python - 用大块 pandas 将唯一的行写入CSV

设定

一百万行

np.random.seed([3, 1415])
n = 1_000_000
dfout = pd.DataFrame({
    'id': np.random.randint(1000, size=n),
    'date': np.random.choice(pd.date_range('2019-01-01', periods=1000), size=n)
})

dfout.to_csv('my-file.csv.gz', compression='gzip', sep='\t', index=False)

解

像你一样大块

df_chunks = pd.read_csv(
    'my-file.csv.gz',
    sep='\t',
    chunksize=100000,
    compression='gzip')

每个唯一写入单个文件 date

for i, df in enumerate(df_chunks):
    for date, d in df.groupby('date'):
        date = pd.Timestamp(date)
        d.drop_duplicates().to_csv(
            f'{date:%Y%m%d}.csv.gz',
            compression='gzip',
            mode='a',
            index=False,
            header=False
        )
    print(f'\r{i}', end='')

读入每个日期文件drop_duplicates，然后写回

from pathlib import Path

path = Path('.')

for i, fh in enumerate(path.glob('[0-9]' * 8 + '.csv.gz')):
    df = pd.read_csv(fh, header=None)
    df.drop_duplicates().to_csv(
        'my_filtered.csv.gz',
        compression='gzip',
        mode='a',
        index=False,
        header=False
    )
    print(f'\r{i}: {fh}', end='')

df = pd.read_csv(
    'my_filtered.csv.gz',
    compression='gzip',
    header=None,
    names=['id', 'date']
)

验证方式

assert len(df) == len(dfout) - dfout.duplicated().sum()
assert df.duplicated().sum() == 0