chore(script): Refactor dataframe loading code

Improved readability of dataframe loading, used improved chaining
and some list comprehension to make it much less messy.
This commit is contained in:
Marty Oehme 2023-12-09 23:38:08 +01:00
parent 3f05283f6d
commit 8e7f99b20d
Signed by: Marty
GPG key ID: EDBF2ED917B2EF6A

View file

@ -55,6 +55,42 @@ for partial_bib in WORKING_DATA.glob("**/*.bib"):
bib_sample = bibtexparser.parse_string(bib_string)
```
```{python}
# load relevant studies
from src import data
# load zotero-based metadata: citations and uses
zot_df = pd.DataFrame([
[
entry["doi"] if "doi" in entry.fields_dict else None,
entry["times-cited"] if "times-cited" in entry.fields_dict else None,
entry["usage"] if "usage" in entry.fields_dict else None,
entry["keywords"] if "keywords" in entry.fields_dict else None,
]
for entry in bib_sample.entries
], 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()
df_country_groups = pd.read_excel(WB_COUNTRY_GROUPS_FILE).set_index("Economy")
bib_df = (data.from_yml(f"{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"]),
zot_usage=lambda _df: _df["doi"].map(zot_df["usage"]),
zot_keywords=lambda _df: _df["doi"].map(zot_df["keywords"]),
date = lambda _df: pd.to_datetime(_df["year"], format="%Y"),
year = lambda _df: _df["date"].dt.year,
region = lambda _df: _df["country"].map(df_country_groups["Region"]),
income_group = lambda _df: _df["country"].map(df_country_groups["Income group"]),
)
.query("year >= 2000")
)
zot_df = None
df_country_groups = None
```
# Introduction
This section will introduce the reader to the concern of inequality in the World of Work (WoW),
@ -363,7 +399,6 @@ It restricts studies to those that comprise primary research published after 200
with a focus on the narrowing criteria specified in @tbl-inclusion-criteria.
```{python}
#| echo: false
#| label: tbl-inclusion-criteria
#| tbl-cap: Study inclusion and exclusion scoping criteria {#tbl-inclusion-criteria}
@ -447,41 +482,6 @@ with small decreases between 2001 and 2008, as well as more significant ones in
as can be seen in @fig-publications-per-year.
Keeping in mind that these results are not yet screened for their full relevance to the topic at hand, so far only being *potentially* relevant in falling into the requirements of the search pattern, an increased results output does not necessarily mean a clearly rising amount of relevant literature.
```{python}
# load relevant studies
from src import data
bib_df = data.from_yml(f"{PROCESSED_DATA}/relevant")
# load zotero-based metadata
reformatted = []
for e in sample_relevant:
ed = e.fields_dict
reformatted.append([
ed.get("doi", Field(key="doi", value=None)).value,
ed.get("times-cited", Field(key="times-cited", value=None)).value,
ed.get("usage-count-since-2013", Field(key="usage-count-since-2013", value=None)).value,
ed.get("keywords", Field(key="keywords", value=None)).value,
])
zot_df = pd.DataFrame(reformatted, columns = ["doi", "cited", "usage", "keywords"])
bib_df["doi"] = bib_df["uri"].str.extract(r"https?://(?:dx\.)?doi\.org/(.*)", expand=False)
bib_df["zot_cited"] = bib_df["doi"].map(zot_df.drop_duplicates("doi").set_index("doi")["cited"])
bib_df["zot_usage"] = bib_df["doi"].map(zot_df.drop_duplicates("doi").set_index("doi")["usage"])
bib_df["zot_keywords"] = bib_df["doi"].map(zot_df.drop_duplicates("doi").set_index("doi")["keywords"])
bib_df["date"] = pd.to_datetime(bib_df["year"], format="%Y")
bib_df["year"] = bib_df["date"].dt.year
# only keep newer entries
bib_df = bib_df[bib_df["year"] >= 2000]
# Add WB country grouping definitions (income group, world region)
WB_COUNTRY_GROUPS_FILE = Path(f"{SUPPLEMENTARY_DATA}/wb-country-groupings.xlsx").resolve()
df_country_groups = pd.read_excel(WB_COUNTRY_GROUPS_FILE)
bib_df["income group"] = bib_df["country"].map(df_country_groups.set_index("Economy")["Income group"])
bib_df["region"] = bib_df["country"].map(df_country_groups.set_index("Economy")["Region"])
```
<!-- TODO Should this be sub-divided by region or subdivision later per-section? -->
```{python}
#| label: fig-publications-per-year