chore(repo): Move yml files to extracted data dir

README.md

@@ -1,18 +1,21 @@
 # Scoping Review: Inequalities on the Labour Market
 
-
 This repository contains all data, modelling and processing source code and the complete textual content to reproduce the scoping review study.
 The most up-to-date version of this repository can always be found [here](https://git.martyoeh.me/professional/wow-inequalities).
 
-Raw, intermediate and processed data can all be found in the `data/` directory:
-Raw data include the unmodified database queries using the scoping review search terms.
-Intermediate data are made up of the bibtex file produced by Zotero, after tagging and sorting in a Zotero library, ready to be re-imported into the application.
-Processed data include the fully extracted studies which make up the main sample for the review.
+Raw references, extracted and processed data can all be found in the `data/` directory:
+Reference data include the unmodified database queries using the scoping review search terms,
+and the bibtex file produced by Zotero after tagging and sorting in a Zotero library, ready to be re-imported into the application.
+Extracted data include the fully extracted studies which make up the main sample for the review.
+Processed data are ready to import into a dataframe or visualize in a report.
 
-The full article text and code can be found in the `scoping_review.qmd` file.
-It makes use of supplementary processing code which resides in the `src/` directory,
+All full texts and visualization code reside in the `manuscripts/` directory.
+The full working paper text and code can be found in the `scoping_review.qmd` file.
+The full article text can be found in the `article.qmd` file.
+
+They both make use of supplementary extraction and processing code which resides in the `src/` directory,
 mainly to load processed data from the `data/` directory and turn it into `.csv` data,
-as well as pre-processing those for visualization and validity ranking within the study.
+as well as pre-processing for visualization and validity ranking within the study.
 
 ## Execution and Reproduction
 

manuscript/meeting_eoy.qmd

@@ -52,7 +52,7 @@ zot_df = pd.DataFrame([
 WB_COUNTRY_GROUPS_FILE = Path(f"{g.SUPPLEMENTARY_DATA}/wb-country-groupings.xlsx").resolve()
 df_country_groups = pd.read_excel(WB_COUNTRY_GROUPS_FILE).set_index("Economy")
 
-bib_df = (load_data.from_yml(f"{g.PROCESSED_DATA}/relevant")
+bib_df = (load_data.from_yml(f"{g.EXTRACTED_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"]),

src/extract/load_data.py

@@ -9,7 +9,11 @@ try:
 except ModuleNotFoundError:
     import yml as yaml  # for directly running the package
 
-DEFAULT_YAML_PATH = Path("data/processed")
+try:
+    import src.globals as g
+    DEFAULT_YAML_PATH = g.EXTRACTED_DATA
+except ModuleNotFoundError:
+    DEFAULT_YAML_PATH = Path("data")
 
 
 def to_tsv(studies: list[dict]) -> str:

src/globals.py

@@ -5,7 +5,7 @@ PROJECT_DIR = Path(os.getenv("QUARTO_PROJECT_DIR", "."))
 
 DATA_DIR = PROJECT_DIR.joinpath("data")
 
-PROCESSED_DATA = DATA_DIR.joinpath("processed")
-SUPPLEMENTARY_DATA = DATA_DIR.joinpath("supplementary")
-
+EXTRACTED_DATA = DATA_DIR.joinpath("extracted")
 REFERENCE_DATA = DATA_DIR.joinpath("references")
+SUPPLEMENTARY_DATA = DATA_DIR.joinpath("supplementary")
+PROCESSED_DATA = DATA_DIR.joinpath("processed")

src/process/generate_dataframes.py

@@ -20,7 +20,7 @@ from src.extract import load_data as load
 
 # each observation in a single dataframe
 df = meta.observations_with_metadata_df(
-    raw_observations = load.from_yml(g.PROCESSED_DATA),
+    raw_observations = load.from_yml(g.EXTRACTED_DATA),
     study_metadata = meta.bib_metadata_df(bib_sample),
     country_groups = meta.country_groups_df(Path(f"{g.SUPPLEMENTARY_DATA}/wb-country-groupings.xlsx")),
 )