load data, boilerplate:

```{python}
#| echo: false
from pathlib import Path
import re
## standard imports
from IPython.core.display import Markdown as md
import numpy as np
import pandas as pd
from matplotlib import pyplot as plt
import seaborn as sns
from tabulate import tabulate
import bibtexparser

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 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"):
    with open(partial_bib) as f:
        bib_string+="\n".join(f.readlines())
bib_sample = bibtexparser.parse_string(bib_string)
```

```{python}
# load relevant studies
from src import load_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 = (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"]),
        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
```

```{python}
df_country_groups = pd.concat([pd.read_excel(WB_COUNTRY_GROUPS_FILE), pd.DataFrame(data={'Economy':['global'],'Code':['WLD'],'Region':['Europe & Central Asia;South Asia;North America;East Asia & Pacific;Sub-Saharan Africa;Europe & Central Asia;Latin America & Caribbean'], 'Income group':[''], 'Lending category':['']})]).set_index("Economy")

def countries_to_regions(countries:str):
    res = set()
    for c in countries.replace(" ;", ";").replace("; ",";").split(";"):
        if c in df_country_groups.index:
            region = df_country_groups.at[c,'Region']
            res.add(region)
    return ";".join(res)

# countries_to_regions("India; Nicaragua")
bib_df['region'] = bib_df['country'].map(countries_to_regions)
bib_df['region'].value_counts().plot.bar()
```

prep data: 

Map a 0-5 external validity score based on 'representativeness' to rows:

```{python}
df=bib_df
vd=df[(df['design'] == 'quasi-experimental') | (df['design'] == 'experimental')]

vd = vd.assign(valid_ext=0)
vd["representativeness"] = vd["representativeness"].fillna("")

mask_subnational = vd['representativeness'].str.contains("subnational")
mask_national = vd['representativeness'].str.contains("national")
mask_regional = vd['representativeness'].str.contains("regional")
mask_local = vd['representativeness'].str.contains("local")

vd.loc[mask_regional, 'valid_ext'] = 5
vd.loc[mask_national, 'valid_ext'] = 4
vd.loc[mask_subnational, 'valid_ext'] = 3
vd.loc[mask_local, 'valid_ext'] = 2

vd[['representativeness', 'valid_ext']]
```

Map an internal validity score based on study design/method:

```{python}
vd = vd.assign(valid_int=0)
vd["method"] = vd["method"].fillna("")

vd.loc[vd['method'].str.contains("RCT"), 'valid_int'] = 5.0
vd.loc[vd['method'].str.contains("|".join(["RD","regression.vdiscontinuity"])), 'valid_int'] = 4.5
vd.loc[vd['method'].str.contains("|".join(["IV","instrumental.variable"])), 'valid_int'] = 4.0
vd.loc[vd['method'].str.contains("|".join(["PSM","propensity.score.matching"])), 'valid_int'] = 3.5
vd.loc[vd['method'].str.contains("|".join(["DM","discontinuity.matching"])), 'valid_int'] = 3.0
vd.loc[vd['method'].str.contains("|".join(["DID","difference.in.difference"])), 'valid_int'] = 3.0
vd.loc[vd['method'].str.contains("|".join(["OLS","ordinary.least.square"])), 'valid_int'] = 2.0
vd[['method', 'valid_int']]
```