审计不平等观测及其年份

from pathlib import Path
import base64, gzip, hashlib, json, platform
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from IPython.display import display, HTML
from IPython.display import display as _display
def display(value):
    if isinstance(value,pd.DataFrame):
        table=value.to_html(max_rows=12,escape=True)
        style="<style>.vibeit-readable-table{max-width:100%;overflow-x:auto}.vibeit-readable-table table{width:max-content;max-width:none;border-collapse:collapse}.vibeit-readable-table td,.vibeit-readable-table th{white-space:nowrap!important;word-break:normal!important;overflow-wrap:normal!important}</style>"
        return _display(HTML(style+'<div class="vibeit-readable-table">'+table+'</div>'))
    return _display(value)
RECIPE_ID='ec03-inequality'
OUTPUT_DIR=Path.cwd()/"results"/RECIPE_ID
plt.rcParams.update({"figure.dpi":120,"font.size":10,"axes.spines.top":False,"axes.spines.right":False,
                      "axes.prop_cycle":plt.cycler(color=["#18785f","#416aa6","#bc6541","#9974a5"])})
print("Python:",platform.python_version(),"; NumPy:",np.__version__,"; Pandas:",pd.__version__)
print("Working folder:",Path.cwd())
print("Core data mode: embedded snapshot; no network requests")

Python: 3.13.13 ; NumPy: 2.5.3 ; Pandas: 3.0.6
Working folder: /Users/zhiluo/Developer/vibeit-cookbook/cookbook/downloads
Core data mode: embedded snapshot; no network requests

def load_snapshot(recipe_id, expected_sha256, snapshot_key):
    """Read embedded data from this notebook, including a renamed copy."""
    for path in sorted(Path.cwd().glob("*.ipynb")):
        try:
            notebook = json.loads(path.read_text(encoding="utf-8"))
            metadata = notebook.get("metadata", {}).get("vibeit_cookbook", {})
            blob = metadata.get("snapshots", {}).get(snapshot_key)
            if metadata.get("recipe_id") != recipe_id or not blob:
                continue
            if blob.get("sha256") != expected_sha256:
                continue
            raw = gzip.decompress(base64.b64decode(blob["gzip_base64"], validate=True))
            if hashlib.sha256(raw).hexdigest() != expected_sha256:
                raise ValueError("Embedded snapshot checksum mismatch: " + snapshot_key)
            return json.loads(raw)
        except (OSError, json.JSONDecodeError):
            continue
    raise FileNotFoundError(
        "Save/open the complete .ipynb in the active working folder. "
        "The embedded snapshot could not be located for " + recipe_id)

SNAPSHOT_HASHES={'worldbank': 'd45779250297fb9371748b85b81321b2ae88f93ecf70cfb88256647a68e54376'}
def snapshot(key):
    return load_snapshot(RECIPE_ID,SNAPSHOT_HASHES[key],key)
print("Embedded snapshots:",list(SNAPSHOT_HASHES))

Embedded snapshots: ['worldbank']

def worldbank_panel(payload):
    """Preserve missing observations; official economy metadata excludes aggregates."""
    economies=pd.DataFrame(payload['economies']).set_index('iso3')
    observations=pd.DataFrame(payload['observations'])
    observations=observations[observations.iso3.isin(economies.index)].copy()
    if observations.duplicated(['iso3','year','indicator']).any():raise ValueError('Duplicate economy/year/indicator observations')
    observations['value']=pd.to_numeric(observations.value,errors='raise')
    wide=observations.pivot(index=['iso3','year'],columns='indicator',values='value').sort_index()
    return wide,economies,observations

print("Method ready: worldbank_panel")

Method ready: worldbank_panel

wb=snapshot("worldbank");panel,economies,observations=worldbank_panel(wb)
countries=["CHN","USA","DEU","BRA","IND","ZAF"]
assert set(countries)<=set(economies.index)
print("Economy/year records:",len(panel),"; official aggregates excluded; missing values preserved")
display(economies.loc[countries,["name","region","income_group"]])
gini=panel["SI.POV.GINI"].unstack("iso3").reindex(index=range(2010,2025),columns=countries)
observed=gini.stack().dropna().rename("Gini_index").reset_index()
assert observed.Gini_index.between(0,100).all();display(observed.head(8))

Economy/year records: 3255 ; official aggregates excluded; missing values preserved

fig,ax=plt.subplots(figsize=(9,5))
for code in countries:ax.plot(gini.index,gini[code],"o",label=economies.loc[code,"name"])
ax.set(xlabel="Indicator-reference year",ylabel="Gini index (0–100)",title="Reported values without imputation");ax.legend(fontsize=8);plt.tight_layout();plt.show()

latest=observed.sort_values("year").groupby("iso3").tail(1).set_index("iso3").reindex(countries)
display(latest)
labels=[economies.loc[c,"name"]+" ("+(str(int(latest.loc[c,"year"])) if pd.notna(latest.loc[c,"year"]) else "no observation")+")" for c in countries]
fig,ax=plt.subplots(figsize=(9,4));ax.barh(labels,latest.Gini_index)
ax.set(xlabel="Reported Gini index (0–100)",title="Last available 2010–2024 values; dates differ");plt.tight_layout();plt.show()

	year	Gini_index
iso3
CHN	2022	36.0
USA	2024	41.8
DEU	2022	33.7
BRA	2024	50.3
IND	2023	23.0
ZAF	2022	54.1

fig,ax=plt.subplots(figsize=(9,4));im=ax.imshow(gini.notna().T,aspect="auto",cmap="Blues",vmin=0,vmax=1)
ax.set_xticks(range(15),range(2010,2025),rotation=45);ax.set_yticks(range(6),[economies.loc[c,"name"] for c in countries])
ax.set(xlabel="Indicator year",title="Coverage: 1=reported, 0=missing");fig.colorbar(im,ax=ax,ticks=[0,1]);plt.tight_layout();plt.show()

assert len(observed)==int(gini.notna().to_numpy().sum())
for code in countries:
 available=gini[code].dropna()
 if not available.empty:assert latest.loc[code,"year"]==available.index.max()
OUTPUT_DIR.mkdir(parents=True,exist_ok=True);gini.to_csv(OUTPUT_DIR/"Gini-with-missing-years.csv")
latest.to_csv(OUTPUT_DIR/"dated-last-observations.csv")
print("Source count/year selection reconciled:",len(observed),"observations")

Source count/year selection reconciled: 61 observations

RUN_ONLINE_UPDATE=False
if RUN_ONLINE_UPDATE:
    import requests
    try:
        response=requests.get('https://api.worldbank.org/v2/indicator/NY.GDP.PCAP.KD?format=json',timeout=20)
        response.raise_for_status()
        print("Source:",response.url)
        print(response.text[:700])
    except requests.RequestException as error:
        print("Online extension unavailable:",type(error).__name__,str(error)[:160])
else:
    print("Online extension skipped; embedded core data unchanged")

Online extension skipped; embedded core data unchanged