Skip to content

Add remove_from_default_na options to read_csv, read_excel... #55280

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

Closed
wants to merge 4 commits into from
Closed

Add remove_from_default_na options to read_csv, read_excel... #55280

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
669adb9
Add remove_from_default_na options to read_csv, read_excel...
oda Sep 25, 2023
8fe299c
Nit: Fix typo and lint.
oda Sep 25, 2023
1733f4b
Fix docstring.
oda Sep 25, 2023
94a9a18
Nit: Fix lint.
oda Sep 25, 2023
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
41 changes: 36 additions & 5 deletions pandas/io/parsers/readers.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -211,6 +211,9 @@
+ fill('", "'.join(sorted(STR_NA_VALUES)), 70, subsequent_indent=" ")
+ """ ".

remove_from_default_na : Hashable or Iterable of Hashable, optional
Remvoe values from the default ``NaN`` values when parsing the data.

keep_default_na : bool, default True
Whether or not to include the default ``NaN`` values when parsing the data.
Depending on whether ``na_values`` is passed in, the behavior is as follows:
Expand Down Expand Up @@ -718,6 +721,9 @@ def read_csv(
| Iterable[Hashable]
| Mapping[Hashable, Iterable[Hashable]]
| None = ...,
remove_from_default_na: Hashable
| Iterable[Hashable]
| None = ...,
keep_default_na: bool = ...,
na_filter: bool = ...,
verbose: bool = ...,
Expand Down Expand Up @@ -781,6 +787,9 @@ def read_csv(
| Iterable[Hashable]
| Mapping[Hashable, Iterable[Hashable]]
| None = ...,
remove_from_default_na: Hashable
| Iterable[Hashable]
| None = ...,
keep_default_na: bool = ...,
na_filter: bool = ...,
verbose: bool = ...,
Expand Down Expand Up @@ -844,6 +853,9 @@ def read_csv(
| Iterable[Hashable]
| Mapping[Hashable, Iterable[Hashable]]
| None = ...,
remove_from_default_na: Hashable
| Iterable[Hashable]
| None = ...,
keep_default_na: bool = ...,
na_filter: bool = ...,
verbose: bool = ...,
Expand Down Expand Up @@ -920,6 +932,9 @@ def read_csv(
| Iterable[Hashable]
| Mapping[Hashable, Iterable[Hashable]]
| None = None,
remove_from_default_na: Hashable
| Iterable[Hashable]
| None = ...,
keep_default_na: bool = True,
na_filter: bool = True,
verbose: bool = False,
Expand Down Expand Up @@ -1013,6 +1028,7 @@ def read_table(
skipfooter: int = ...,
nrows: int | None = ...,
na_values: Sequence[str] | Mapping[str, Sequence[str]] | None = ...,
remove_from_default_na: Sequence[str] | None = ...,
keep_default_na: bool = ...,
na_filter: bool = ...,
verbose: bool = ...,
Expand Down Expand Up @@ -1073,6 +1089,7 @@ def read_table(
skipfooter: int = ...,
nrows: int | None = ...,
na_values: Sequence[str] | Mapping[str, Sequence[str]] | None = ...,
remove_from_default_na: Sequence[str] | None = ...,
keep_default_na: bool = ...,
na_filter: bool = ...,
verbose: bool = ...,
Expand Down Expand Up @@ -1133,6 +1150,7 @@ def read_table(
skipfooter: int = ...,
nrows: int | None = ...,
na_values: Sequence[str] | Mapping[str, Sequence[str]] | None = ...,
remove_from_default_na: Sequence[str] | None = ...,
keep_default_na: bool = ...,
na_filter: bool = ...,
verbose: bool = ...,
Expand Down Expand Up @@ -1193,6 +1211,7 @@ def read_table(
skipfooter: int = ...,
nrows: int | None = ...,
na_values: Sequence[str] | Mapping[str, Sequence[str]] | None = ...,
remove_from_default_na: Sequence[str] | None = ...,
keep_default_na: bool = ...,
na_filter: bool = ...,
verbose: bool = ...,
Expand Down Expand Up @@ -1268,6 +1287,7 @@ def read_table(
nrows: int | None = None,
# NA and Missing Data Handling
na_values: Sequence[str] | Mapping[str, Sequence[str]] | None = None,
remove_from_default_na: Sequence[str] | None = ...,
keep_default_na: bool = True,
na_filter: bool = True,
verbose: bool = False,
Expand Down Expand Up @@ -1740,7 +1760,10 @@ def _clean_options(

# Converting values to NA
keep_default_na = options["keep_default_na"]
na_values, na_fvalues = _clean_na_values(na_values, keep_default_na)
remove_from_default_na = options["remove_from_default_na"]
na_values, na_fvalues = _clean_na_values(
na_values, remove_from_default_na, keep_default_na
)

# handle skiprows; this is internally handled by the
# c-engine, so only need for python and pyarrow parsers
Expand Down Expand Up @@ -1916,6 +1939,8 @@ def TextParser(*args, **kwds) -> TextFileReader:
not in the header.
na_values : scalar, str, list-like, or dict, optional
Additional strings to recognize as NA/NaN.
remove_from_default_na : scalar, str, list-like, or dict, optional
Strings not to recognize as NA/NaN.
keep_default_na : bool, default True
thousands : str, optional
Thousands separator
Expand Down Expand Up @@ -1952,11 +1977,17 @@ def TextParser(*args, **kwds) -> TextFileReader:
return TextFileReader(*args, **kwds)


def _clean_na_values(na_values, keep_default_na: bool = True):
def _clean_na_values(na_values, remove_from_default_na, keep_default_na: bool = True):
na_fvalues: set | dict
if remove_from_default_na is None:
remove_from_default_na = set()
elif not is_list_like(remove_from_default_na):
remove_from_default_na = set([remove_from_default_na])
else:
remove_from_default_na = set(remove_from_default_na)
if na_values is None:
if keep_default_na:
na_values = STR_NA_VALUES
na_values = STR_NA_VALUES - remove_from_default_na
else:
na_values = set()
na_fvalues = set()
Expand All @@ -1973,7 +2004,7 @@ def _clean_na_values(na_values, keep_default_na: bool = True):
v = [v]

if keep_default_na:
v = set(v) | STR_NA_VALUES
v = set(v) | (STR_NA_VALUES - remove_from_default_na)

na_values[k] = v
na_fvalues = {k: _floatify_na_values(v) for k, v in na_values.items()}
Expand All @@ -1982,7 +2013,7 @@ def _clean_na_values(na_values, keep_default_na: bool = True):
na_values = [na_values]
na_values = _stringify_na_values(na_values)
if keep_default_na:
na_values = na_values | STR_NA_VALUES
na_values = na_values | (STR_NA_VALUES - remove_from_default_na)

na_fvalues = _floatify_na_values(na_values)

Expand Down
20 changes: 20 additions & 0 deletions pandas/tests/io/parser/test_na_values.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -277,6 +277,26 @@ def test_na_value_dict_multi_index(all_parsers, index_col, expected):
}
),
),
(
{"remove_from_default_na": ["nan"]},
DataFrame(
{
"A": ["a", "b", np.nan, "d", "e", "nan", "g"],
"B": [1, 2, 3, 4, 5, 6, 7],
"C": ["one", "two", "three", "nan", "five", np.nan, "seven"],
}
),
),
(
{"na_values": ["nan"], "remove_from_default_na": ["nan"]},
DataFrame(
{
"A": ["a", "b", np.nan, "d", "e", np.nan, "g"],
"B": [1, 2, 3, 4, 5, 6, 7],
"C": ["one", "two", "three", np.nan, "five", np.nan, "seven"],
}
),
),
],
)
def test_na_values_keep_default(all_parsers, kwargs, expected):
Expand Down