chore(repo): Move manuscripts to separate dir

Both the manuscripts for the working paper and the article are now
collected in a separate manuscripts folder.

_quarto-article.yml

@@ -1,7 +1,7 @@
 project:
   type: default
   render:
-    - article.qmd
+    - manuscript/article.qmd
 
 format:
   elsevier-html:

_quarto-workingpaper.yml

@@ -1,9 +1,9 @@
 project:
   render:
-    - presentation_summary.md
+    - manuscript/presentation_summary.md
-    - notes.qmd
+    - manuscript/notes.qmd
-    - meeting_eoy.qmd
+    - manuscript/meeting_eoy.qmd
-    - scoping_review.qmd
+    - manuscript/scoping_review.qmd
 
 toc: true
 format:

manuscript/article.qmd

@@ -102,7 +102,7 @@ with a focus on the narrowing criteria specified in @tbl-inclusion-criteria.
 ::: {#tbl-inclusion-criteria}
 
 ```{python}
-inclusion_criteria = pd.read_csv("data/supplementary/inclusion-criteria.tsv", sep="\t")
+inclusion_criteria = pd.read_csv(f"{g.SUPPLEMENTARY_DATA}/inclusion-criteria.tsv", sep="\t")
 Markdown(tabulate(inclusion_criteria, showindex=False, headers="keys", tablefmt="grid"))
 ```
 
@@ -152,7 +152,7 @@ ultimately resulting in the process represented in the PRISMA chart in @fig-pris
 ```{mermaid}
 %%| label: fig-prisma
 %%| fig-cap: PRISMA flowchart for scoping process
-%%| file: data/processed/prisma.mmd
+%%| file: ../data/processed/prisma.mmd
 ```
 
 All relevant data concerning both their major findings and statistical significance are then extracted from the individual studies into a collective results matrix.
@@ -225,7 +225,7 @@ def strength_for(val):
     ]
 
 
-findings_institutional = pd.read_csv("data/supplementary/findings-institutional.csv")
+findings_institutional = pd.read_csv(f"{g.SUPPLEMENTARY_DATA}/findings-institutional.csv")
 
 outp = Markdown(
     tabulate(
@@ -695,7 +695,7 @@ Another reason could be the actual implementation of different policy programmes
 ::: {#appatbl-wow-terms}
 
 ```{python}
-terms_wow = pd.read_csv("data/supplementary/terms_wow.csv")
+terms_wow = pd.read_csv(f"{g.SUPPLEMENTARY_DATA}/terms_wow.csv")
 Markdown(tabulate(terms_wow.fillna(""), showindex=False, headers="keys", tablefmt="grid"))
 ```
 
@@ -706,7 +706,7 @@ World of work term cluster
 ::: {#appatbl-intervention-terms}
 
 ```{python}
-terms_policy = pd.read_csv("data/supplementary/terms_policy.csv")
+terms_policy = pd.read_csv(f"{g.SUPPLEMENTARY_DATA}/terms_policy.csv")
 # different headers to include 'social norms'
 headers = ["General", "Institutional", "Structural", "Agency & social norms"]
 Markdown(tabulate(terms_policy.fillna(""), showindex=False, headers=headers, tablefmt="grid"))
@@ -719,7 +719,7 @@ Policy intervention term cluster
 ::: {#appatbl-inequality-terms}
 
 ```{python}
-terms_inequality = pd.read_csv("data/supplementary/terms_inequality.csv")
+terms_inequality = pd.read_csv(f"{g.SUPPLEMENTARY_DATA}/terms_inequality.csv")
 Markdown(tabulate(terms_inequality.fillna(""), showindex=False, headers="keys", tablefmt="grid"))
 ```
 

manuscript/meeting_eoy.qmd

@@ -1,5 +1,5 @@
 ---
-bibliography: data/intermediate/zotero-library.bib
+bibliography: ../data/intermediate/zotero-library.bib
 csl: /home/marty/documents/library/utilities/styles/APA-7.csl
 papersize: A4
 linestretch: 1.5
@@ -30,26 +30,22 @@ import bibtexparser
 
 sns.set_style("whitegrid")
 
-DATA_DIR=Path("./data")
+from src import globals as g
-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 RAW_DATA.glob("**/*.bib"):
+for partial_bib in g.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 WORKING_DATA.glob("**/*.bib"):
+for partial_bib in g.WORKING_DATA.glob("**/*.bib"):
     with open(partial_bib) as f:
         bib_string+="\n".join(f.readlines())
 bib_sample = bibtexparser.parse_string(bib_string)
 
 # load relevant studies
-from src import load_data
+from src.extract import load_data
 
 # load zotero-based metadata: citations and uses
 zot_df = pd.DataFrame([
@@ -63,10 +59,10 @@ 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"{SUPPLEMENTARY_DATA}/wb-country-groupings.xlsx").resolve()
+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"{PROCESSED_DATA}/relevant")
+bib_df = (load_data.from_yml(f"{g.PROCESSED_DATA}/relevant")
     .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"]),

manuscript/notes.qmd

@@ -1,5 +1,5 @@
 ---
-bibliography: data/intermediate/zotero-library.bib
+bibliography: ../data/intermediate/zotero-library.bib
 csl: /home/marty/documents/library/utilities/styles/APA-7.csl
 papersize: A4
 linestretch: 1.5
@@ -21,12 +21,7 @@ subtitle: Conceptual Definitions and Key Terms
 
 ```{python}
 #| echo: false
-from pathlib import Path
+from src import globals as g
-DATA_DIR=Path("./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")
 
 ## standard imports
 from IPython.core.display import Markdown as md
@@ -396,7 +391,7 @@ Policy *areas*, identified by @ILO2022b:
 #| label: tbl-inclusion-criteria
 #| tbl-cap: Study inclusion and exclusion scoping criteria {#tbl-inclusion-criteria}
 
-inclusion_criteria = pd.read_csv("data/supplementary/inclusion-criteria.tsv", sep="\t")
+inclusion_criteria = pd.read_csv(f"{g.SUPPLEMENTARY_DATA}/inclusion-criteria.tsv", sep="\t")
 md(tabulate(inclusion_criteria, showindex=False, headers="keys", tablefmt="grid"))
 ```
 
@@ -861,7 +856,7 @@ from @Pinto2021:
 ```{python}
 #| echo: false
 #| output: asis
-with open(f"{SUPPLEMENTARY_DATA}/query.txt") as f:
+with open(f"{g.SUPPLEMENTARY_DATA}/query.txt") as f:
     query = f.read()
 
 t3 = "`" * 3

manuscript/scoping_review.qmd

@@ -26,6 +26,7 @@ crossref:
 #| echo: false
 #| output: false
 import src.globals as g
+import re
 from IPython.display import display, Markdown, HTML
 import numpy as np
 import pandas as pd
@@ -303,7 +304,7 @@ with the search query requiring a term from the general column and one other col
 ```{python}
 #| label: tbl-wow-terms
 #| tbl-cap: World of work term cluster
-terms_wow = pd.read_csv("data/supplementary/terms_wow.csv")
+terms_wow = pd.read_csv(f"{g.SUPPLEMENTARY_DATA}/terms_wow.csv")
 Markdown(tabulate(terms_wow.fillna(""), showindex=False, headers="keys", tablefmt="grid"))
 ```
 
@@ -319,7 +320,7 @@ For the database query, a single term from the general category is required to b
 ```{python}
 #| label: tbl-intervention-terms
 #| tbl-cap: Policy intervention term cluster
-terms_policy = pd.read_csv("data/supplementary/terms_policy.csv")
+terms_policy = pd.read_csv(f"{g.SUPPLEMENTARY_DATA}/terms_policy.csv")
 # different headers to include 'social norms'
 headers = ["General", "Institutional", "Structural", "Agency & social norms"]
 Markdown(tabulate(terms_policy.fillna(""), showindex=False, headers=headers, tablefmt="grid"))
@@ -331,7 +332,7 @@ as seen in @tbl-inequality-terms.
 ```{python}
 #| label: tbl-inequality-terms
 #| tbl-cap: Inequality term cluster
-terms_inequality = pd.read_csv("data/supplementary/terms_inequality.csv")
+terms_inequality = pd.read_csv(f"{g.SUPPLEMENTARY_DATA}/terms_inequality.csv")
 Markdown(tabulate(terms_inequality.fillna(""), showindex=False, headers="keys", tablefmt="grid"))
 ```
 
@@ -355,7 +356,7 @@ with a focus on the narrowing criteria specified in @tbl-inclusion-criteria.
 ```{python}
 #| label: inclusion-criteria
 
-inclusion_criteria = pd.read_csv("data/supplementary/inclusion-criteria.tsv", sep="\t")
+inclusion_criteria = pd.read_csv(f"{g.SUPPLEMENTARY_DATA}/inclusion-criteria.tsv", sep="\t")
 Markdown(tabulate(inclusion_criteria, showindex=False, headers="keys", tablefmt="grid"))
 ```
 
@@ -382,7 +383,7 @@ The resulting process can be seen in @fig-prisma.
 ```{mermaid}
 %%| label: fig-prisma
 %%| fig-cap: PRISMA flowchart for scoping process
-%%| file: data/processed/prisma.mmd
+%%| file: ../data/processed/prisma.mmd
 ```
 
 All relevant data concerning both their major findings and statistical significance are then extracted from the individual studies into a collective results matrix.
@@ -559,7 +560,7 @@ study_strength_bins = {
 def strength_for(val):
     return list(study_strength_bins.keys())[list(study_strength_bins.values()).index(val)]
 
-findings_institutional = pd.read_csv("data/supplementary/findings-institutional.csv")
+findings_institutional = pd.read_csv(f"{g.SUPPLEMENTARY_DATA}/findings-institutional.csv")
 fd_df = validity.add_to_findings(findings_institutional, by_intervention, study_strength_bins)
 
 Markdown(tabulate(fd_df[["area of policy",  "internal_validity", "external_validity", "findings", "channels"]].fillna(""), showindex=False, headers=["area of policy", "internal strength", "external strength", "main findings", "channels"], tablefmt="grid"))
@@ -791,7 +792,7 @@ One limitation of the study is the modelling assumption that workers will have t
 #| label: tbl-findings-structural
 from src.model import validity
 
-findings_structural = pd.read_csv("data/supplementary/findings-structural.csv")
+findings_structural = pd.read_csv(f"{g.SUPPLEMENTARY_DATA}/findings-structural.csv")
 fd_df = validity.add_to_findings(findings_structural, by_intervention, study_strength_bins)
 
 Markdown(tabulate(fd_df[["area of policy",  "internal_validity", "external_validity", "findings", "channels"]].fillna(""), showindex=False, headers=["area of policy", "internal strength", "external strength", "main findings", "channels"], tablefmt="grid"))
@@ -1028,7 +1029,7 @@ Though the intervention clearly aims at strengthening some aspect of individual
 #| label: tbl-findings-agency
 from src.model import validity
 
-findings_agency = pd.read_csv("data/supplementary/findings-agency.csv")
+findings_agency = pd.read_csv(f"{g.SUPPLEMENTARY_DATA}/findings-agency.csv")
 fd_df = validity.add_to_findings(findings_agency, by_intervention, study_strength_bins)
 
 Markdown(tabulate(fd_df[["area of policy",  "internal_validity", "external_validity", "findings", "channels"]].fillna(""), showindex=False, headers=["area of policy", "internal strength", "external strength", "main findings", "channels"], tablefmt="grid"))