World Bank Remittance Flows Datasets

curl -O 'https://datacatalogfiles.worldbank.org/ddh-published/0066877/DR0095407/Inward_remittance_flows_(July_13_2025).xlsx'

"""World Bank inward-remittance workbook -> tidy pandas -> Parquet. No key."""
import io
import re
import zipfile
import xml.etree.ElementTree as ET
import pandas as pd
import requests

URL = "https://datacatalogfiles.worldbank.org/ddh-published/0066877/DR0095407/Inward_remittance_flows_(July_13_2025).xlsx"
NS = {"m": "http://schemas.openxmlformats.org/spreadsheetml/2006/main"}
r = requests.get(URL, timeout=60)
r.raise_for_status()
with zipfile.ZipFile(io.BytesIO(r.content)) as book:
    root = ET.fromstring(book.read("xl/sharedStrings.xml"))
    strings = ["".join(n.text or "" for n in item.findall(".//m:t", NS))
               for item in root.findall("m:si", NS)]
    sheet = ET.fromstring(book.read("xl/worksheets/sheet1.xml"))
rows = []
for row in sheet.findall(".//m:sheetData/m:row", NS):
    values = {}
    for cell in row.findall("m:c", NS):
        column = re.match(r"[A-Z]+", cell.attrib["r"]).group()
        value = cell.find("m:v", NS)
        if value is None:
            values[column] = None
        elif cell.attrib.get("t") == "s":
            values[column] = strings[int(value.text)]
        else:
            values[column] = float(value.text)
    rows.append(values)
wide = pd.DataFrame(rows)
wide.columns = ["economy"] + [str(int(x)) for x in wide.iloc[0, 1:]]
wide = wide.iloc[1:].copy()
df = wide.melt(id_vars="economy", var_name="year", value_name="usd_millions")
df["usd_millions"] = pd.to_numeric(df["usd_millions"], errors="coerce")
df = df.dropna(subset=["economy", "usd_millions"])
df["year"] = df["year"].astype("int16")
df.to_parquet("world_bank_inward_remittances.parquet", index=False)
print(len(df), "observations", df["economy"].nunique(), "economies", df["year"].min(), "to", df["year"].max())