Skip to content

amended denominator criteria for annual counts #34

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
YaminaB merged 2 commits into from
Apr 2, 2026
Merged

amended denominator criteria for annual counts #34

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
54f61fc
amended denominator criteria for annual counts
YaminaB Apr 2, 2026
8eae6ef
fixed overall row in date of uk entry cohort file
YaminaB Apr 2, 2026
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
4 changes: 1 addition & 3 deletions analysis/process_date_of_uk_entry_cohort.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,7 +25,6 @@ output_file <- "output/tables/demographics_date_of_uk_entry_cohort.csv"
args <- commandArgs(trailingOnly=TRUE)
print(commandArgs(trailingOnly=TRUE))


# Import data ----
cohort <- read_feather(cohort_file) %>%
mutate(
Expand All @@ -45,7 +44,6 @@ vars_to_summarise <- c(
"imd_quintile"
)


rounding <- function(vars) {
case_when(vars == 0 ~ 0,
vars > 7 ~ round(vars / 5) * 5)
Expand All @@ -54,7 +52,7 @@ rounding <- function(vars) {
table_freq_overall <- cohort %>%
group_by(any_migrant) %>%
summarise(
n = rounding(nrow(cohort)),
n = rounding(n()),
percentage = 100) %>%
mutate(
subgroup = "All",
Expand Down
31 changes: 26 additions & 5 deletions analysis/utilities.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,10 +14,31 @@ def build_common_vars(INTERVAL):
# -------------------
was_alive_on_1Jan = patients.is_alive_on(INTERVAL.start_date)

was_registered_on1Jan = (
practice_registrations.for_patient_on(INTERVAL.start_date)
.exists_for_patient()
)
was_registered_at_any_point_during_interval = practice_registrations.where(
# registered for the entire interval
((practice_registrations.start_date.is_on_or_before(INTERVAL.start_date))
& (practice_registrations.end_date.is_on_or_after(INTERVAL.end_date))) |

# registered during the interval and end date is after the interval end date
((practice_registrations.start_date.is_after(INTERVAL.start_date))
& (practice_registrations.end_date.is_on_or_after(INTERVAL.end_date))) |

# registered before the interval and registration is ongoing
((practice_registrations.start_date.is_on_or_before(INTERVAL.start_date)) &
(practice_registrations.end_date.is_null())) |

# registered after interval start date and registration is ongoing
((practice_registrations.start_date.is_after(INTERVAL.start_date)) &
(practice_registrations.end_date.is_null())) |

# registered before the interval start date and end date is before the end date, but after the start date
((practice_registrations.start_date.is_before(INTERVAL.start_date)) &
(practice_registrations.end_date.is_between_but_not_on(INTERVAL.start_date, INTERVAL.end_date))) |

# registered for part of the interval only
((practice_registrations.start_date.is_between_but_not_on(INTERVAL.start_date, INTERVAL.end_date)) &
(practice_registrations.end_date.is_between_but_not_on(INTERVAL.start_date, INTERVAL.end_date)))
).exists_for_patient()

has_recorded_sex = patients.sex.is_in(["male", "female"])

Expand All @@ -28,7 +49,7 @@ def build_common_vars(INTERVAL):

denominator = (
was_alive_on_1Jan
& was_registered_on1Jan
& was_registered_at_any_point_during_interval
& has_recorded_sex
& has_possible_age
)
Expand Down