Skip to content

Move docstring of NDFrame.replace in preparation of #32542 #38561

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 3 commits into from
Dec 22, 2020
Merged

Move docstring of NDFrame.replace in preparation of #32542 #38561

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
4a4f319
move shared docs of replace
oguzhanogreden Dec 18, 2020
3ef1d26
revert PRIVATE_IMPORTS_TO_IGNORE and set doc kwargs per module
oguzhanogreden Dec 22, 2020
f968ad0
revert unnecessary line breaks
oguzhanogreden Dec 22, 2020
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
8 changes: 7 additions & 1 deletion pandas/core/frame.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -156,6 +156,7 @@
)
from pandas.core.reshape.melt import melt
from pandas.core.series import Series
from pandas.core.shared_docs import _shared_doc_kwargs as core_shared_doc_kwargs
from pandas.core.sorting import get_group_index, lexsort_indexer, nargsort

from pandas.io.common import get_handle
Expand Down Expand Up @@ -4522,7 +4523,12 @@ def pop(self, item: Label) -> Series:
"""
return super().pop(item=item)

@doc(NDFrame.replace, **_shared_doc_kwargs)
@doc(
NDFrame.replace,
inplace=core_shared_doc_kwargs["inplace"],
replace_iloc=core_shared_doc_kwargs["replace_iloc"],
**_shared_doc_kwargs,
)
def replace(
self,
to_replace=None,
Expand Down
305 changes: 18 additions & 287 deletions pandas/core/generic.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -105,7 +105,7 @@
from pandas.core.internals import BlockManager
from pandas.core.missing import find_valid_index
from pandas.core.ops import align_method_FRAME
from pandas.core.shared_docs import _shared_docs
from pandas.core.shared_docs import _shared_doc_kwargs, _shared_docs
from pandas.core.sorting import get_indexer_indexer
from pandas.core.window import Expanding, ExponentialMovingWindow, Rolling, Window

Expand All @@ -128,15 +128,17 @@
# goal is to be able to define the docs close to function, while still being
# able to share
_shared_docs = {**_shared_docs}
_shared_doc_kwargs = {
"axes": "keywords for axes",
"klass": "Series/DataFrame",
"axes_single_arg": "int or labels for object",
"args_transpose": "axes to permute (int or label for object)",
"optional_by": """
by : str or list of str
Name or list of names to sort by""",
}
_shared_doc_kwargs.update(
{
"axes": "keywords for axes",
"klass": "Series/DataFrame",
"axes_single_arg": "int or labels for object",
"args_transpose": "axes to permute (int or label for object)",
"optional_by": """
by : str or list of str
Name or list of names to sort by""",
}
)


bool_t = bool # Need alias because NDFrame has def bool:
Expand Down Expand Up @@ -6469,7 +6471,12 @@ def bfill(

backfill = bfill

@doc(klass=_shared_doc_kwargs["klass"])
@doc(
_shared_docs["replace"],
klass=_shared_doc_kwargs["klass"],
inplace=_shared_doc_kwargs["inplace"],
replace_iloc=_shared_doc_kwargs["replace_iloc"],
)
def replace(
self,
to_replace=None,
Expand All @@ -6479,282 +6486,6 @@ def replace(
regex=False,
method="pad",
):
"""
Replace values given in `to_replace` with `value`.

Values of the {klass} are replaced with other values dynamically.
This differs from updating with ``.loc`` or ``.iloc``, which require
you to specify a location to update with some value.

Parameters
----------
to_replace : str, regex, list, dict, Series, int, float, or None
How to find the values that will be replaced.

* numeric, str or regex:

- numeric: numeric values equal to `to_replace` will be
replaced with `value`
- str: string exactly matching `to_replace` will be replaced
with `value`
- regex: regexs matching `to_replace` will be replaced with
`value`

* list of str, regex, or numeric:

- First, if `to_replace` and `value` are both lists, they
**must** be the same length.
- Second, if ``regex=True`` then all of the strings in **both**
lists will be interpreted as regexs otherwise they will match
directly. This doesn't matter much for `value` since there
are only a few possible substitution regexes you can use.
- str, regex and numeric rules apply as above.

* dict:

- Dicts can be used to specify different replacement values
for different existing values. For example,
``{{'a': 'b', 'y': 'z'}}`` replaces the value 'a' with 'b' and
'y' with 'z'. To use a dict in this way the `value`
parameter should be `None`.
- For a DataFrame a dict can specify that different values
should be replaced in different columns. For example,
``{{'a': 1, 'b': 'z'}}`` looks for the value 1 in column 'a'
and the value 'z' in column 'b' and replaces these values
with whatever is specified in `value`. The `value` parameter
should not be ``None`` in this case. You can treat this as a
special case of passing two lists except that you are
specifying the column to search in.
- For a DataFrame nested dictionaries, e.g.,
``{{'a': {{'b': np.nan}}}}``, are read as follows: look in column
'a' for the value 'b' and replace it with NaN. The `value`
parameter should be ``None`` to use a nested dict in this
way. You can nest regular expressions as well. Note that
column names (the top-level dictionary keys in a nested
dictionary) **cannot** be regular expressions.

* None:

- This means that the `regex` argument must be a string,
compiled regular expression, or list, dict, ndarray or
Series of such elements. If `value` is also ``None`` then
this **must** be a nested dictionary or Series.

See the examples section for examples of each of these.
value : scalar, dict, list, str, regex, default None
Value to replace any values matching `to_replace` with.
For a DataFrame a dict of values can be used to specify which
value to use for each column (columns not in the dict will not be
filled). Regular expressions, strings and lists or dicts of such
objects are also allowed.
inplace : bool, default False
If True, in place. Note: this will modify any
other views on this object (e.g. a column from a DataFrame).
Returns the caller if this is True.
limit : int or None, default None
Maximum size gap to forward or backward fill.
regex : bool or same types as `to_replace`, default False
Whether to interpret `to_replace` and/or `value` as regular
expressions. If this is ``True`` then `to_replace` *must* be a
string. Alternatively, this could be a regular expression or a
list, dict, or array of regular expressions in which case
`to_replace` must be ``None``.
method : {{'pad', 'ffill', 'bfill', `None`}}
The method to use when for replacement, when `to_replace` is a
scalar, list or tuple and `value` is ``None``.

Returns
-------
{klass} or None
Object after replacement or None if ``inplace=True``.

Raises
------
AssertionError
* If `regex` is not a ``bool`` and `to_replace` is not
``None``.

TypeError
* If `to_replace` is not a scalar, array-like, ``dict``, or ``None``
* If `to_replace` is a ``dict`` and `value` is not a ``list``,
``dict``, ``ndarray``, or ``Series``
* If `to_replace` is ``None`` and `regex` is not compilable
into a regular expression or is a list, dict, ndarray, or
Series.
* When replacing multiple ``bool`` or ``datetime64`` objects and
the arguments to `to_replace` does not match the type of the
value being replaced

ValueError
* If a ``list`` or an ``ndarray`` is passed to `to_replace` and
`value` but they are not the same length.

See Also
--------
{klass}.fillna : Fill NA values.
{klass}.where : Replace values based on boolean condition.
Series.str.replace : Simple string replacement.

Notes
-----
* Regex substitution is performed under the hood with ``re.sub``. The
rules for substitution for ``re.sub`` are the same.
* Regular expressions will only substitute on strings, meaning you
cannot provide, for example, a regular expression matching floating
point numbers and expect the columns in your frame that have a
numeric dtype to be matched. However, if those floating point
numbers *are* strings, then you can do this.
* This method has *a lot* of options. You are encouraged to experiment
and play with this method to gain intuition about how it works.
* When dict is used as the `to_replace` value, it is like
key(s) in the dict are the to_replace part and
value(s) in the dict are the value parameter.

Examples
--------

**Scalar `to_replace` and `value`**

>>> s = pd.Series([0, 1, 2, 3, 4])
>>> s.replace(0, 5)
0 5
1 1
2 2
3 3
4 4
dtype: int64

>>> df = pd.DataFrame({{'A': [0, 1, 2, 3, 4],
... 'B': [5, 6, 7, 8, 9],
... 'C': ['a', 'b', 'c', 'd', 'e']}})
>>> df.replace(0, 5)
A B C
0 5 5 a
1 1 6 b
2 2 7 c
3 3 8 d
4 4 9 e

**List-like `to_replace`**

>>> df.replace([0, 1, 2, 3], 4)
A B C
0 4 5 a
1 4 6 b
2 4 7 c
3 4 8 d
4 4 9 e

>>> df.replace([0, 1, 2, 3], [4, 3, 2, 1])
A B C
0 4 5 a
1 3 6 b
2 2 7 c
3 1 8 d
4 4 9 e

>>> s.replace([1, 2], method='bfill')
0 0
1 3
2 3
3 3
4 4
dtype: int64

**dict-like `to_replace`**

>>> df.replace({{0: 10, 1: 100}})
A B C
0 10 5 a
1 100 6 b
2 2 7 c
3 3 8 d
4 4 9 e

>>> df.replace({{'A': 0, 'B': 5}}, 100)
A B C
0 100 100 a
1 1 6 b
2 2 7 c
3 3 8 d
4 4 9 e

>>> df.replace({{'A': {{0: 100, 4: 400}}}})
A B C
0 100 5 a
1 1 6 b
2 2 7 c
3 3 8 d
4 400 9 e

**Regular expression `to_replace`**

>>> df = pd.DataFrame({{'A': ['bat', 'foo', 'bait'],
... 'B': ['abc', 'bar', 'xyz']}})
>>> df.replace(to_replace=r'^ba.$', value='new', regex=True)
A B
0 new abc
1 foo new
2 bait xyz

>>> df.replace({{'A': r'^ba.$'}}, {{'A': 'new'}}, regex=True)
A B
0 new abc
1 foo bar
2 bait xyz

>>> df.replace(regex=r'^ba.$', value='new')
A B
0 new abc
1 foo new
2 bait xyz

>>> df.replace(regex={{r'^ba.$': 'new', 'foo': 'xyz'}})
A B
0 new abc
1 xyz new
2 bait xyz

>>> df.replace(regex=[r'^ba.$', 'foo'], value='new')
A B
0 new abc
1 new new
2 bait xyz

Compare the behavior of ``s.replace({{'a': None}})`` and
``s.replace('a', None)`` to understand the peculiarities
of the `to_replace` parameter:

>>> s = pd.Series([10, 'a', 'a', 'b', 'a'])

When one uses a dict as the `to_replace` value, it is like the
value(s) in the dict are equal to the `value` parameter.
``s.replace({{'a': None}})`` is equivalent to
``s.replace(to_replace={{'a': None}}, value=None, method=None)``:

>>> s.replace({{'a': None}})
0 10
1 None
2 None
3 b
4 None
dtype: object

When ``value=None`` and `to_replace` is a scalar, list or
tuple, `replace` uses the method parameter (default 'pad') to do the
replacement. So this is why the 'a' values are being replaced by 10
in rows 1 and 2 and 'b' in row 4 in this case.
The command ``s.replace('a', None)`` is actually equivalent to
``s.replace(to_replace='a', value=None, method='pad')``:

>>> s.replace('a', None)
0 10
1 10
2 10
3 b
4 b
dtype: object
"""
if not (
is_scalar(to_replace)
or is_re_compilable(to_replace)
Expand Down
Loading