def _make_test_datasets(self, inputs, **kwargs):
# Test by comparing its output to what we could get with map->decode_csv
filenames = self.setup_files(inputs)
dataset_expected = core_readers.TextLineDataset(filenames)
dataset_expected = dataset_expected.map(
lambda l: gen_parsing_ops.decode_csv(l, **kwargs))
dataset_actual = readers.CsvDataset(filenames, **kwargs)
return (dataset_actual, dataset_expected)
def decode_csv_v2(records,
record_defaults,
field_delim=",",
use_quote_delim=True,
na_value="",
select_cols=None,
name=None):
"""Convert CSV records to tensors. Each column maps to one tensor.
RFC 4180 format is expected for the CSV records.
(https://tools.ietf.org/html/rfc4180)
Note that we allow leading and trailing spaces with int or float field.
Args:
records: A `Tensor` of type `string`.
Each string is a record/row in the csv and all records should have
the same format.
record_defaults: A list of `Tensor` objects with specific types.
Acceptable types are `float32`, `float64`, `int32`, `int64`, `string`.
One tensor per column of the input record, with either a
scalar default value for that column or an empty vector if the column is
required.
field_delim: An optional `string`. Defaults to `","`.
char delimiter to separate fields in a record.
use_quote_delim: An optional `bool`. Defaults to `True`.
If false, treats double quotation marks as regular
characters inside of the string fields (ignoring RFC 4180, Section 2,
Bullet 5).
na_value: Additional string to recognize as NA/NaN.
select_cols: Optional sorted list of column indices to select. If specified,
only this subset of columns will be parsed and returned.
name: A name for the operation (optional).
Returns:
A list of `Tensor` objects. Has the same type as `record_defaults`.
Each tensor will have the same shape as records.
Raises:
ValueError: If any of the arguments is malformed.
"""
if select_cols is not None and any(select_cols[i] >= select_cols[i + 1]
for i in range(len(select_cols) - 1)):
raise ValueError("select_cols is not strictly increasing.")
if select_cols is not None and select_cols[0] < 0:
raise ValueError("select_cols contains negative values.")
if select_cols is not None and len(select_cols) != len(record_defaults):
raise ValueError(
"Length of select_cols and record_defaults do not match.")
return gen_parsing_ops.decode_csv(
records=records,
record_defaults=record_defaults,
field_delim=field_delim,
use_quote_delim=use_quote_delim,
na_value=na_value,
name=name,
select_cols=select_cols,
)
def benchmarkMapWithStrings(self):
self._setUp(self.STR_VAL)
for i in range(len(self._filenames)):
num_cols = self._num_cols[i]
kwargs = {'record_defaults': [['']] * num_cols}
dataset = core_readers.TextLineDataset(self._filenames[i]).repeat()
dataset = dataset.map(lambda l: gen_parsing_ops.decode_csv(l, **kwargs)) # pylint: disable=cell-var-from-loop
self._runBenchmark(dataset, num_cols, 'csv_strings_map_decode_csv')
self._tearDown()
def benchmarkBatchThenMap(self):
self._setUp()
for i in range(len(self._filenames)):
num_cols = self._num_cols[i]
kwargs = {'record_defaults': [[0.0]] * num_cols}
dataset = core_readers.TextLineDataset(self._filenames[i]).repeat()
dataset = dataset.map(
lambda l: gen_parsing_ops.decode_csv(l, **kwargs)) # pylint: disable=cell-var-from-loop
dataset = dataset.batch(self._batch_size)
self._runBenchmark(dataset, num_cols, 'csv_map_then_batch')
self._tearDown()
