chore(code): By default use all processed data

This commit is contained in:
Marty Oehme 2023-12-22 19:09:35 +01:00
parent ea26a5932e
commit 75717f837c
Signed by: Marty
GPG key ID: EDBF2ED917B2EF6A
2 changed files with 2 additions and 2 deletions

View file

@ -91,7 +91,7 @@ def countries_to_income_groups(countries:str):
return ";".join(res) return ";".join(res)
bib_df = (data.from_yml(f"{PROCESSED_DATA}/relevant") bib_df = (data.from_yml(f"{PROCESSED_DATA}")
.assign( .assign(
doi=lambda _df: _df["uri"].str.extract(r"https?://(?:dx\.)?doi\.org/(.*)", expand=False), 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_cited=lambda _df: _df["doi"].map(zot_df["cited"]),

View file

@ -7,7 +7,7 @@ except ModuleNotFoundError:
import load_yaml as yaml # for directly running the package import load_yaml as yaml # for directly running the package
from pandas import DataFrame, read_csv from pandas import DataFrame, read_csv
DEFAULT_YAML_PATH = Path("02-data/processed/relevant") DEFAULT_YAML_PATH = Path("02-data/processed")
def to_tsv(studies: list[dict]) -> str: def to_tsv(studies: list[dict]) -> str: