From 28f44a19540e968f0da1e2f237f8c9021feb5f95 Mon Sep 17 00:00:00 2001
From: Jakub Dylag <jjd1c23@soton.ac.uk>
Date: Fri, 24 Jan 2025 13:49:21 +0000
Subject: [PATCH] rename JSON "meldb_phenotypes" -> "concept_set"
---
README.md | 8 ++++----
main.py | 10 +++++-----
report.py | 8 ++++----
3 files changed, 13 insertions(+), 13 deletions(-)
diff --git a/README.md b/README.md
index aa00cae..0eab45d 100644
--- a/README.md
+++ b/README.md
@@ -103,7 +103,7 @@ The JSON configuration file specifies how input codes are grouped into **concept
### Folder and File Definitions
-The `"codes"` section defines the location and description of all input files required for processing. Each `"folder"` is defined as an object of within the `"codes"` list. Similarily all files are objects within the `"files"` list.
+The `"codes"` section defines the location and description of all input medical coding lists required for processing. Each `"folder"` is defined as an object of within the `"codes"` list. Similarily all files are objects within the `"files"` list.
- **`folder`**: Specifies the directory containing the input files.
- **`description`**: Provides a brief summary of the content or purpose of the files, often including additional context such as the date the data was downloaded.
@@ -163,9 +163,9 @@ The `"concept_sets"` object defines the structure and rules for grouping input c
- **`concept_set_status`**: Maps to the column indicating the status of the concept set. Only concept sets the **"AGREED"** status will be outputted!
- **`metadata`**: A list of additional columns in the CSV file that should be copied to the output for descriptive or contextual purposes.
-The `"codes"` object specifies the source files containing input codes and assigns them to the corresponding concept sets through the `"meldb_phenotypes"` field.
+The `"codes"` object specifies the source files containing input codes and assigns them to the corresponding concept sets through the `"concept_set"` field.
- - **`meldb_phenotypes`**: Lists the concept sets to which all codes within this file will be assigned.
+ - **`concept_set`**: Lists the concept sets to which all codes within this file will be assigned.
```json
{
@@ -185,7 +185,7 @@ The `"codes"` object specifies the source files containing input codes and assig
"files": [
{
"file": "WP02_SAIL_WILK_matched_drug_codes_with_categories.xlsx",
- "meldb_phenotypes": ["ALL_MEDICATIONS"]
+ "concept_set": ["ALL_MEDICATIONS"]
}
]
}
diff --git a/main.py b/main.py
index f1c082a..81832ed 100644
--- a/main.py
+++ b/main.py
@@ -226,21 +226,21 @@ def run_all(mapping_file, target_code_type,
if len(df) == 0:
pass
# out = df
- elif ("meldb_phenotypes" in file) and isinstance(df, pd.core.frame.DataFrame):
+ elif ("concept_set" in file) and isinstance(df, pd.core.frame.DataFrame):
out = map_file(df,
target_code_type,
out,
- concepts=file["meldb_phenotypes"],
+ concepts=file["concept_set"],
meta_columns=meta_columns,
no_translate=no_translate)
- elif ("meldb_phenotypes_categories" in file) and isinstance(df, pd.core.groupby.generic.DataFrameGroupBy):
+ elif ("concept_set_categories" in file) and isinstance(df, pd.core.groupby.generic.DataFrameGroupBy):
meta_columns.remove(divide_col) #delete categorical column
for cat, grp in df:
- if cat in file["meldb_phenotypes_categories"].keys(): #check if category is mapped
+ if cat in file["concept_set_categories"].keys(): #check if category is mapped
grp = grp.drop(columns=[divide_col]) #delete categorical column
print("Category:", cat)
out = map_file(grp, target_code_type, out,
- concepts = file["meldb_phenotypes_categories"][cat],
+ concepts = file["concept_set_categories"][cat],
meta_columns=meta_columns)
else:
diff --git a/report.py b/report.py
index c36a298..d4069c3 100644
--- a/report.py
+++ b/report.py
@@ -11,11 +11,11 @@ def get_json_files(folders):
if "files" in folder:
for file in folder["files"]:
file_path = folder["folder"]+"/"+file["file"]
- if "meldb_phenotypes" in file:
- for concept in file["meldb_phenotypes"]:
+ if "concept_set" in file:
+ for concept in file["concept_set"]:
out.append({"json_concept":concept, "filepath":file_path, "json_code_types":list(file["columns"].keys())})
- elif "meldb_phenotypes_categories" in file:
- for code, concept in file["meldb_phenotypes_categories"].items():
+ elif "concept_set_categories" in file:
+ for code, concept in file["concept_set_categories"].items():
out.append({"json_concept":concept[0], "filepath":file_path, "json_code_types":list(file["columns"].keys())})
else:
out.append({"json_concept":None, "filepath":file_path})
--
GitLab