wow-inequalities/notebooks/bibmanip.qmd
Marty Oehme 4f9acd0816
chore(repo): Move references to reference data dir
Begin restructuring data dir by separating out references into their own
data sub-dir containing only references and bibtex files.
2024-07-16 15:59:41 +02:00

119 lines
2.7 KiB
Text

---
bibliography: ../data/intermediate/zotero-library.bib
csl: /home/marty/documents/library/utilities/styles/APA-7.csl
papersize: A4
linestretch: 1.5
fontfamily: lmodern
fontsize: "12"
geometry:
- left=2.2cm
- right=3.5cm
- top=2.5cm
- bottom=2.5cm
toc: false
link-citations: true
link-bibliography: true
number-sections: false
lang: en
title: Scoping review on 'what works'
subtitle: Addressing inequalities in the World of Work
---
```{python}
#| echo: false
from pathlib import Path
import src.globals as g
data_dir = g.DATA_DIR
## 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
```
```{python}
sns.set_style("whitegrid")
```
```{python}
#| echo: false
# load and parse overall bibtex sample
import bibtexparser
bib_string=""
sample_dir = g.REFERENCE_DATA.joinpath("01_wos-sample_2023-11-02")
print(f"path: {sample_dir.absolute()}")
for partial_bib in sample_dir.glob("*.bib"):
with open(partial_bib) as f:
bib_string+="\n".join(f.readlines())
sample = bibtexparser.parse_string(bib_string)
```
## Description of results
```{python}
#| echo: false
sample_size = len(sample.entries)
md(f"""
The exploratory execution of queries results in an initial sample of {sample_size} studies after the identification process.
""")
```
yrs:
```{python}
reformatted = []
for e in sample.entries:
reformatted.append([e["Year"], e["Author"], e["Title"], e["Type"], e["Times-Cited"], e["Usage-Count-Since-2013"]])
bib_df = pd.DataFrame(reformatted, columns = ["Year", "Author", "Title", "Type", "Cited", "Usage"])
bib_df["Date"] = pd.to_datetime(bib_df["Year"], format="%Y")
bib_df["Year"] = bib_df["Date"].dt.year
bib_df
```
```{python}
# RESTRICT FOR NEWER STUDIES
bib_df = bib_df[bib_df["Year"] >= 2000]
```
Publications per year:
```{python}
ax = sns.countplot(bib_df[bib_df["Year"] >= 2000], x="Year")
ax.tick_params(axis='x', rotation=45)
plt.tight_layout()
plt.show()
```
By type:
```{python}
bib_df["Type"].value_counts()
bib_df["Literature"] = np.where(bib_df["Type"].str.contains("article", case=False, regex=False), "white", "gray")
bib_df["Literature"] = bib_df["Literature"].astype("category")
```
Per type:
```{python}
ax = sns.countplot(bib_df[bib_df["Year"] >= 2000], x="Year", hue="Literature")
ax.tick_params(axis='x', rotation=45)
# ax.set_xlabel("")
plt.tight_layout()
plt.show()
```
Avg num of citations:
```{python}
bib_df["Cited"] = bib_df["Cited"].astype("int")
grpd = bib_df.groupby(["Year"], as_index=False)["Cited"].mean()
ax = sns.barplot(grpd, x="Year", y="Cited")
ax.tick_params(axis='x', rotation=45)
plt.tight_layout()
plt.show()
```