Skip to content

Commit

Permalink
Disable test
Browse files Browse the repository at this point in the history
  • Loading branch information
@mariosasko
mariosasko committed Jun 16, 2022
1 parent 6eab0e4 commit 97ee698
Show file tree
Hide file tree
Showing 2 changed files with 6 additions and 6 deletions.
6 changes: 3 additions & 3 deletions tests/test_arrow_dataset.py
View file
Expand Up @@ -3056,9 +3056,9 @@ def test_pickle_dataset_after_transforming_the_table(in_memory, method_and_param


@pytest.mark.skipif(
os.name == "nt" and os.getenv("CIRCLECI") == "true",
reason='On Windows CircleCI, it raises botocore.exceptions.EndpointConnectionError: Could not connect to the endpoint URL: "http://127.0.0.1:5555/test"',
) # TODO(QL): find what's wrong with CircleCI
os.name in ["posix", "nt"] and os.getenv("CIRCLECI") == "true",
reason='On Linux/Windows CircleCI, it raises botocore.exceptions.EndpointConnectionError: Could not connect to the endpoint URL: "http://127.0.0.1:5555/test"',
) # TODO(QL, mario): find what's wrong with CircleCI
@require_s3
def test_dummy_dataset_serialize_s3(s3, dataset):
mock_bucket = s3_test_bucket_name
Expand Down
6 changes: 3 additions & 3 deletions tests/test_dataset_dict.py
View file
Expand Up @@ -656,9 +656,9 @@ def test_datasetdict_from_text_split(split, text_path, tmp_path):


@pytest.mark.skipif(
os.name == "nt" and os.getenv("CIRCLECI") == "true",
reason='On Windows CircleCI, it raises botocore.exceptions.EndpointConnectionError: Could not connect to the endpoint URL: "http://127.0.0.1:5555/test"',
) # TODO(QL): find what's wrong with CircleCI
os.name in ["posix", "nt"] and os.getenv("CIRCLECI") == "true",
reason='On Linux/Windows CircleCI, it raises botocore.exceptions.EndpointConnectionError: Could not connect to the endpoint URL: "http://127.0.0.1:5555/test"',
) # TODO(QL, mario): find what's wrong with CircleCI
@require_s3
def test_dummy_dataset_serialize_s3(s3, dataset):
dsets = DatasetDict({"train": dataset, "test": dataset.select(range(2))})
Expand Down

1 comment on commit 97ee698

@github-actions
Copy link

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Show benchmarks

PyArrow==6.0.0

Show updated benchmarks!

Benchmark: benchmark_array_xd.json

metric read_batch_formatted_as_numpy after write_array2d read_batch_formatted_as_numpy after write_flattened_sequence read_batch_formatted_as_numpy after write_nested_sequence read_batch_unformated after write_array2d read_batch_unformated after write_flattened_sequence read_batch_unformated after write_nested_sequence read_col_formatted_as_numpy after write_array2d read_col_formatted_as_numpy after write_flattened_sequence read_col_formatted_as_numpy after write_nested_sequence read_col_unformated after write_array2d read_col_unformated after write_flattened_sequence read_col_unformated after write_nested_sequence read_formatted_as_numpy after write_array2d read_formatted_as_numpy after write_flattened_sequence read_formatted_as_numpy after write_nested_sequence read_unformated after write_array2d read_unformated after write_flattened_sequence read_unformated after write_nested_sequence write_array2d write_flattened_sequence write_nested_sequence
new / old (diff) 0.008588 / 0.011353 (-0.002765) 0.004508 / 0.011008 (-0.006500) 0.034799 / 0.038508 (-0.003709) 0.036289 / 0.023109 (0.013179) 0.341764 / 0.275898 (0.065866) 0.359491 / 0.323480 (0.036011) 0.006579 / 0.007986 (-0.001406) 0.003938 / 0.004328 (-0.000390) 0.006812 / 0.004250 (0.002561) 0.047586 / 0.037052 (0.010534) 0.320268 / 0.258489 (0.061779) 0.345465 / 0.293841 (0.051624) 0.033739 / 0.128546 (-0.094807) 0.011065 / 0.075646 (-0.064581) 0.269146 / 0.419271 (-0.150126) 0.058017 / 0.043533 (0.014485) 0.327275 / 0.255139 (0.072136) 0.347371 / 0.283200 (0.064171) 0.114360 / 0.141683 (-0.027323) 1.585429 / 1.452155 (0.133275) 1.699079 / 1.492716 (0.206363)

Benchmark: benchmark_getitem_100B.json

metric get_batch_of_1024_random_rows get_batch_of_1024_rows get_first_row get_last_row
new / old (diff) 0.293300 / 0.018006 (0.275294) 0.477280 / 0.000490 (0.476790) 0.055555 / 0.000200 (0.055355) 0.000311 / 0.000054 (0.000257)

Benchmark: benchmark_indices_mapping.json

metric select shard shuffle sort train_test_split
new / old (diff) 0.026123 / 0.037411 (-0.011288) 0.112123 / 0.014526 (0.097597) 0.121953 / 0.176557 (-0.054604) 0.278178 / 0.737135 (-0.458957) 0.126597 / 0.296338 (-0.169741)

Benchmark: benchmark_iterating.json

metric read 5000 read 50000 read_batch 50000 10 read_batch 50000 100 read_batch 50000 1000 read_formatted numpy 5000 read_formatted pandas 5000 read_formatted tensorflow 5000 read_formatted torch 5000 read_formatted_batch numpy 5000 10 read_formatted_batch numpy 5000 1000 shuffled read 5000 shuffled read 50000 shuffled read_batch 50000 10 shuffled read_batch 50000 100 shuffled read_batch 50000 1000 shuffled read_formatted numpy 5000 shuffled read_formatted_batch numpy 5000 10 shuffled read_formatted_batch numpy 5000 1000
new / old (diff) 0.420180 / 0.215209 (0.204971) 4.164275 / 2.077655 (2.086621) 1.901672 / 1.504120 (0.397552) 1.757083 / 1.541195 (0.215889) 1.793773 / 1.468490 (0.325283) 0.481970 / 4.584777 (-4.102807) 4.362805 / 3.745712 (0.617092) 1.045813 / 5.269862 (-4.224048) 1.050076 / 4.565676 (-3.515601) 0.057616 / 0.424275 (-0.366659) 0.012162 / 0.007607 (0.004555) 0.535323 / 0.226044 (0.309279) 5.460349 / 2.268929 (3.191420) 2.422221 / 55.444624 (-53.022403) 2.119287 / 6.876477 (-4.757190) 2.163101 / 2.142072 (0.021029) 0.572939 / 4.805227 (-4.232288) 0.126096 / 6.500664 (-6.374568) 0.065932 / 0.075469 (-0.009537)

Benchmark: benchmark_map_filter.json

metric filter map fast-tokenizer batched map identity map identity batched map no-op batched map no-op batched numpy map no-op batched pandas map no-op batched pytorch map no-op batched tensorflow
new / old (diff) 1.633438 / 1.841788 (-0.208350) 15.362329 / 8.074308 (7.288021) 28.368584 / 10.191392 (18.177192) 0.995469 / 0.680424 (0.315045) 0.636827 / 0.534201 (0.102626) 0.452710 / 0.579283 (-0.126573) 0.499244 / 0.434364 (0.064881) 0.313871 / 0.540337 (-0.226466) 0.306721 / 1.386936 (-1.080215)
PyArrow==latest
Show updated benchmarks!

Benchmark: benchmark_array_xd.json

metric read_batch_formatted_as_numpy after write_array2d read_batch_formatted_as_numpy after write_flattened_sequence read_batch_formatted_as_numpy after write_nested_sequence read_batch_unformated after write_array2d read_batch_unformated after write_flattened_sequence read_batch_unformated after write_nested_sequence read_col_formatted_as_numpy after write_array2d read_col_formatted_as_numpy after write_flattened_sequence read_col_formatted_as_numpy after write_nested_sequence read_col_unformated after write_array2d read_col_unformated after write_flattened_sequence read_col_unformated after write_nested_sequence read_formatted_as_numpy after write_array2d read_formatted_as_numpy after write_flattened_sequence read_formatted_as_numpy after write_nested_sequence read_unformated after write_array2d read_unformated after write_flattened_sequence read_unformated after write_nested_sequence write_array2d write_flattened_sequence write_nested_sequence
new / old (diff) 0.006273 / 0.011353 (-0.005080) 0.004190 / 0.011008 (-0.006819) 0.030599 / 0.038508 (-0.007909) 0.035151 / 0.023109 (0.012041) 0.338736 / 0.275898 (0.062838) 0.389512 / 0.323480 (0.066033) 0.003944 / 0.007986 (-0.004041) 0.003576 / 0.004328 (-0.000752) 0.005310 / 0.004250 (0.001059) 0.039457 / 0.037052 (0.002405) 0.318778 / 0.258489 (0.060289) 0.386932 / 0.293841 (0.093091) 0.034152 / 0.128546 (-0.094394) 0.010893 / 0.075646 (-0.064754) 0.296793 / 0.419271 (-0.122479) 0.076400 / 0.043533 (0.032867) 0.332152 / 0.255139 (0.077013) 0.384429 / 0.283200 (0.101229) 0.120202 / 0.141683 (-0.021481) 1.593190 / 1.452155 (0.141035) 1.693272 / 1.492716 (0.200555)

Benchmark: benchmark_getitem_100B.json

metric get_batch_of_1024_random_rows get_batch_of_1024_rows get_first_row get_last_row
new / old (diff) 0.275557 / 0.018006 (0.257551) 0.486152 / 0.000490 (0.485663) 0.039980 / 0.000200 (0.039780) 0.000654 / 0.000054 (0.000599)

Benchmark: benchmark_indices_mapping.json

metric select shard shuffle sort train_test_split
new / old (diff) 0.026531 / 0.037411 (-0.010881) 0.123103 / 0.014526 (0.108577) 0.134924 / 0.176557 (-0.041633) 0.182199 / 0.737135 (-0.554936) 0.143906 / 0.296338 (-0.152433)

Benchmark: benchmark_iterating.json

metric read 5000 read 50000 read_batch 50000 10 read_batch 50000 100 read_batch 50000 1000 read_formatted numpy 5000 read_formatted pandas 5000 read_formatted tensorflow 5000 read_formatted torch 5000 read_formatted_batch numpy 5000 10 read_formatted_batch numpy 5000 1000 shuffled read 5000 shuffled read 50000 shuffled read_batch 50000 10 shuffled read_batch 50000 100 shuffled read_batch 50000 1000 shuffled read_formatted numpy 5000 shuffled read_formatted_batch numpy 5000 10 shuffled read_formatted_batch numpy 5000 1000
new / old (diff) 0.462078 / 0.215209 (0.246869) 4.469899 / 2.077655 (2.392245) 2.197552 / 1.504120 (0.693432) 1.938373 / 1.541195 (0.397178) 1.970338 / 1.468490 (0.501848) 0.457815 / 4.584777 (-4.126962) 4.317354 / 3.745712 (0.571642) 1.089567 / 5.269862 (-4.180295) 1.035072 / 4.565676 (-3.530605) 0.060265 / 0.424275 (-0.364010) 0.011900 / 0.007607 (0.004292) 0.583423 / 0.226044 (0.357378) 5.603776 / 2.268929 (3.334847) 2.729527 / 55.444624 (-52.715097) 2.210892 / 6.876477 (-4.665584) 2.274457 / 2.142072 (0.132384) 0.571196 / 4.805227 (-4.234032) 0.124639 / 6.500664 (-6.376025) 0.069562 / 0.075469 (-0.005908)

Benchmark: benchmark_map_filter.json

metric filter map fast-tokenizer batched map identity map identity batched map no-op batched map no-op batched numpy map no-op batched pandas map no-op batched pytorch map no-op batched tensorflow
new / old (diff) 1.712302 / 1.841788 (-0.129486) 15.502658 / 8.074308 (7.428350) 27.565706 / 10.191392 (17.374314) 1.023969 / 0.680424 (0.343545) 0.652434 / 0.534201 (0.118233) 0.430271 / 0.579283 (-0.149012) 0.522807 / 0.434364 (0.088444) 0.326643 / 0.540337 (-0.213694) 0.346335 / 1.386936 (-1.040601)

CML watermark

Please sign in to comment.