Notebook report

.Rproj.user/23EE8BC9/pcs/source-pane.pper

@@ -0,0 +1,3 @@
+{
+    "activeTab": 3
+}

.gitignore

@@ -6,3 +6,8 @@ __pycache__
 output/*
 metadata/*
 venv/
+.Rproj.user
+*/Rhistory
+.Rhistory
+*/test.ipynb
+notebooks_jupyter/local_report_ethnicity.ipynb

README.md

@@ -1,22 +1,17 @@
 # ethnicity-short-data-report
 
-This is the code and configuration for ethnicity-short-data-report.
-
 You can run this project via [Gitpod](https://gitpod.io) in a web browser by clicking on this badge: [![Gitpod ready-to-code](https://img.shields.io/badge/Gitpod-ready--to--code-908a85?logo=gitpod)](https://gitpod.io/#https://github.com/opensafely/ethnicity-short-data-report)
 
-* The paper is [here]()
-* Raw model outputs, including charts, crosstabs, etc, are in `released_outputs/`
-* If you are interested in how we defined our variables, take a look at the [study definition](analysis/study_definition.py); this is written in `python`, but non-programmers should be able to understand what is going on there
-* If you are interested in how we defined our code lists, look in the [codelists folder](./codelists/).
-* Developers and epidemiologists interested in the framework should review [the OpenSAFELY documentation](https://docs.opensafely.org)
+[View on OpenSAFELY](https://jobs.opensafely.org/datalab/ethnicity-short-data-report/)
+
+Details of the purpose and any published outputs from this project can be found at the link above.
 
-# About the OpenSAFELY framework
+The contents of this repository MUST NOT be considered an accurate or valid representation of the study or its purpose. This repository may reflect an incomplete or incorrect analysis with no further ongoing work. The content has ONLY been made public to support the OpenSAFELY [open science and transparency principles](https://www.opensafely.org/about/#contributing-to-best-practice-around-open-science) and to support the sharing of re-usable code for other subsequent users. No clinical, policy or safety conclusions must be drawn from the contents of this repository.
 
-The OpenSAFELY framework is a Trusted Research Environment (TRE) for electronic
-health records research in the NHS, with a focus on public accountability and
-research quality.
+About the OpenSAFELY framework
+The OpenSAFELY framework is a Trusted Research Environment (TRE) for electronic health records research in the NHS, with a focus on public accountability and research quality.
 
-Read more at [OpenSAFELY.org](https://opensafely.org).
+Read more at [OpenSAFELY.org](https://opensafely.org/).
 
-# Licences
-As standard, research projects have a MIT license. 
+Licences
+As standard, research projects have a MIT license.

analysis/00_trim_snomed_codelist.r

@@ -0,0 +1,67 @@
+## splits the PRIMIS, CTV3 and SNOMED ethnicity codelists into 5 and 16 group categories
+
+library('tidyverse')
+library('sf')
+
+# # import data
+df_input <- read_csv(here::here("codelists","opensafely-ethnicity.csv"))
+group_split<-df_input %>%
+  group_split(Grouping_6)
+
+ethnicities<-c('white','mixed','asian','black','other')
+
+for (i in 1:5){
+  list<-group_split[i][[1]] %>% select(Code,Description)
+  write_csv(list,here::here("codelists",paste0("ethnicity_5_",ethnicities[i],".csv"))) 
+}
+
+df_input <- read_csv(here::here("codelists","opensafely-ethnicity-snomed-0removed.csv")) %>%
+  filter(Grouping_6!=0)
+group_split<-df_input %>%
+  group_split(Grouping_6)
+
+for (i in 1:5){
+  list<-group_split[i][[1]] %>% select(snomedcode,Ethnicity) %>% rename(Code = snomedcode)
+  write_csv(list,here::here("codelists",paste0("ethnicity_new_5_",ethnicities[i],".csv"))) 
+}
+
+df_input <- read_csv(here::here("codelists","primis-covid19-vacc-uptake-eth2001.csv"))
+group_split<-df_input %>%
+  group_split(grouping_6_id)
+
+for (i in 1:5){
+  list<-group_split[i][[1]] %>% select(code,term) %>% rename(Code=code)
+  write_csv(list,here::here("codelists",paste0("ethnicity_primis_5_",ethnicities[i],".csv"))) 
+}
+
+### group 16
+df_input <- read_csv(here::here("codelists","opensafely-ethnicity.csv"))
+group_split<-df_input %>%
+  group_split(Grouping_16)
+
+ethnicities_16<-c('White_British','White_Irish','Other_White','White_and_Black_Caribbean','White_and_Black_African','White_and_Asian','Other_Mixed','Indian','Pakistani','Bangladeshi','Other_Asian','Caribbean','African','Other_Black','Chinese','Any_other_ethnic_group')
+
+for (i in 1:16){
+  list<-group_split[i][[1]] %>% select(Code,Description)
+  write_csv(list,here::here("codelists",paste0("ethnicity_16_",ethnicities_16[i],".csv"))) 
+}
+
+df_input <- read_csv(here::here("codelists","opensafely-ethnicity-snomed-0removed.csv")) %>%
+  filter(Grouping_16!=0)
+
+group_split<-df_input %>%
+  group_split(Grouping_16)
+
+for (i in 1:16){
+  list<-group_split[i][[1]] %>% select(snomedcode,Ethnicity) %>% rename(Code = snomedcode)
+  write_csv(list,here::here("codelists",paste0("ethnicity_new_16_",ethnicities_16[i],".csv"))) 
+}
+
+df_input <- read_csv(here::here("codelists","primis-covid19-vacc-uptake-eth2001.csv"))
+group_split<-df_input %>%
+  group_split(grouping_16_id)
+
+for (i in 1:16){
+  list<-group_split[i][[1]] %>% select(code,term) %>% rename(Code=code)
+  write_csv(list,here::here("codelists",paste0("ethnicity_primis_16_",ethnicities_16[i],".csv"))) 
+}