dedina.py

# coding=utf-8
# pip install pandas xlrd

import collections

import pandas as pd

df = pd.read_excel('https://www.mvcr.cz/odk2/soubor/databaze-obci-1-1-2014-xlsx.aspx')

cleaned = []
for one in df['Název obce']:
    parts = one.split()
    if len(parts) >= 3:  # Dětřichov nad Bystřicí
        name = parts[0]
    elif len(parts) == 2:  # Dlouhá Brtnice
        name = parts[1] if parts[1] not in ('I', 'II', 'III') else parts[0]
    else:
        name = parts[0]

    cleaned.append(name[-3:] if not
                   (name.endswith('ov') or
                    name.endswith('ín')) else name[-2:])

print(collections.Counter(cleaned).most_common(20))