.gitignore

@@ -1,14 +1,6 @@
-/documentation/DB
-/documentation/library
-/output
-/manuscript/*_files/
-
-# Elsevier journal target:
-# Ignore bibliography style, spl (for natbib?) and latex class
-# since they don't get deleted after compilation
-*.spl
-*.bst
-*.cls
+/03-documentation/DB
+/03-documentation/library
+/04-outputs
 
 # Created by https://www.toptal.com/developers/gitignore/api/-f,python,linux,vim,quarto,markdown,jupyternotebooks
 # Edit at https://www.toptal.com/developers/gitignore?templates=-f,python,linux,vim,quarto,markdown,jupyternotebooks

00-notebooks/bibmanip.qmd

@@ -1,5 +1,5 @@
 ---
-bibliography: ../data/intermediate/zotero-library.bib
+bibliography: ../02-data/intermediate/zotero-library.bib
 csl: /home/marty/documents/library/utilities/styles/APA-7.csl
 papersize: A4
 linestretch: 1.5
@@ -22,8 +22,7 @@ subtitle: Addressing inequalities in the World of Work
 ```{python}
 #| echo: false
 from pathlib import Path
-import src.globals as g
-data_dir = g.DATA_DIR
+data_dir=Path("../02-data")
 
 ## standard imports
 from IPython.core.display import Markdown as md
@@ -44,9 +43,8 @@ sns.set_style("whitegrid")
 import bibtexparser
 
 bib_string=""
-sample_dir = g.REFERENCE_DATA.joinpath("01_wos-sample_2023-11-02")
-print(f"path: {sample_dir.absolute()}")
-for partial_bib in sample_dir.glob("*.bib"):
+print(f"path: {data_dir.joinpath('raw/01_wos-sample_2023-11-02').absolute()}")
+for partial_bib in data_dir.joinpath("raw/01_wos-sample_2023-11-02").glob("*.bib"):
     with open(partial_bib) as f:
         bib_string+="\n".join(f.readlines())
 sample = bibtexparser.parse_string(bib_string)

00-notebooks/explore.qmd

@@ -1,5 +1,5 @@
 ---
-bibliography: data/intermediate/zotero-library.bib
+bibliography: 02-data/intermediate/zotero-library.bib
 title: Grab yml
 ---
 
@@ -184,18 +184,23 @@ from matplotlib import pyplot as plt
 import seaborn as sns
 from tabulate import tabulate
 import bibtexparser
-import src.globals as g
 
 sns.set_style("whitegrid")
 
+DATA_DIR=Path("./02-data")
+RAW_DATA=DATA_DIR.joinpath("raw")
+WORKING_DATA=DATA_DIR.joinpath("intermediate")
+PROCESSED_DATA=DATA_DIR.joinpath("processed")
+SUPPLEMENTARY_DATA=DATA_DIR.joinpath("supplementary")
+
 bib_string=""
-for partial_bib in g.REFERENCE_DATA.glob("**/*.bib"):
+for partial_bib in RAW_DATA.glob("**/*.bib"):
     with open(partial_bib) as f:
         bib_string+="\n".join(f.readlines())
 bib_sample_raw_db = bibtexparser.parse_string(bib_string)
 
 bib_string=""
-for partial_bib in g.REFERENCE_DATA.joinpath("zotero-library.bib"):
+for partial_bib in WORKING_DATA.glob("**/*.bib"):
     with open(partial_bib) as f:
         bib_string+="\n".join(f.readlines())
 bib_sample = bibtexparser.parse_string(bib_string)
@@ -217,10 +222,10 @@ zot_df = pd.DataFrame([
 ], columns = ["doi", "cited", "usage", "keywords"]).drop_duplicates("doi").set_index("doi")
 
 # Add WB country grouping definitions (income group, world region)
-WB_COUNTRY_GROUPS_FILE = Path(f"{g.SUPPLEMENTARY_DATA}/wb-country-groupings.xlsx").resolve()
+WB_COUNTRY_GROUPS_FILE = Path(f"{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}")
+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"]),

00-notebooks/main-findings.qmd

@@ -15,7 +15,7 @@ import bibtexparser
 
 sns.set_style("whitegrid")
 
-DATA_DIR=Path("./data")
+DATA_DIR=Path("./02-data")
 RAW_DATA=DATA_DIR.joinpath("raw")
 WORKING_DATA=DATA_DIR.joinpath("intermediate")
 PROCESSED_DATA=DATA_DIR.joinpath("processed")
@@ -120,7 +120,7 @@ datavis:
 
 
 ```{python}
-findings_institutional = pd.read_csv("data/supplementary/findings-institutional.csv")
+findings_institutional = pd.read_csv("02-data/supplementary/findings-institutional.csv")
 findings_institutional
 from src.model import validity
 import math

00-notebooks/rank_validities.qmd

@@ -16,7 +16,7 @@ import bibtexparser
 
 sns.set_style("whitegrid")
 
-DATA_DIR=Path("./data")
+DATA_DIR=Path("./02-data")
 RAW_DATA=DATA_DIR.joinpath("raw")
 WORKING_DATA=DATA_DIR.joinpath("intermediate")
 PROCESSED_DATA=DATA_DIR.joinpath("processed")

00-notebooks/test-magma.qmd

@@ -1,5 +1,5 @@
 ---
-bibliography: data/intermediate/zotero-library.bib
+bibliography: 02-data/intermediate/zotero-library.bib
 csl: /home/marty/documents/library/utilities/styles/APA-7.csl
 papersize: A4
 linestretch: 1.5
@@ -28,10 +28,8 @@ zotero:
 ```{python}
 #| echo: false
 from pathlib import Path
-import src.globals as g
-DATA_DIR = g.DATA_DIR
-RAW_DATA = g.RAW_DATA
-BIB_PATH = g.REFERENCE_DATA.joinpath("01_wos-sample_2023-11-02")
+DATA_DIR=Path("./02-data")
+BIB_PATH = DATA_DIR.joinpath("raw/01_wos-sample_2023-11-02")
 
 ## standard imports
 from IPython.core.display import Markdown as md

02-data/processed/relevant/Dustmann2012.yml

@@ -15,7 +15,7 @@ group: working mothers
 data: national administrative Social Security Records (1975-2008)
 
 design: quasi-experimental
-method: difference-in-difference analysis; regression discontinuity
+method: difference-in-difference analysis
 sample: 13000
 unit: individual
 representativeness: national, census