gy stats2.py

import pandas as pd

def generate_statistics(df: pd.DataFrame, window: int) -> None:
    cuts = pd.interval_range(start=0, end = df.szamok.max(), freq=window)
    (
        df
        .groupby(pd.cut(df.szamok, cuts))
        .agg(
            osszeg = ('szamok', sum),
            max_ertek = ('szamok', max),
            min_ertek = ('szamok', min),
            darab = ('szamok', 'count')
        )
        .reset_index()
        .assign(
            start = lambda df: df.szamok.apply(lambda x: x.left),
            end = lambda df: df.szamok.apply(lambda x: x.right),
        )
        .drop('szamok', axis=1)
        .to_csv(f'bontas-{window}.tsv', sep='\t', index=False)
    )

# A szamsort tartalmazo file:
input_file = 'input.txt'

# Az osszes bontas:
windows = [100, 500, 1000, 5000]

# Szamsor beolvasa:
df = pd.read_csv(input_file, header=None, names=['szamok'])

for window in windows:
    generate_statistics(df, window)