Function test_read_csv_index

dask/dataframe/io/tests/test_csv.py:527–543

()

def test_read_csv_index():
    with filetext(csv_text) as fn:
        f = dd.read_csv(fn, blocksize=20).set_index("amount")
        result = f.compute(scheduler="sync")
        assert result.index.name == "amount"

        blocks = compute_as_if_collection(
            dd.DataFrame, f.dask, f.__dask_keys__(), scheduler="sync"
        )
        for i, block in enumerate(blocks):
            if i < len(f.divisions) - 2:
                assert (block.index < f.divisions[i + 1]).all()
            if i > 0:
                assert (block.index >= f.divisions[i]).all()

        expected = pd.read_csv(fn).set_index("amount")
        assert_eq(result, expected)


def test_read_csv_skiprows_range():