Skip to content

Exclude med status == 6, and add to gitignore all things qmd related #70

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
viv3ckj merged 2 commits into from
Jun 10, 2026
Merged

Exclude med status == 6, and add to gitignore all things qmd related #70

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
f3e4e7a
Exclude med status == 6, and add to gitignore all things qmd related
viv3ckj Jun 10, 2026
a7d6e14
filter out the med status == 6
viv3ckj Jun 10, 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
8 changes: 7 additions & 1 deletion .gitignore
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,4 +11,10 @@ venv/
.Rproj.user/
released_output/*
reports/pharmacy_first_data_development.html
reports/resources/*
reports/resources/*
reports/pharmacy_first_data_development_files/*
pharmacy_first_data_development.*
publish
justfile
reports/_publish_ids.yml
lib/validation/data/df_bsa_validation.csv
15 changes: 8 additions & 7 deletions analysis/data_development_med_status_post_counts.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,18 +3,19 @@ library(arrow)
library(dplyr)

selected_variables_list <- list(
"post_anymed" <- paste0("post_anymed_", paste0("status", 0:28)),
"post_anypfid" <- paste0("post_anypfid_", paste0("status", 0:28)),
"post_anypfdate" <- paste0("post_anypfdate_", paste0("status", 0:28)),
"post_pfmed" <- paste0("post_pfmed_", paste0("status", 0:28)),
"post_pfmedid" <- paste0("post_pfmedid_", paste0("status", 0:28)),
"post_pfmedpfdate" <- paste0("post_pfmedpfdate_", paste0("status", 0:28))
post_anymed = paste0("post_anymed_", paste0("status", c(0:5, 7:28))),
post_anypfid = paste0("post_anypfid_", paste0("status", c(0:5, 7:28))),
post_anypfdate = paste0("post_anypfdate_", paste0("status", c(0:5, 7:28))),
post_pfmed = paste0("post_pfmed_", paste0("status", c(0:5, 7:28))),
post_pfmedid = paste0("post_pfmedid_", paste0("status", c(0:5, 7:28))),
post_pfmedpfdate = paste0("post_pfmedpfdate_", paste0("status", c(0:5, 7:28)))
)

# Load data
df_med_status <- arrow::read_feather(
here::here("output", "data_development", "med_status_data_development.arrow")
) %>% select(all_of(unlist(selected_variables_list)))
) %>%
dplyr::select(-dplyr::matches("status6$"))

print("Load data successfully")

Expand Down
19 changes: 11 additions & 8 deletions analysis/data_development_med_status_pre_counts.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,23 +3,26 @@ library(arrow)
library(dplyr)

selected_variables_list <- list(
"pre_anymed" <- paste0("pre_anymed_", paste0("status", 0:28)),
"pre_anypfid" <- paste0("pre_anypfid_", paste0("status", 0:28)),
"pre_anypfdate" <- paste0("pre_anypfdate_", paste0("status", 0:28)),
"pre_pfmed" <- paste0("pre_pfmed_", paste0("status", 0:28)),
"pre_pfmedid" <- paste0("pre_pfmedid_", paste0("status", 0:28)),
"pre_pfmedpfdate" <- paste0("pre_pfmedpfdate_", paste0("status", 0:28))
pre_anymed = paste0("pre_anymed_", paste0("status", c(0:5, 7:28))),
pre_anypfid = paste0("pre_anypfid_", paste0("status", c(0:5, 7:28))),
pre_anypfdate = paste0("pre_anypfdate_", paste0("status", c(0:5, 7:28))),
pre_pfmed = paste0("pre_pfmed_", paste0("status", c(0:5, 7:28))),
pre_pfmedid = paste0("pre_pfmedid_", paste0("status", c(0:5, 7:28))),
pre_pfmedpfdate = paste0("pre_pfmedpfdate_", paste0("status", c(0:5, 7:28)))
)

# Load data
expected <- unlist(selected_variables_list)

df_med_status <- arrow::read_feather(
here::here("output", "data_development", "med_status_data_development.arrow")
) %>% select(all_of(unlist(selected_variables_list)))
) %>%
dplyr::select(-dplyr::matches("status6$"))

print("Load data successfully")

# Check that all names defined in data_extractions are in df df_med_status
# all(unlist(selected_variables_list) %in% names(df_med_status))
#all(unlist(selected_variables_list) %in% names(df_med_status))

print("Define variable names successfully")

Expand Down
2 changes: 2 additions & 0 deletions analysis/dataset_definition_med_status_data_development.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -207,6 +207,8 @@
# This will add 6 x 28 = 168 new columns
for desc, selected_medications in selected_medications_dict.items():
for status in range(29):
if status == 6:
continue
count_med_status_query = selected_medications.where(
selected_medications.medication_status.is_in([status])
).count_for_patient()
Expand Down
Loading