def _prepare_split(self, split_generator, **kwargs):
fname = "{}-{}.arrow".format(self.name, split_generator.name)
writer = ArrowWriter(features=self.info.features, path=os.path.join(self._cache_dir, fname))
writer.write_batch({"text": ["foo"] * 100})
num_examples, num_bytes = writer.finalize()
split_generator.split_info.num_examples = num_examples
split_generator.split_info.num_bytes = num_bytes
def test_write_batch_schema(self):
fields = {"col_1": pa.string(), "col_2": pa.int64()}
output = pa.BufferOutputStream()
writer = ArrowWriter(stream=output, schema=pa.schema(fields))
writer.write_batch({"col_1": ["foo", "bar"], "col_2": [1, 2]})
num_examples, num_bytes = writer.finalize()
self.assertEqual(num_examples, 2)
self.assertGreater(num_bytes, 0)
self.assertEqual(writer._schema,
pa.schema(fields, metadata=writer._schema.metadata))
self._check_output(output.getvalue())
def test_write_file(self):
with tempfile.TemporaryDirectory() as tmp_dir:
fields = {"col_1": pa.string(), "col_2": pa.int64()}
output = os.path.join(tmp_dir, "test.arrow")
writer = ArrowWriter(path=output, schema=pa.schema(fields))
writer.write_batch({"col_1": ["foo", "bar"], "col_2": [1, 2]})
num_examples, num_bytes = writer.finalize()
self.assertEqual(num_examples, 2)
self.assertGreater(num_bytes, 0)
self.assertEqual(
writer._schema,
pa.schema(fields, metadata=writer._schema.metadata))
self._check_output(output)
def test_as_dataset(self):
with tempfile.TemporaryDirectory() as tmp_dir:
dummy_builder = DummyBuilder(cache_dir=tmp_dir, name="dummy")
os.makedirs(dummy_builder.cache_dir)
dummy_builder.info.splits = SplitDict()
dummy_builder.info.splits.add(SplitInfo("train", num_examples=10))
dummy_builder.info.splits.add(SplitInfo("test", num_examples=10))
for split in dummy_builder.info.splits:
writer = ArrowWriter(
path=os.path.join(dummy_builder.cache_dir,
f"dummy_builder-{split}.arrow"),
features=Features({"text": Value("string")}),
)
writer.write_batch({"text": ["foo"] * 10})
writer.finalize()
dsets = dummy_builder.as_dataset()
self.assertIsInstance(dsets, DatasetDict)
self.assertListEqual(list(dsets.keys()), ["train", "test"])
self.assertEqual(len(dsets["train"]), 10)
self.assertEqual(len(dsets["test"]), 10)
self.assertDictEqual(dsets["train"].features,
Features({"text": Value("string")}))
self.assertDictEqual(dsets["test"].features,
Features({"text": Value("string")}))
self.assertListEqual(dsets["train"].column_names, ["text"])
self.assertListEqual(dsets["test"].column_names, ["text"])
del dsets
dset = dummy_builder.as_dataset("train")
self.assertIsInstance(dset, Dataset)
self.assertEqual(dset.split, "train")
self.assertEqual(len(dset), 10)
self.assertDictEqual(dset.features,
Features({"text": Value("string")}))
self.assertListEqual(dset.column_names, ["text"])
del dset
dset = dummy_builder.as_dataset("train+test[:30%]")
self.assertIsInstance(dset, Dataset)
self.assertEqual(dset.split, "train+test[:30%]")
self.assertEqual(len(dset), 13)
self.assertDictEqual(dset.features,
Features({"text": Value("string")}))
self.assertListEqual(dset.column_names, ["text"])
del dset
def test_write_batch(self, array_feature, shape_1, shape_2):
with tempfile.TemporaryDirectory() as tmp_dir:
my_features = self.get_features(array_feature, shape_1, shape_2)
writer = ArrowWriter(features=my_features,
path=os.path.join(tmp_dir, "beta.arrow"))
dict_examples = self.get_dict_examples(shape_1, shape_2)
dict_examples = my_features.encode_batch(dict_examples)
writer.write_batch(dict_examples)
num_examples, num_bytes = writer.finalize()
dataset = datasets.Dataset.from_file(
os.path.join(tmp_dir, "beta.arrow"))
self._check_getitem_output_type(dataset, shape_1, shape_2,
dict_examples["matrix"][0])
def test_builder_as_dataset(split, expected_dataset_class,
expected_dataset_length, in_memory, tmp_path):
cache_dir = str(tmp_path)
dummy_builder = DummyBuilder(cache_dir=cache_dir, name="dummy")
os.makedirs(dummy_builder.cache_dir)
dummy_builder.info.splits = SplitDict()
dummy_builder.info.splits.add(SplitInfo("train", num_examples=10))
dummy_builder.info.splits.add(SplitInfo("test", num_examples=10))
for info_split in dummy_builder.info.splits:
writer = ArrowWriter(
path=os.path.join(dummy_builder.cache_dir,
f"dummy_builder-{info_split}.arrow"),
features=Features({"text": Value("string")}),
)
writer.write_batch({"text": ["foo"] * 10})
writer.finalize()
previous_allocated_memory = pa.total_allocated_bytes()
dataset = dummy_builder.as_dataset(split=split, in_memory=in_memory)
increased_allocated_memory = (pa.total_allocated_bytes() -
previous_allocated_memory) > 0
assert isinstance(dataset, expected_dataset_class)
if isinstance(dataset, DatasetDict):
assert list(dataset.keys()) == ["train", "test"]
datasets = dataset.values()
expected_splits = ["train", "test"]
elif isinstance(dataset, Dataset):
datasets = [dataset]
expected_splits = [split]
for dataset, expected_split in zip(datasets, expected_splits):
assert dataset.split == expected_split
assert len(dataset) == expected_dataset_length
assert dataset.features == Features({"text": Value("string")})
dataset.column_names == ["text"]
assert increased_allocated_memory == in_memory
def test_as_dataset_with_post_process_with_index(self):
def _post_process(self, dataset, resources_paths):
if os.path.exists(resources_paths["index"]):
dataset.load_faiss_index("my_index", resources_paths["index"])
return dataset
else:
dataset.add_faiss_index_from_external_arrays(
external_arrays=np.ones((len(dataset), 8)),
string_factory="Flat",
index_name="my_index")
dataset.save_faiss_index("my_index", resources_paths["index"])
return dataset
def _post_processing_resources(self, split):
return {"index": "Flat-{split}.faiss".format(split=split)}
with tempfile.TemporaryDirectory() as tmp_dir:
dummy_builder = DummyBuilder(cache_dir=tmp_dir, name="dummy")
dummy_builder._post_process = types.MethodType(
_post_process, dummy_builder)
dummy_builder._post_processing_resources = types.MethodType(
_post_processing_resources, dummy_builder)
os.makedirs(dummy_builder.cache_dir)
dummy_builder.info.splits = SplitDict()
dummy_builder.info.splits.add(SplitInfo("train", num_examples=10))
dummy_builder.info.splits.add(SplitInfo("test", num_examples=10))
for split in dummy_builder.info.splits:
writer = ArrowWriter(
path=os.path.join(dummy_builder.cache_dir,
f"dummy_builder-{split}.arrow"),
features=Features({"text": Value("string")}),
)
writer.write_batch({"text": ["foo"] * 10})
writer.finalize()
writer = ArrowWriter(
path=os.path.join(dummy_builder.cache_dir,
f"small_dataset-{split}.arrow"),
features=Features({"text": Value("string")}),
)
writer.write_batch({"text": ["foo"] * 2})
writer.finalize()
dsets = dummy_builder.as_dataset()
self.assertIsInstance(dsets, DatasetDict)
self.assertListEqual(list(dsets.keys()), ["train", "test"])
self.assertEqual(len(dsets["train"]), 10)
self.assertEqual(len(dsets["test"]), 10)
self.assertDictEqual(dsets["train"].features,
Features({"text": Value("string")}))
self.assertDictEqual(dsets["test"].features,
Features({"text": Value("string")}))
self.assertListEqual(dsets["train"].column_names, ["text"])
self.assertListEqual(dsets["test"].column_names, ["text"])
self.assertListEqual(dsets["train"].list_indexes(), ["my_index"])
self.assertListEqual(dsets["test"].list_indexes(), ["my_index"])
self.assertGreater(dummy_builder.info.post_processing_size, 0)
self.assertGreater(
dummy_builder.info.post_processed.resources_checksums["train"]
["index"]["num_bytes"], 0)
del dsets
dset = dummy_builder.as_dataset("train")
self.assertIsInstance(dset, Dataset)
self.assertEqual(dset.split, "train")
self.assertEqual(len(dset), 10)
self.assertDictEqual(dset.features,
Features({"text": Value("string")}))
self.assertListEqual(dset.column_names, ["text"])
self.assertListEqual(dset.list_indexes(), ["my_index"])
del dset
dset = dummy_builder.as_dataset("train+test[:30%]")
self.assertIsInstance(dset, Dataset)
self.assertEqual(dset.split, "train+test[:30%]")
self.assertEqual(len(dset), 13)
self.assertDictEqual(dset.features,
Features({"text": Value("string")}))
self.assertListEqual(dset.column_names, ["text"])
self.assertListEqual(dset.list_indexes(), ["my_index"])
del dset
def test_as_dataset_with_post_process(self):
def _post_process(self, dataset, resources_paths):
def char_tokenize(example):
return {"tokens": list(example["text"])}
return dataset.map(
char_tokenize,
cache_file_name=resources_paths["tokenized_dataset"])
def _post_processing_resources(self, split):
return {
"tokenized_dataset":
"tokenized_dataset-{split}.arrow".format(split=split)
}
with tempfile.TemporaryDirectory() as tmp_dir:
dummy_builder = DummyBuilder(cache_dir=tmp_dir, name="dummy")
dummy_builder.info.post_processed = PostProcessedInfo(
features=Features({
"text": Value("string"),
"tokens": [Value("string")]
}))
dummy_builder._post_process = types.MethodType(
_post_process, dummy_builder)
dummy_builder._post_processing_resources = types.MethodType(
_post_processing_resources, dummy_builder)
os.makedirs(dummy_builder.cache_dir)
dummy_builder.info.splits = SplitDict()
dummy_builder.info.splits.add(SplitInfo("train", num_examples=10))
dummy_builder.info.splits.add(SplitInfo("test", num_examples=10))
for split in dummy_builder.info.splits:
writer = ArrowWriter(
path=os.path.join(dummy_builder.cache_dir,
f"dummy_builder-{split}.arrow"),
features=Features({"text": Value("string")}),
)
writer.write_batch({"text": ["foo"] * 10})
writer.finalize()
writer = ArrowWriter(
path=os.path.join(dummy_builder.cache_dir,
f"tokenized_dataset-{split}.arrow"),
features=Features({
"text": Value("string"),
"tokens": [Value("string")]
}),
)
writer.write_batch({
"text": ["foo"] * 10,
"tokens": [list("foo")] * 10
})
writer.finalize()
dsets = dummy_builder.as_dataset()
self.assertIsInstance(dsets, DatasetDict)
self.assertListEqual(list(dsets.keys()), ["train", "test"])
self.assertEqual(len(dsets["train"]), 10)
self.assertEqual(len(dsets["test"]), 10)
self.assertDictEqual(
dsets["train"].features,
Features({
"text": Value("string"),
"tokens": [Value("string")]
}))
self.assertDictEqual(
dsets["test"].features,
Features({
"text": Value("string"),
"tokens": [Value("string")]
}))
self.assertListEqual(dsets["train"].column_names,
["text", "tokens"])
self.assertListEqual(dsets["test"].column_names,
["text", "tokens"])
del dsets
dset = dummy_builder.as_dataset("train")
self.assertIsInstance(dset, Dataset)
self.assertEqual(dset.split, "train")
self.assertEqual(len(dset), 10)
self.assertDictEqual(
dset.features,
Features({
"text": Value("string"),
"tokens": [Value("string")]
}))
self.assertListEqual(dset.column_names, ["text", "tokens"])
self.assertGreater(dummy_builder.info.post_processing_size, 0)
self.assertGreater(
dummy_builder.info.post_processed.resources_checksums["train"]
["tokenized_dataset"]["num_bytes"], 0)
del dset
dset = dummy_builder.as_dataset("train+test[:30%]")
self.assertIsInstance(dset, Dataset)
self.assertEqual(dset.split, "train+test[:30%]")
self.assertEqual(len(dset), 13)
self.assertDictEqual(
dset.features,
Features({
"text": Value("string"),
"tokens": [Value("string")]
}))
self.assertListEqual(dset.column_names, ["text", "tokens"])
del dset
def _post_process(self, dataset, resources_paths):
return dataset.select([0, 1], keep_in_memory=True)
with tempfile.TemporaryDirectory() as tmp_dir:
dummy_builder = DummyBuilder(cache_dir=tmp_dir, name="dummy")
dummy_builder._post_process = types.MethodType(
_post_process, dummy_builder)
os.makedirs(dummy_builder.cache_dir)
dummy_builder.info.splits = SplitDict()
dummy_builder.info.splits.add(SplitInfo("train", num_examples=10))
dummy_builder.info.splits.add(SplitInfo("test", num_examples=10))
for split in dummy_builder.info.splits:
writer = ArrowWriter(
path=os.path.join(dummy_builder.cache_dir,
f"dummy_builder-{split}.arrow"),
features=Features({"text": Value("string")}),
)
writer.write_batch({"text": ["foo"] * 10})
writer.finalize()
writer = ArrowWriter(
path=os.path.join(dummy_builder.cache_dir,
f"small_dataset-{split}.arrow"),
features=Features({"text": Value("string")}),
)
writer.write_batch({"text": ["foo"] * 2})
writer.finalize()
dsets = dummy_builder.as_dataset()
self.assertIsInstance(dsets, DatasetDict)
self.assertListEqual(list(dsets.keys()), ["train", "test"])
self.assertEqual(len(dsets["train"]), 2)
self.assertEqual(len(dsets["test"]), 2)
self.assertDictEqual(dsets["train"].features,
Features({"text": Value("string")}))
self.assertDictEqual(dsets["test"].features,
Features({"text": Value("string")}))
self.assertListEqual(dsets["train"].column_names, ["text"])
self.assertListEqual(dsets["test"].column_names, ["text"])
del dsets
dset = dummy_builder.as_dataset("train")
self.assertIsInstance(dset, Dataset)
self.assertEqual(dset.split, "train")
self.assertEqual(len(dset), 2)
self.assertDictEqual(dset.features,
Features({"text": Value("string")}))
self.assertListEqual(dset.column_names, ["text"])
del dset
dset = dummy_builder.as_dataset("train+test[:30%]")
self.assertIsInstance(dset, Dataset)
self.assertEqual(dset.split, "train+test[:30%]")
self.assertEqual(len(dset), 2)
self.assertDictEqual(dset.features,
Features({"text": Value("string")}))
self.assertListEqual(dset.column_names, ["text"])
del dset
