wow-inequalities/00-notebooks/explore.qmd

---
bibliography: 02-data/supplementary/lib.bib
title: Grab yml
---

```{python}
import pandas as pd
from src import data

df = data.from_yml()
```

Get interventions:

```{python}
df['intervention'].str.split(";").explode().str.strip().value_counts()
```

Get inequalities:

```{python}
df['inequality'].str.split(";").explode().str.strip().value_counts()
```

```{python}
df.groupby(["author", "year", "title"]).first().join(df['intervention'])
```

Unique values in chain method:

```{python}
(
    df.groupby(["author", "year", "title"])
    .agg(
        {
            "intervention": lambda _col:"; ".join(_col),
            "inequality": lambda _col:"; ".join(_col),
        }
    )
    .drop_duplicates()
    .explode("inequality")
    ["inequality"].str.strip()
    .value_counts()
)
```

Merge dataset so it is collected by *STUDY* not by *OBSERVATION*.
Any required columns can be calculated similar to the agg function here.

```{python}
by_study = (
    df.groupby(["author", "year", "title"])
    .agg(
        {
            "intervention": lambda _col: "; ".join(_col),
            "inequality": lambda _col: "; ".join(_col),
            "date": lambda _col: "; ".join(_col),
            "findings": lambda _col: "; ".join(_col),
            # "region": lambda _col: "; ".join(_col), # only accessible when merging with WB data
            # "income_group": lambda _col: "; ".join(_col),
        }
    )
    .reset_index()
    .drop_duplicates()
    .assign(
        # create de-duplicated joins for all observations
        intervention=lambda _df: _df["intervention"].apply(
            lambda _cell: set([x.strip() for x in _cell.split(";")])
        ),
        inequality=lambda _df: _df["inequality"].apply(
            lambda _cell: set([x.strip() for x in _cell.split(";")])
        ),
    )
)
```

```{python}
by_study = (
    df.groupby(["author", "year", "title"])
    .first()
    .reset_index()
    .drop_duplicates()
    .assign(
        # create de-duplicated joins for all observations
        intervention=lambda _df: _df["intervention"].apply(
            lambda _cell: set([x.strip() for x in _cell.split(";")])
        ),
        inequality=lambda _df: _df["inequality"].apply(
            lambda _cell: set([x.strip() for x in _cell.split(";")])
        ),
    )
)
```

```{python}
import re
from matplotlib import pyplot as plt
import seaborn as sns
by_intervention = (
    df.groupby(["author", "year", "title"])
    .agg(
        {
            "intervention": lambda _col: "; ".join(_col),
        }
    )
    .reset_index()
    .drop_duplicates()
    .assign(
        intervention=lambda _df: _df["intervention"].apply(
            lambda _cell: set([x.strip() for x in re.sub(r"\(.*\)", "", _cell).split(";")])
        ),
    )
    .explode("intervention")
)
sort_order = by_intervention["intervention"].value_counts().index

fig = plt.figure()
fig.set_size_inches(6, 3)
ax = sns.countplot(by_intervention, x="intervention", order=by_intervention["intervention"].value_counts().index)
plt.setp(ax.get_xticklabels(), rotation=45, ha="right",
         rotation_mode="anchor")
plt.show()
by_intervention = None
```

```{python}
#| label: fig-publications-per-year
#| fig-cap: Publications per year

df_study_years = (
    df.groupby(["author", "year", "title"])
    .first()
    .reset_index()
    .drop_duplicates()
)
# plot by year TODO decide if we want to distinguish by literature type/region/etc as hue
# FIXME should be timeseries plot so no years are missing
ax = sns.countplot(df_study_years, x="year", native_scale=True)
ax.tick_params(axis='x', rotation=45)
ax.set_xlabel("")
plt.tight_layout()
plt.show()
df_study_years = None
```

```{python}
#| label: tbl-income-crosstab
#| tbl-cap: Interventions targeting income inequality

df_income = df.copy()
df_income['Inequality'] = df_income['inequality'].str.split(";").explode(ignore_index=True).str.strip()
df_income = df_income.loc[df_income['Inequality'] == "income"].copy()
df_income['Intervention'] = df_income['intervention'].str.split(";").explode(ignore_index=True).str.replace(r"\(.+\)", "", regex=True).str.strip()
pd.crosstab(df_income["Intervention"], df_income["Inequality"])
```

```{python}
#| label: tbl-income-crosstab
#| tbl-cap: Interventions targeting income inequality

temp_df = df[["intervention", "inequality"]].copy().reset_index(drop=True)
temp_df['Inequality'] = temp_df['inequality'].str.split(";").explode(ignore_index=True).str.strip()
temp_df['Intervention'] = temp_df['intervention'].str.split(";").explode(ignore_index=True).str.replace(r"\(.+\)", "", regex=True).str.strip()

gender_df = temp_df.loc[temp_df["Inequality"] == "gender"]
income_df = temp_df.loc[temp_df["Inequality"] == "income"]
```

prep full data set:

```{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 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
```

```{python}
df_country_groups = pd.concat([pd.read_excel(WB_COUNTRY_GROUPS_FILE), pd.DataFrame(data={'Economy':['global'],'Code':['WLD'],'Region':['World'], '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)
```

```{python}
bib_df = (bib_df
    .assign(
        # create de-duplicated joins for all observations
        region=lambda _df: _df["region"].apply(
            lambda _cell: set([x.strip() for x in _cell.split(";")])
        ),
     )
    .explode("region")
)
# bib_df["region"] = bib_df["region"].str.split(";").explode().str.strip()
ax = sns.countplot(bib_df, x="region", order=bib_df["region"].value_counts().index)
plt.setp(ax.get_xticklabels(), rotation=45, ha="right",
         rotation_mode="anchor")
plt.show()
```