Skip to content

Support pandas 1.3.0 read_csv #2593

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Jul 5, 2021
Merged

Support pandas 1.3.0 read_csv #2593

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
a53fdfe
support pandas 1.3.0 read_csv
lhoestq Jul 5, 2021
21aa683
style
lhoestq Jul 5, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
88 changes: 49 additions & 39 deletions src/datasets/packaged_modules/csv/csv.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,6 +11,9 @@

logger = datasets.utils.logging.get_logger(__name__)

_PANDAS_READ_CSV_NO_DEFAULT_PARAMETERS = ["names", "prefix"]
_PANDAS_READ_CSV_DEPRECATED_PARAMETERS = ["warn_bad_lines", "error_bad_lines"]


@dataclass
class CsvConfig(datasets.BuilderConfig):
Expand Down Expand Up @@ -60,6 +63,51 @@ def __post_init__(self):
if self.column_names is not None:
self.names = self.column_names

@property
def read_csv_kwargs(self):
read_csv_kwargs = dict(
sep=self.sep,
header=self.header,
names=self.names,
index_col=self.index_col,
usecols=self.usecols,
prefix=self.prefix,
mangle_dupe_cols=self.mangle_dupe_cols,
engine=self.engine,
true_values=self.true_values,
false_values=self.false_values,
skipinitialspace=self.skipinitialspace,
skiprows=self.skiprows,
nrows=self.nrows,
na_values=self.na_values,
keep_default_na=self.keep_default_na,
na_filter=self.na_filter,
verbose=self.verbose,
skip_blank_lines=self.skip_blank_lines,
thousands=self.thousands,
decimal=self.decimal,
lineterminator=self.lineterminator,
quotechar=self.quotechar,
quoting=self.quoting,
escapechar=self.escapechar,
comment=self.comment,
encoding=self.encoding,
dialect=self.dialect,
error_bad_lines=self.error_bad_lines,
warn_bad_lines=self.warn_bad_lines,
skipfooter=self.skipfooter,
doublequote=self.doublequote,
memory_map=self.memory_map,
float_precision=self.float_precision,
chunksize=self.chunksize,
)
# some kwargs must not be passed if they don't have a default value
# some others are deprecated and we can also not pass them if they are the default value
for read_csv_parameter in _PANDAS_READ_CSV_NO_DEFAULT_PARAMETERS + _PANDAS_READ_CSV_DEPRECATED_PARAMETERS:
if read_csv_kwargs[read_csv_parameter] == getattr(CsvConfig(), read_csv_parameter):
del read_csv_kwargs[read_csv_parameter]
return read_csv_kwargs


class Csv(datasets.ArrowBasedBuilder):
BUILDER_CONFIG_CLASS = CsvConfig
Expand Down Expand Up @@ -89,45 +137,7 @@ def _generate_tables(self, files):
# dtype allows reading an int column as str
dtype = {name: dtype.to_pandas_dtype() for name, dtype in zip(schema.names, schema.types)} if schema else None
for file_idx, file in enumerate(files):
csv_file_reader = pd.read_csv(
file,
iterator=True,
dtype=dtype,
sep=self.config.sep,
header=self.config.header,
names=self.config.names,
index_col=self.config.index_col,
usecols=self.config.usecols,
prefix=self.config.prefix,
mangle_dupe_cols=self.config.mangle_dupe_cols,
engine=self.config.engine,
true_values=self.config.true_values,
false_values=self.config.false_values,
skipinitialspace=self.config.skipinitialspace,
skiprows=self.config.skiprows,
nrows=self.config.nrows,
na_values=self.config.na_values,
keep_default_na=self.config.keep_default_na,
na_filter=self.config.na_filter,
verbose=self.config.verbose,
skip_blank_lines=self.config.skip_blank_lines,
thousands=self.config.thousands,
decimal=self.config.decimal,
lineterminator=self.config.lineterminator,
quotechar=self.config.quotechar,
quoting=self.config.quoting,
escapechar=self.config.escapechar,
comment=self.config.comment,
encoding=self.config.encoding,
dialect=self.config.dialect,
error_bad_lines=self.config.error_bad_lines,
warn_bad_lines=self.config.warn_bad_lines,
skipfooter=self.config.skipfooter,
doublequote=self.config.doublequote,
memory_map=self.config.memory_map,
float_precision=self.config.float_precision,
chunksize=self.config.chunksize,
)
csv_file_reader = pd.read_csv(file, iterator=True, dtype=dtype, **self.config.read_csv_kwargs)

try:
for batch_idx, df in enumerate(csv_file_reader):
Expand Down