From 4dd8e13d6b4face6a8a39c35d4c8375e21bd4781 Mon Sep 17 00:00:00 2001
From: Marty Oehme <marty.oehme@gmail.com>
Date: Wed, 10 Jan 2024 17:27:48 +0100
Subject: [PATCH] chore(repo): Rename data loading module

---
 pyproject.toml                | 2 +-
 scoping_review.qmd            | 4 ++--
 src/{data.py => load_data.py} | 4 ++--
 src/{load_yaml.py => yaml.py} | 0
 4 files changed, 5 insertions(+), 5 deletions(-)
 rename src/{data.py => load_data.py} (90%)
 rename src/{load_yaml.py => yaml.py} (100%)

diff --git a/pyproject.toml b/pyproject.toml
index 8b52d0c..a5a08ad 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -41,7 +41,7 @@ cmd = "nvim"
 [tool.poe.tasks.extract]
 help = "Extract the csv data from raw yaml files"
 shell = """
-python src/data.py > 02-data/processed/extracted.csv
+python src/load_data.py > 02-data/processed/extracted.csv
 """
 [tool.poe.tasks.milestone]
 help = "Extract, render, commit and version a finished artifact"
diff --git a/scoping_review.qmd b/scoping_review.qmd
index 990a79a..776bf37 100644
--- a/scoping_review.qmd
+++ b/scoping_review.qmd
@@ -57,7 +57,7 @@ bib_sample = bibtexparser.parse_string(bib_string)
 
 ```{python}
 # load relevant studies
-from src import data
+from src import load_data
 
 # load zotero-based metadata: citations and uses
 zot_df = pd.DataFrame([
@@ -91,7 +91,7 @@ def countries_to_income_groups(countries:str):
     return ";".join(res)
 
 
-bib_df = (data.from_yml(f"{PROCESSED_DATA}")
+bib_df = (load_data.from_yml(f"{PROCESSED_DATA}")
     .assign(
         doi=lambda _df: _df["uri"].str.extract(r"https?://(?:dx\.)?doi\.org/(.*)", expand=False),
         zot_cited=lambda _df: _df["doi"].map(zot_df["cited"]),
diff --git a/src/data.py b/src/load_data.py
similarity index 90%
rename from src/data.py
rename to src/load_data.py
index 460b96b..8fddf72 100644
--- a/src/data.py
+++ b/src/load_data.py
@@ -2,9 +2,9 @@ import io
 from pathlib import Path
 import sys
 try:
-    import src.load_yaml as yaml # for quarto document scripts
+    import src.yaml as yaml # for quarto document scripts
 except ModuleNotFoundError:
-    import load_yaml as yaml # for directly running the package
+    import yaml as yaml # for directly running the package
 from pandas import DataFrame, read_csv
 
 DEFAULT_YAML_PATH = Path("02-data/processed")
diff --git a/src/load_yaml.py b/src/yaml.py
similarity index 100%
rename from src/load_yaml.py
rename to src/yaml.py