benchmarks/db-benchmark/groupby-datafusion.py [258:288]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
m = memory_usage()
t_start = timeit.default_timer()
df = ctx.create_dataframe([ans])
chk = (
    df.aggregate([], [f.sum(col("v1")), f.sum(col("v2")), f.sum(col("v3"))])
    .collect()[0]
    .to_pandas()
    .to_numpy()[0]
)
chkt = timeit.default_timer() - t_start
write_log(
    task=task,
    data=data_name,
    in_rows=in_rows,
    question=question,
    out_rows=shape[0],
    out_cols=shape[1],
    solution=solution,
    version=ver,
    git=git,
    fun=fun,
    run=1,
    time_sec=t,
    mem_gb=m,
    cache=cache,
    chk=make_chk([chk]),
    chk_time_sec=chkt,
    on_disk=on_disk,
)
del ans
gc.collect()
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



benchmarks/db-benchmark/groupby-datafusion.py [300:330]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
m = memory_usage()
t_start = timeit.default_timer()
df = ctx.create_dataframe([ans])
chk = (
    df.aggregate([], [f.sum(col("v1")), f.sum(col("v2")), f.sum(col("v3"))])
    .collect()[0]
    .to_pandas()
    .to_numpy()[0]
)
chkt = timeit.default_timer() - t_start
write_log(
    task=task,
    data=data_name,
    in_rows=in_rows,
    question=question,
    out_rows=shape[0],
    out_cols=shape[1],
    solution=solution,
    version=ver,
    git=git,
    fun=fun,
    run=1,
    time_sec=t,
    mem_gb=m,
    cache=cache,
    chk=make_chk([chk]),
    chk_time_sec=chkt,
    on_disk=on_disk,
)
del ans
gc.collect()
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -