Merge pull request #25 from zmek/update-notebooks-with-public-data

Update notebooks with public data
zmek · Sep 30, 2024 · a412e6c · a412e6c
2 parents 0d65ed9 + e062f7e
commit a412e6c
Show file tree

Hide file tree

Showing 69 changed files with 3,575 additions and 3,828 deletions.
diff --git a/README.md b/README.md
@@ -124,5 +124,3 @@ There are two arguments
 ## Acknowledgements
 
 This work was funded by a grant from the UCL Impact Funding. We are grateful to the Information Governance team and the Caldicott Guardian at UCLH for agreeing that we can release real patient data.
-
-
diff --git a/data-dictionaries/ed_visits_data_dictionary.csv b/data-dictionaries/ed_visits_data_dictionary.csv
diff --git a/data-dictionaries/ed_visits_data_dictionary.md b/data-dictionaries/ed_visits_data_dictionary.md
diff --git a/data-dictionaries/inpatient_arrivals_data_dictionary.csv b/data-dictionaries/inpatient_arrivals_data_dictionary.csv
@@ -0,0 +1,6 @@
+Column Name,Data Type,Description,Additional Details
+training_validation_test,object,"Whether visit snapshot is assigned to training, validation or test set","Frequencies: {test: 3,701, train: 7,730, valid: 1,244}"
+arrival_datetime,"datetime64[ns, UTC]",arrival_datetime,Date Range: 2031-03-01 00:03 - 2031-12-31 23:32
+sex,object,Sex of patient,"Frequencies: {F: 6,389, M: 6,286}"
+specialty,object,specialty,"Frequencies: {haem/onc: 1,340, medical: 6,932, nan: 217, paediatric: 1,091, surgical: 3,095}"
+is_child,bool,Is under age of 18 on day of arrival,"Frequencies: {False: 11,314, True: 1,361}"
diff --git a/data-dictionaries/inpatient_arrivals_data_dictionary.md b/data-dictionaries/inpatient_arrivals_data_dictionary.md
@@ -0,0 +1,7 @@
+| Column Name              | Data Type           | Description                                                            | Additional Details                                                                           |
+| :----------------------- | :------------------ | :--------------------------------------------------------------------- | :------------------------------------------------------------------------------------------- |
+| training_validation_test | object              | Whether visit snapshot is assigned to training, validation or test set | Frequencies: {test: 3,701, train: 7,730, valid: 1,244}                                       |
+| arrival_datetime         | datetime64[ns, UTC] | arrival_datetime                                                       | Date Range: 2031-03-01 00:03 - 2031-12-31 23:32                                              |
+| sex                      | object              | Sex of patient                                                         | Frequencies: {F: 6,389, M: 6,286}                                                            |
+| specialty                | object              | specialty                                                              | Frequencies: {haem/onc: 1,340, medical: 6,932, nan: 217, paediatric: 1,091, surgical: 3,095} |
+| is_child                 | bool                | Is under age of 18 on day of arrival                                   | Frequencies: {False: 11,314, True: 1,361}                                                    |
Original file line number	Diff line number	Diff line change
Expand Up		@@ -124,5 +124,3 @@ There are two arguments
		## Acknowledgements

		This work was funded by a grant from the UCL Impact Funding. We are grateful to the Information Governance team and the Caldicott Guardian at UCLH for agreeing that we can release real patient data.