
|
||||
, "\nGot:",length(pivot_cols) )
|
||||
quit()
|
||||
}
|
||||
|
||||
expected_rows_serum_lf = nrow(serum_df_adults_clean) * (length(serum_df_adults_clean) - length(pivot_cols)); expected_rows_serum_lf
|
||||
|
||||
# using regex:
|
||||
serum_adults_lf = serum_df_adults_clean %>%
|
||||
tidyr::pivot_longer(-all_of(pivot_cols)
|
||||
, names_to = c("mediator", "sample_type", "timepoint")
|
||||
, names_pattern = "(.*)_(.*)([1-3]{1})"
|
||||
, values_to = "value")
|
||||
|
||||
if (
|
||||
(nrow(serum_adults_lf) == expected_rows_serum_lf) & (sum(table(is.na(serum_adults_lf$mediator))) == expected_rows_serum_lf)
|
||||
) {
|
||||
cat(paste0("PASS: long format data has correct no. of rows and NA in mediator:"
|
||||
, "\nNo. of rows: ", nrow(serum_adults_lf)
|
||||
, "\nNo. of cols: ", ncol(serum_adults_lf)))
|
||||
} else{
|
||||
cat(paste0("FAIL:long format data has unexpected no. of rows or NAs in mediator"
|
||||
, "\nExpected no. of rows: ", expected_rows_serum_lf
|
||||
, "\nGot: ", nrow(serum_adults_lf)
|
||||
, "\ncheck expected rows calculation!"))
|
||||
quit()
|
||||
}
|
||||
|
||||
#==============
|
||||
# lf data: npa
|
||||
#==============
|
||||
str(npa_df)
|
||||
table(npa_df$obesity); table(npa_df$obese2)
|
||||
|
||||
npa_df_adults = npa_df[npa_df$adult == 1,]
|
||||
|
||||
|
||||
cols_to_omit = c("flustat", "type", "obesity"
|
||||
, "height", "height_unit", "weight", "weight_unit","visual_est_bmi", "bmi_rating")
|
||||
|
||||
#npa_df_adults_clean = npa_df_adults[!cols_to_omit]
|
||||
|
||||
wf_cols = colnames(npa_df_adults)[!colnames(npa_df_adults)%in%cols_to_omit]
|
||||
npa_df_adults_clean = npa_df_adults[wf_cols]
|
||||
|
||||
pivot_cols = meta_data_cols
|
||||
pivot_cols = meta_data_cols[!meta_data_cols%in%cols_to_omit];pivot_cols
|
||||
|
||||
if (length(pivot_cols) == length(meta_data_cols) - length(cols_to_omit)){
|
||||
cat("PASS: pivot cols successfully extracted")
|
||||
}else{
|
||||
cat("FAIL: length mismatch! pivot cols could not be extracted"
|
||||
, "\nExpected length:", length(meta_data_cols) - length(cols_to_omit)
|
||||
, "\nGot:",length(pivot_cols) )
|
||||
quit()
|
||||
}
|
||||
|
||||
expected_rows_npa_lf = nrow(npa_df_adults_clean) * (length(npa_df_adults_clean) - length(pivot_cols)); expected_rows_npa_lf
|
||||
|
||||
# using regex:
|
||||
npa_adults_lf = npa_df_adults_clean %>%
|
||||
tidyr::pivot_longer(-all_of(pivot_cols)
|
||||
, names_to = c("mediator", "sample_type", "timepoint")
|
||||
, names_pattern = "(.*)_(.*)([1-3]{1})"
|
||||
, values_to = "value")
|
||||
|
||||
if (
|
||||
(nrow(npa_adults_lf) == expected_rows_npa_lf) & (sum(table(is.na(npa_adults_lf$mediator))) == expected_rows_npa_lf)
|
||||
) {
|
||||
cat(paste0("PASS: long format data has correct no. of rows and NA in mediator:"
|
||||
, "\nNo. of rows: ", nrow(npa_adults_lf)
|
||||
, "\nNo. of cols: ", ncol(npa_adults_lf)))
|
||||
} else{
|
||||
cat(paste0("FAIL:long format data has unexpected no. of rows or NAs in mediator"
|
||||
, "\nExpected no. of rows: ", expected_rows_npa_lf
|
||||
, "\nGot: ", nrow(npa_adults_lf)
|
||||
, "\ncheck expected rows calculation!"))
|
||||
quit()
|
||||
}
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
###############################################################################
|
||||
# remove unnecessary variables
|
||||
rm(sam_regex, sam_regex_log_days, sam_cols, sam_cols_b, sam_cols_clean, sam_cols_i, sam_cols_to_extract, sam_cols_to_omit)
|
||||
rm(serum_regex, serum_regex_log_days, serum_cols, serum_cols_clean, serum_cols_i, serum_cols_to_extract, serum_cols_to_omit)
|
||||
rm(npa_regex, npa_regex_log_days, npa_cols, npa_cols_clean, npa_cols_i, npa_cols_to_extract, npa_cols_to_omit)
|
||||
rm(all_df)
|
||||
rm(colnames_check)
|
||||
rm(i, j, expected_cols, start, wf_cols, extra_cols, cols_to_omit)
|
||||
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue