-
-
Notifications
You must be signed in to change notification settings - Fork 18.4k
ENH: support downcasting of nullable EAs in pd.to_numeric #38746
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.
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
Changes from 3 commits
a594847
a1bb9fc
dbba7b4
ddb71cb
323cfdc
7b4180e
337589a
4e8761a
e2b4cbb
23c4ae6
e140b7a
f583a10
a6cb152
d707a61
6b2c39f
fda4ba1
1a23118
1015b07
0279be9
56747da
File filter
Filter by extension
Conversations
Jump to
Diff view
Diff view
There are no files selected for viewing
Original file line number | Diff line number | Diff line change |
---|---|---|
|
@@ -7,6 +7,9 @@ | |
ensure_object, | ||
is_datetime_or_timedelta_dtype, | ||
is_decimal, | ||
is_extension_array_dtype, | ||
is_float_dtype, | ||
is_integer_dtype, | ||
is_number, | ||
is_numeric_dtype, | ||
is_scalar, | ||
|
@@ -15,6 +18,8 @@ | |
from pandas.core.dtypes.generic import ABCIndex, ABCSeries | ||
|
||
import pandas as pd | ||
from pandas.core.arrays.numeric import NumericArray | ||
from pandas.core.construction import extract_array | ||
|
||
|
||
def to_numeric(arg, errors="raise", downcast=None): | ||
|
@@ -118,10 +123,14 @@ def to_numeric(arg, errors="raise", downcast=None): | |
is_series = False | ||
is_index = False | ||
is_scalars = False | ||
is_numeric_extension_dtype = False | ||
|
||
if isinstance(arg, ABCSeries): | ||
is_series = True | ||
values = arg.values | ||
if is_extension_array_dtype(arg) and isinstance(values, NumericArray): | ||
is_numeric_extension_dtype = True | ||
values = extract_array(arg) | ||
elif isinstance(arg, ABCIndex): | ||
is_index = True | ||
if needs_i8_conversion(arg.dtype): | ||
|
@@ -142,6 +151,12 @@ def to_numeric(arg, errors="raise", downcast=None): | |
else: | ||
values = arg | ||
|
||
if is_numeric_extension_dtype or ( | ||
is_extension_array_dtype(arg) and isinstance(values, NumericArray) | ||
): | ||
is_numeric_extension_dtype = True | ||
mask, values = values._mask, values._data | ||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. you likely need to just take the masked values only for the following block of code There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Done |
||
|
||
values_dtype = getattr(values, "dtype", None) | ||
if is_numeric_dtype(values_dtype): | ||
pass | ||
|
@@ -188,6 +203,16 @@ def to_numeric(arg, errors="raise", downcast=None): | |
if values.dtype == dtype: | ||
break | ||
|
||
if is_numeric_extension_dtype: | ||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. L194 might need to handle the mask There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Do you mean?
I feel like there's a testcase I haven't looked at if yes (the ones I have work as is) |
||
if is_integer_dtype(values): | ||
from pandas.core.arrays import IntegerArray | ||
|
||
values = IntegerArray(values, mask) | ||
elif is_float_dtype(values): | ||
from pandas.core.arrays import FloatingArray | ||
|
||
values = FloatingArray(values, mask) | ||
|
||
if is_series: | ||
return arg._constructor(values, index=arg.index, name=arg.name) | ||
elif is_index: | ||
|
Original file line number | Diff line number | Diff line change |
---|---|---|
|
@@ -725,3 +725,19 @@ def test_to_numeric_from_nullable_string(values, expected): | |
s = Series(values, dtype="string") | ||
result = to_numeric(s) | ||
tm.assert_series_equal(result, expected) | ||
|
||
|
||
@pytest.mark.parametrize( | ||
"data, input_dtype, downcast, expected_dtype", | ||
( | ||
([1, 1], "Int64", "integer", "Int8"), | ||
([450, 300], "Int64", "integer", "Int16"), | ||
([1, 1], "Float64", "float", "Float32"), | ||
([1, 1], "Float64", "integer", "Int8"), | ||
arw2019 marked this conversation as resolved.
Show resolved
Hide resolved
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Nit: maybe move this one up to the other "integer" downcast cases There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Done |
||
), | ||
) | ||
def test_downcast_nullable_numeric(data, input_dtype, downcast, expected_dtype): | ||
arr = pd.array(data, dtype=input_dtype) | ||
result = pd.to_numeric(arr, downcast=downcast) | ||
expected = pd.array(data, dtype=expected_dtype) | ||
tm.assert_extension_array_equal(result, expected) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Is this extract_array line needed? (the
values = arg.values
from above should have worked fine, I think)There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
It's not, I reverted this bit