Skip to content

optimize chi_get_proper_pop function #27

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
dcolombara merged 5 commits into from
May 15, 2025
Merged

optimize chi_get_proper_pop function #27

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
8332ec7
chi_suppress_results created
dcolombara May 9, 2025
f6fa693
fucntion to check if latest version installed
dcolombara May 10, 2025
d701f39
optimize chi_get_proper_pop function
dcolombara May 9, 2025
c02d83f
refactor chi_get_proper_pop
dcolombara May 14, 2025
6a36002
FIX chi_calc
dcolombara May 15, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions DESCRIPTION
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -35,6 +35,7 @@ Imports:
Remotes:
github::PHSKC-APDE/rads, github::PHSKC-APDE/dtsurvey
Suggests:
devtools,
httr,
keyring,
knitr,
Expand Down
8 changes: 8 additions & 0 deletions NAMESPACE
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,6 +15,7 @@ export(chi_get_proper_pop)
export(chi_get_yaml)
export(chi_keep_proper_ages)
export(chi_qa_tro)
export(chi_suppress_results)
export(chi_update_sql)
import(data.table)
import(dtsurvey)
Expand All @@ -30,10 +31,12 @@ importFrom(DBI,dbGetQuery)
importFrom(DBI,dbWriteTable)
importFrom(data.table,"%between%")
importFrom(data.table,":=")
importFrom(data.table,':=')
importFrom(data.table,.GRP)
importFrom(data.table,.SD)
importFrom(data.table,CJ)
importFrom(data.table,`:=`)
importFrom(data.table,alloc.col)
importFrom(data.table,as.data.table)
importFrom(data.table,between)
importFrom(data.table,copy)
Expand All @@ -46,18 +49,23 @@ importFrom(data.table,rbindlist)
importFrom(data.table,set)
importFrom(data.table,setDT)
importFrom(data.table,setcolorder)
importFrom(data.table,setkey)
importFrom(data.table,setnames)
importFrom(data.table,setorder)
importFrom(data.table,setorderv)
importFrom(data.table,tstrsplit)
importFrom(data.table,uniqueN)
importFrom(future,plan)
importFrom(future.apply,future_lapply)
importFrom(glue,glue)
importFrom(glue,glue_sql)
importFrom(odbc,odbc)
importFrom(progressr,handler_progress)
importFrom(progressr,handlers)
importFrom(progressr,progressor)
importFrom(progressr,with_progress)
importFrom(qs,qread)
importFrom(qs,qsave)
importFrom(rads,calc)
importFrom(rads,round2)
importFrom(rads,string_clean)
Expand Down
33 changes: 25 additions & 8 deletions R/chi_calc.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -267,15 +267,32 @@ chi_calc <- function(ph.data = NULL,


# Tidy results ----
# When there are no observation in a row, rads::calc() gives NA for numerator, but want zero ----
tempCHIest[is.na(numerator), `:=` (
# When we have no events, but a valid denominator ----
tempCHIest[
(is.na(numerator) | numerator == 0) & !is.na(denominator) & denominator > 0,
`:=` (
result = 0,
se = 0,
lower_bound = 0,
upper_bound = 0,
numerator = 0,
numerator = ifelse(is.na(numerator), 0, numerator),
rse = NA # undefined because mean will be zero
)]
)
]

# When we have no events in the denominator ----
tempCHIest[
(is.na(denominator) | denominator == 0),
`:=` (
result = NA,
se = NA,
lower_bound = NA,
upper_bound = NA,
numerator = 0, # This might not be necessary depending on your needs
denominator = 0, # Setting NA denominator to 0
rse = NA
)
]

# drop when cat1_group is missing (e.g., cat1 == 'Regions' and region is NA) ----
tempCHIest <- tempCHIest[!is.na(cat1_group)]
Expand Down Expand Up @@ -367,10 +384,10 @@ chi_calc <- function(ph.data = NULL,
tempCHIest[, data_source := source_name]

if(small_num_suppress == TRUE){
tempCHIest <- rads::suppress(sup_data = tempCHIest,
suppress_range = c(suppress_low, suppress_high),
secondary = T,
secondary_exclude = cat1_varname != 'race3')
tempCHIest <- apde.chi.tools::chi_suppress_results(ph.data = tempCHIest,
suppress_range = c(suppress_low, suppress_high),
secondary = T,
secondary_exclude = cat1_varname != 'race3')
} else {tempCHIest[, suppression := NA_character_]}

tempCHIest[rse>=30 | numerator == 0, caution := "!"]
Expand Down
16 changes: 8 additions & 8 deletions R/chi_compare_estimates.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -84,8 +84,8 @@ chi_compare_estimates <- function(OLD = NULL, NEW = NULL, OLD.year = NULL, NEW.y

# calculate percent differences between old (x) and new(y)
comp[, relative.diff := round2(abs((result.x - result.y) / result.x)*100, 1)]
comp[result_type != "rate", absolute.diff := round2(abs(result.x - result.y)*100, 1)]
comp[result_type == "rate", absolute.diff := round2(abs(result.x - result.y), 1)]
comp[grepl("mean|proportion", result_type, ignore.case = T), absolute.diff := round2(abs(result.x - result.y)*100, 1)]
comp[grepl("rate", result_type, ignore.case = T), absolute.diff := round2(abs(result.x - result.y), 1)]
comp <- comp[!is.na(absolute.diff)] # drop if absolute difference is NA

# order variables
Expand All @@ -111,18 +111,18 @@ chi_compare_estimates <- function(OLD = NULL, NEW = NULL, OLD.year = NULL, NEW.y
# First, identify whether to use absolute or relative change for each indicator_key
qa_type = NEW[tab=='_kingcounty']
qa_type[, qa_type := 'relative']
qa_type[result_type=='proportion' & result >= 0.05, qa_type := 'absolute']
qa_type[result_type=='rate' & result >= 5, qa_type := 'absolute']
qa_type[grepl('mean|proportion', result_type, ignore.case = T) & result >= 0.05, qa_type := 'absolute']
qa_type[grepl('rate', result_type, ignore.case = T) & result >= 5, qa_type := 'absolute']
qa_type <- qa_type[, list(indicator_key, qa_type)]

# Merge on qa_type
comp <- merge(comp, qa_type, by = 'indicator_key', all = T)

# Identify notable changes
comp[qa_type == 'absolute' & result_type=='proportion' & absolute.diff >= 3, notable := 1] # absolute difference was multiplied by 100, so assess with >= 3
comp[qa_type == 'absolute' & result_type=='rate' & absolute.diff >= 3, notable := 1]
comp[qa_type == 'relative' & result_type=='proportion' & relative.diff >= 50, notable := 1] # absolute difference was multiplied by 100, so assess with >= 3
comp[qa_type == 'relative' & result_type=='rate' & relative.diff >= 50, notable := 1]
comp[qa_type == 'absolute' & grepl('mean|proportion', result_type, ignore.case = T) & absolute.diff >= 3, notable := 1] # absolute difference was multiplied by 100, so assess with >= 3
comp[qa_type == 'absolute' & grepl('rate', result_type, ignore.case = T) & absolute.diff >= 3, notable := 1]
comp[qa_type == 'relative' & grepl('mean|proportion', result_type, ignore.case = T) & relative.diff >= 50, notable := 1] # absolute difference was multiplied by 100, so assess with >= 3
comp[qa_type == 'relative' & grepl('rate', result_type, ignore.case = T) & relative.diff >= 50, notable := 1]

# Return object ----
return(comp)
Expand Down
Loading