区分 CPI、通胀与实值

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='ec02-inflation'
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"]])
cpi=panel.loc["USA","FP.CPI.TOTL"].reindex(range(2010,2025))
reported=panel.loc["USA","FP.CPI.TOTL.ZG"].reindex(cpi.index)
assert cpi.loc[2010]>0
rebased=100*cpi/cpi.loc[2010];nominal=1000.0
fig,ax=plt.subplots(figsize=(8,4));ax.plot(rebased.index,rebased,"o-")
ax.set(xlabel="Indicator year",ylabel="Rebased CPI (2010=100)",title="Price-index level, not a rate");plt.tight_layout();plt.show()

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

	name	region	income_group
iso3
CHN	China	East Asia & Pacific	Upper middle income
USA	United States	North America	High income
DEU	Germany	Europe & Central Asia	High income
BRA	Brazil	Latin America & Caribbean	Upper middle income
IND	India	South Asia	Lower middle income
ZAF	South Africa	Sub-Saharan Africa	Upper middle income

computed=100*cpi.pct_change(fill_method=None)
fig,ax=plt.subplots(figsize=(8,4));ax.plot(computed.index,computed,"o-",label="From frozen CPI")
ax.plot(reported.index,reported,"x--",label="Published inflation")
ax.set(xlabel="Indicator year",ylabel="Annual change (%)",title="Rates and source reconciliation");ax.legend();plt.tight_layout();plt.show()
comparison=pd.DataFrame({"computed_percent":computed,"reported_percent":reported,"difference_percentage_points":computed-reported})
display(comparison.tail(7))

	computed_percent	reported_percent	difference_percentage_points
year
2018	2.442583	2.442583	9.325873e-15
2019	1.812210	1.812210	3.563816e-13
2020	1.233584	1.233584	-5.031531e-13
2021	4.697859	4.697859	-3.730349e-14
2022	8.002800	8.002800	6.235013e-13
2023	4.116338	4.116338	-2.149392e-13
2024	2.949525	2.949525	-2.593481e-13

real=nominal*100/rebased
fig,ax=plt.subplots(figsize=(8,4));ax.plot(cpi.index,np.full(len(cpi),nominal),label="Hypothetical nominal USD")
ax.plot(real.index,real,"o-",label="CPI-based 2010-price amount")
ax.set(xlabel="Indicator year",ylabel="USD / 2010-price USD",title="Stated hypothetical purchasing-power example");ax.legend();plt.tight_layout();plt.show()

assert np.isclose(rebased.loc[2010],100) and np.isclose(real.loc[2010],nominal) and pd.isna(computed.loc[2010])
OUTPUT_DIR.mkdir(parents=True,exist_ok=True)
pd.DataFrame({"source_CPI":cpi,"rebased_2010_100":rebased,"hypothetical_nominal_USD":nominal,"CPI_based_2010_price_USD":real}).to_csv(OUTPUT_DIR/"price-and-real-amount.csv")
comparison.to_csv(OUTPUT_DIR/"inflation-reconciliation.csv")
print("Rebasing checked; maximum discrepancy (percentage points):",float(comparison.difference_percentage_points.abs().max()))

Rebasing checked; maximum discrepancy (percentage points): 6.235012506294879e-13

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