Data & Code

1import pandas as pd
2import pycountry
3import re
4
5# ----- dummy input -----
6df = pd.DataFrame({"ISO3": ["HKG", "GBR", "CHE", "ETH"]})
7
8# ----- helper class -----
9class CountryCodeConverter:
10    def __init__(self):
11        self.alpha3_to_num = {}
12        self.num_to_alpha3 = {}
13        for c in pycountry.countries:
14            if hasattr(c, "alpha_3") and hasattr(c, "numeric"):
15                iso3 = c.alpha_3
16                num = c.numeric.zfill(3)
17                self.alpha3_to_num[iso3] = num
18                self.num_to_alpha3[num] = iso3
19
20    def to_un_numeric(self, iso3):
21        return self.alpha3_to_num.get(str(iso3).upper())
22
23cc = CountryCodeConverter()
24
25# ----- Generate complimentary identifiers -----
26df["ISO2"] = df["ISO3"].apply(
27    lambda x: pycountry.countries.get(alpha_3=x).alpha_2
28    if pycountry.countries.get(alpha_3=x) else None
29)
30df["UN_numeric"] = df["ISO3"].apply(cc.to_un_numeric)
31df["country"] = df["ISO3"].apply(
32    lambda x: pycountry.countries.get(alpha_3=x).name
33    if pycountry.countries.get(alpha_3=x) else None
34)

1import pandas as pd
2from datetime import datetime
3
4# ----- sample df -----
5df = pd.DataFrame({
6    "label": ["Dot-com", "GFC", "COVID"],
7    "date_str": ["2000-03-10", "2008-09-15", "2020-03-11"]
8})
9
10# ----- convert to datetime -----
11df["date"] = df["date_str"].apply(
12    lambda x: datetime.strptime(x, "%Y-%m-%d")
13)
14# ----- extract components -----
15df["year"] = df["date"].dt.year
16df["month"] = df["date"].dt.month
17df["quarter"] = df["month"].apply(lambda m: (m - 1) // 3 + 1)
18df["year_quarter"] = df.apply(
19    lambda r: f"{r.year}Q{r.quarter}", axis=1
20)

1import pandas as pd
2from datetime import datetime
3
4def output_to_excel(df, filename):
5    today  = datetime.now().strftime('%d%b%Y')
6    # %d%b%Y would return something like "01Jan2026"
7    # Alternatively use: %Y%m%d for "20260101" if you prefer numeric sorting
8    output = f'./{filename}_{today}.xlsx'
9    df.to_excel(output, index=False)
10    print(f"Excel file saved: {output}")
11
12# Usage:
13output_to_excel(df, "Filename")

1import pandas as pd
2from datetime import datetime
3
4def output_to_stata(df, filename):
5    today = datetime.now().strftime('%d%b%Y')
6    # %d%b%Y would return something like "01Jan2026"
7    # Alternatively use: %Y%m%d for "20260101" if you prefer numeric sorting
8    df    = df.copy()   # avoid mutating the caller's DataFrame
9
10    # Clean column names: remove invalid chars, truncate to 32 chars (Stata limit)
11    df.columns = (
12        df.columns
13        .str.replace('-', '_')
14        .str.replace(' ', '_')
15        .str.replace(r'[^0-9a-zA-Z_]', '', regex=True)
16        .str[:32]
17    )
18
19    # Ensure string values are Latin-1 compatible (replaces unencodable chars with '?')
20    for col in df.select_dtypes(include=[object]):
21        df[col] = (
22            df[col].astype(str)
23            .apply(lambda x: x.encode('latin-1', errors='replace').decode('latin-1'))
24        )
25
26    output = f'{filename}_{today}.dta'
27    df.to_stata(output, write_index=False, version=117)
28    print(f"Stata file saved: {output}")
29
30# Usage:
31output_to_stata(df, "Filename")