reformatting code to select needed df for analysis
This commit is contained in:
parent
a6cbaab40a
commit
b72c4df796
7 changed files with 243 additions and 102 deletions
|
|
@ -53,31 +53,36 @@ if ( sum(table(clinical_df$obesity)) & sum(table(clinical_df$age>=18)) & sum(tab
|
|||
|
||||
table(clinical_df$ia_exac_copd)
|
||||
|
||||
str(clinical_df)
|
||||
#clinical_df$o2_sat_suppl
|
||||
|
||||
########################################################################
|
||||
#==================================
|
||||
# asthma and copd status correction
|
||||
# for conflicting field!
|
||||
# Check asthma and copd conflict
|
||||
#=================================
|
||||
if ( table(fp_adults$ia_exac_copd, fp_adults$asthma) [[2,2]] == 0){
|
||||
cat("PASS: asthma and copd do not conflict")
|
||||
}else{
|
||||
cat("Conflict detected in asthm and copd filed, attempting to resolve...")
|
||||
# Reassign the copd and asthma status and do some checks
|
||||
table(fp_adults$ia_exac_copd); sum(is.na(fp_adults$ia_exac_copd))
|
||||
fp_adults$ia_exac_copd[fp_adults$ia_exac_copd< 1]<- 0
|
||||
fp_adults$ia_exac_copd[is.na(fp_adults$ia_exac_copd)] <- 0
|
||||
table(fp_adults$ia_exac_copd); sum(is.na(fp_adults$ia_exac_copd))
|
||||
|
||||
# check copd and asthma status
|
||||
table(fp_adults$ia_exac_copd, fp_adults$asthma)
|
||||
check_copd_and_asthma_1<- subset(fp_adults, ia_exac_copd ==1 & asthma == 1) # check this is 3
|
||||
|
||||
# reassign these 3 so these are treated as non-asthmatics as copd with asthma is NOT TRUE asthma
|
||||
fp_adults$asthma[fp_adults$ia_exac_copd == 1 & fp_adults$asthma == 1]= 0
|
||||
table(fp_adults$ia_exac_copd, fp_adults$asthma)
|
||||
foo<- subset(fp_adults, asthma==1 & ia_exac_copd ==1) # check that its 0
|
||||
rm(check_copd_and_asthma_1, foo)
|
||||
cat("Check status again...")
|
||||
|
||||
# Reassign the copd and asthma status and do some checks
|
||||
table(clinical_df$ia_exac_copd); sum(is.na(clinical_df$ia_exac_copd))
|
||||
}
|
||||
|
||||
clinical_df$ia_exac_copd[clinical_df$ia_exac_copd< 1]<- 0
|
||||
clinical_df$ia_exac_copd[is.na(clinical_df$ia_exac_copd)] <- 0
|
||||
|
||||
table(clinical_df$ia_exac_copd); sum(is.na(clinical_df$ia_exac_copd))
|
||||
|
||||
# check copd and asthma status
|
||||
table(clinical_df$ia_exac_copd, clinical_df$asthma)
|
||||
check_copd_and_asthma_1<- subset(clinical_df, ia_exac_copd ==1 & asthma == 1) # check this is 3
|
||||
|
||||
# reassign these 3 so these are treated as non-asthmatics as copd with asthma is NOT TRUE asthma
|
||||
clinical_df$asthma[clinical_df$ia_exac_copd == 1 & clinical_df$asthma == 1]= 0
|
||||
table(clinical_df$ia_exac_copd, clinical_df$asthma)
|
||||
|
||||
foo<- subset(clinical_df, asthma==1 & ia_exac_copd ==1) # check that its 0
|
||||
|
||||
rm(check_copd_and_asthma_1, foo)
|
||||
#=====================================================================
|
||||
#=================================
|
||||
# resp scores: In, max and t1 & t2
|
||||
|
|
@ -97,7 +102,7 @@ Inresp_sev<- table(clinical_df$inresp_sev)
|
|||
Inresp_sev
|
||||
|
||||
# Reassign the resp score so all 4 are replace by 3
|
||||
clinical_df$max_resp_score[clinical_df$max_resp_score ==4 ] <- 3
|
||||
clinical_df$max_resp_score[clinical_df$max_resp_score == 4 ] <- 3
|
||||
revised_resp_score_table<- table(clinical_df$max_resp_score)
|
||||
revised_resp_score_table
|
||||
|
||||
|
|
@ -125,29 +130,30 @@ rm(max_resp_score_table, T1_resp_score_table, T2_resp_score_table, Inresp_sev
|
|||
# age
|
||||
#========
|
||||
# Create categories of variables
|
||||
clinical_df$age = round(clinical_df$age, digits = 0)
|
||||
table(clinical_df$age)
|
||||
table(clinical_df$asthma, clinical_df$age)
|
||||
min(clinical_df$age); max(clinical_df$age)
|
||||
clinical_df$age_int = round(clinical_df$age, digits = 0)
|
||||
table(clinical_df$age_int)
|
||||
table(clinical_df$asthma, clinical_df$age_int)
|
||||
min(clinical_df$age_int); max(clinical_df$age_int)
|
||||
|
||||
max_age_interval = round_any(max(clinical_df$age), 10, f = ceiling)
|
||||
max_age_interval = round_any(max(clinical_df$age_int), 10, f = ceiling)
|
||||
max_age_interval
|
||||
min_age = min(clinical_df$age); min_age #19
|
||||
min_age = min(clinical_df$age_int); min_age #19
|
||||
min_age_interval = min_age - 1; min_age_interval
|
||||
|
||||
#age_bins = cut(clinical_df$age, c(0,18,30,40,50,60,70,80,90))
|
||||
age_bins = cut(clinical_df$age, c(min_age_interval, 30, 40, 50, 60, 70, max_age_interval))
|
||||
#age_bins = cut(clinical_df$age_int, c(0,18,30,40,50,60,70,80,90))
|
||||
age_bins = cut(clinical_df$age_int, c(min_age_interval, 30, 40, 50, 60, 70, max_age_interval))
|
||||
clinical_df$age_bins = age_bins
|
||||
dim(clinical_df) # 133 27
|
||||
dim(clinical_df) # 133 28
|
||||
|
||||
# age_bins (to keep consistent with the results table)
|
||||
class(clinical_df$age_bins)
|
||||
levels(clinical_df$age_bins)
|
||||
#"(18,30]" "(30,40]" "(40,50]" "(50,60]" "(60,70]" "(70,80]"
|
||||
|
||||
table(clinical_df$asthma, clinical_df$age_bins)
|
||||
# (18,30] (30,40] (40,50] (50,60] (60,70] (70,80]
|
||||
#0 25 17 25 14 11 1
|
||||
#1 11 8 12 5 3 2
|
||||
#1 11 8 12 5 2 2
|
||||
|
||||
if (sum(table(clinical_df$asthma, clinical_df$age_bins)) == nrow(clinical_df) ){
|
||||
cat("\nPASS: age_bins assigned successfully")
|
||||
|
|
@ -156,7 +162,7 @@ if (sum(table(clinical_df$asthma, clinical_df$age_bins)) == nrow(clinical_df) ){
|
|||
quit()
|
||||
}
|
||||
|
||||
# reassign
|
||||
# reassign levels
|
||||
class(clinical_df$age_bins)
|
||||
levels(clinical_df$age_bins) <- c("(18,30]","(30,40]","(40,50]","(50,80]","(50,80]","(50,80]")
|
||||
table(clinical_df$asthma, clinical_df$age_bins)
|
||||
|
|
@ -170,11 +176,25 @@ sum(table(clinical_df$asthma, clinical_df$age_bins)) == nrow(clinical_df)
|
|||
#===========================
|
||||
# O2 saturation binning
|
||||
#===========================
|
||||
clinical_df$o2_sat_admis
|
||||
n1 = sum(is.na(clinical_df$o2_sat_admis))
|
||||
|
||||
clinical_df$o2_sat_admis = round(clinical_df$o2_sat_admis, digits = 0)
|
||||
table(clinical_df$o2_sat_admis)
|
||||
tot_o2 = sum(table(clinical_df$o2_sat_admis))- table(clinical_df$o2_sat_admis)[["-1"]]
|
||||
tot_o2
|
||||
|
||||
n_text_code = table(clinical_df$o2_sat_admis)[["-1"]]
|
||||
|
||||
clinical_df$o2_sat_admis[clinical_df$o2_sat_admis <0] <- NA
|
||||
n2 = sum(is.na(clinical_df$o2_sat_admis))
|
||||
|
||||
if (n2 == n1 + n_text_code) {
|
||||
cat ("PASS: -1 code converted to NA")
|
||||
} else{
|
||||
cat("FAIL: something went wrong!")
|
||||
}
|
||||
|
||||
o2_sat_bin = cut(clinical_df$o2_sat_admis, c(0,92,100))
|
||||
clinical_df$o2_sat_bin = o2_sat_bin
|
||||
table(clinical_df$o2_sat_bin)
|
||||
|
|
@ -184,6 +204,8 @@ sum(table(clinical_df$o2_sat_bin)) == tot_o2
|
|||
#===========================
|
||||
# Onset to initial binning
|
||||
#===========================
|
||||
clinical_df$onset_2_initial
|
||||
|
||||
max_in = max(clinical_df$onset_2_initial); max_in #23
|
||||
min_in = min(clinical_df$onset_2_initial) - 1 ; min_in # -6
|
||||
|
||||
|
|
@ -198,14 +220,15 @@ sum(table(clinical_df$onset_initial_bin)) == tot_onset2ini
|
|||
#=======================
|
||||
# seasonal flu: sfluv
|
||||
#=======================
|
||||
# should be a factor
|
||||
if (! is.factor(clinical_df$sfluv)){
|
||||
clinical_df$sfluv = as.factor(clinical_df$sfluv)
|
||||
}
|
||||
class(clinical_df$sfluv) #[1] "factor"
|
||||
|
||||
class(clinical_df$sfluv)
|
||||
levels(clinical_df$sfluv)
|
||||
|
||||
table(clinical_df$sfluv)
|
||||
table(clinical_df$asthma, clinical_df$sfluv)
|
||||
|
||||
# reassign
|
||||
levels(clinical_df$sfluv) <- c("0", "0", "1")
|
||||
table(clinical_df$asthma, clinical_df$sfluv)
|
||||
|
|
@ -213,14 +236,16 @@ table(clinical_df$asthma, clinical_df$sfluv)
|
|||
#=======================
|
||||
# h1n1v
|
||||
#=======================
|
||||
# should be a factor
|
||||
if (! is.factor(clinical_df$h1n1v)){
|
||||
clinical_df$h1n1v = as.factor(clinical_df$h1n1v)
|
||||
}
|
||||
class(clinical_df$h1n1v) #[1] "factor"
|
||||
|
||||
class(clinical_df$h1n1v)
|
||||
levels(clinical_df$h1n1v)
|
||||
|
||||
table(clinical_df$h1n1v)
|
||||
table(clinical_df$asthma, clinical_df$h1n1v)
|
||||
|
||||
# reassign
|
||||
levels(clinical_df$h1n1v) <- c("0", "0", "1")
|
||||
table(clinical_df$asthma, clinical_df$h1n1v)
|
||||
|
|
@ -229,18 +254,21 @@ table(clinical_df$asthma, clinical_df$h1n1v)
|
|||
# ethnicity
|
||||
#=======================
|
||||
class(clinical_df$ethnicity) # integer
|
||||
table(clinical_df$ethnicity)
|
||||
table(clinical_df$asthma, clinical_df$ethnicity)
|
||||
|
||||
clinical_df$ethnicity[clinical_df$ethnicity == 4] <- 2
|
||||
table(clinical_df$ethnicity)
|
||||
table(clinical_df$asthma, clinical_df$ethnicity)
|
||||
|
||||
#=======================
|
||||
# pneumonia
|
||||
#=======================
|
||||
table(clinical_df$ia_cxr)
|
||||
class(clinical_df$ia_cxr) # integer
|
||||
# ia_cxr 2 ---> yes pneumonia (1)
|
||||
# 1 ---> no (0)
|
||||
# ! 1 or 2 -- > "unkown"
|
||||
# ! 1 or 2 -- > "unknown"
|
||||
|
||||
# reassign the pneumonia codes
|
||||
#0: not performed
|
||||
|
|
@ -251,7 +279,6 @@ class(clinical_df$ia_cxr) # integer
|
|||
#-2: n/a specified by the clinician # not in the data...
|
||||
#-3: unknown specified by clinician
|
||||
|
||||
|
||||
table(clinical_df$ia_cxr)
|
||||
#-3 -1 0 1 2 3
|
||||
#5 48 13 47 17 3
|
||||
|
|
@ -262,6 +289,8 @@ table(clinical_df$ia_cxr)
|
|||
# 1 2
|
||||
#69 47 17
|
||||
|
||||
sum(is.na(clinical_df$ia_cxr))
|
||||
|
||||
clinical_df$ia_cxr[clinical_df$ia_cxr == 1] <- 0
|
||||
clinical_df$ia_cxr[clinical_df$ia_cxr == 2] <- 1
|
||||
table(clinical_df$ia_cxr)
|
||||
|
|
@ -306,7 +335,7 @@ clinical_df$smoking[clinical_df$smoking == 4 | clinical_df$smoking == 2 ] <- 0
|
|||
clinical_df$smoking[clinical_df$smoking == 1 | clinical_df$smoking == 3 ] <- 1
|
||||
clinical_df$smoking[clinical_df$smoking == -1 | clinical_df$smoking == -2 | clinical_df$smoking == -3 ] <- NA
|
||||
|
||||
table(clinical_df$smoking)
|
||||
table(clinical_df$smoking); sum(is.na(clinical_df$smoking))
|
||||
# 0 1
|
||||
#30 49 54
|
||||
|
||||
|
|
@ -316,17 +345,13 @@ table(clinical_df$asthma, clinical_df$smoking)
|
|||
# 0 1
|
||||
#0 24 32 37
|
||||
#1 6 17 17
|
||||
|
||||
# 0 1
|
||||
#0 23 32 35
|
||||
#1 7 17 19
|
||||
|
||||
################################################################
|
||||
|
||||
#=========================
|
||||
# Merge: clinical_df and infile ics
|
||||
#=========================
|
||||
merging_cols = intersect( names(clinical_df), names(clinical_ics) )
|
||||
merging_cols
|
||||
|
||||
clinical_df_ics = merge(clinical_df, clinical_ics, by = merging_cols, all = T); clinical_df_ics
|
||||
|
||||
|
|
@ -351,6 +376,15 @@ if (nrow(clinical_df_ics) == nrow(clinical_df) & nrow(clinical_ics)){
|
|||
, "\nExpected nrows:", nrow(fp_adults))
|
||||
}
|
||||
|
||||
# change the factor vars to integers
|
||||
str(clinical_df_ics)
|
||||
factor_vars = lapply(clinical_df_ics, class) == "factor"
|
||||
table(factor_vars)
|
||||
clinical_df_ics[, factor_vars] <- lapply(clinical_df_ics[, factor_vars], as.integer)
|
||||
table(factor_vars)
|
||||
|
||||
str(clinical_df_ics)
|
||||
|
||||
#======================
|
||||
# writing output file
|
||||
#======================
|
||||
|
|
@ -359,9 +393,8 @@ outfile_reg = paste0(outdir, outfile_name_reg)
|
|||
|
||||
cat("\nWriting clinical file for regression:", outfile_reg)
|
||||
|
||||
write.csv(clinical_df_ics, file = outfile_reg)
|
||||
#write.csv(clinical_df_ics, file = outfile_reg)
|
||||
################################################################
|
||||
|
||||
rm(age_bins, max_age_interval, max_in, min_in
|
||||
, o2_sat_bin, onset_initial_bin, tot_o2
|
||||
, tot_onset2ini, meta_data_cols
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue