chore(code): Refactor data processing into module

src/extract/load_data.py

@@ -5,7 +5,7 @@ from pathlib import Path
 from pandas import DataFrame, read_csv
 
 try:
-    import src.yml as yaml  # for quarto document scripts
+    import src.extract.yml as yaml  # for quarto document scripts
 except ModuleNotFoundError:
     import yml as yaml  # for directly running the package
 

src/extract/raw_to_extracted_csv.py

@@ -8,6 +8,10 @@ try:
 except ModuleNotFoundError:
     from model import validity  # for directly running the package
 
+try:
+    import src.process.load_data as load
+except ModuleNotFoundError:
+    import load_data as load
 
 def extract(df: DataFrame, file: Path | StringIO) -> None:
     (
@@ -21,12 +25,11 @@ if __name__ == "__main__":
     import os
     import sys
 
-    import load_data
 
     if len(sys.argv) == 2:
-        df = load_data.from_yml(Path(sys.argv[1]))
+        df = load.from_yml(Path(sys.argv[1]))
     else:
-        df = load_data.from_yml()
+        df = load.from_yml()
 
     output = StringIO()
     extract(df, output)