Skip to content

Frame ops prelims - de-duplicate, remove unused kwargs #19522

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 8 commits into from
Feb 7, 2018
Merged

Frame ops prelims - de-duplicate, remove unused kwargs #19522

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
a8cc5c0
de-duplicate, remove unused arguments
jbrockmendel Feb 3, 2018
ce3e616
avoid nameerror
jbrockmendel Feb 3, 2018
cffcf31
Merge branch 'master' of https://github.com/pandas-dev/pandas into op…
jbrockmendel Feb 4, 2018
6c0811a
requested edits
jbrockmendel Feb 4, 2018
2de0268
test, whatsnew note
jbrockmendel Feb 6, 2018
92749dc
Merge branch 'master' of https://github.com/pandas-dev/pandas into op…
jbrockmendel Feb 6, 2018
98fdcef
flesh out whatsnew
jbrockmendel Feb 6, 2018
85d501c
Fixup columns changed
jbrockmendel Feb 6, 2018
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
49 changes: 18 additions & 31 deletions pandas/core/frame.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3907,8 +3907,7 @@ def reorder_levels(self, order, axis=0):
# ----------------------------------------------------------------------
# Arithmetic / combination related

def _combine_frame(self, other, func, fill_value=None, level=None,
try_cast=True):
def _combine_frame(self, other, func, fill_value=None, level=None):
this, other = self.align(other, join='outer', level=level, copy=False)
new_index, new_columns = this.index, this.columns

Expand Down Expand Up @@ -3960,52 +3959,40 @@ def f(i):

def _combine_series(self, other, func, fill_value=None, axis=None,
level=None, try_cast=True):
if fill_value is not None:
raise NotImplementedError("fill_value %r not supported." %
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

is this hit in tests?

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

can you use .format() here instead

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Yes to both. tests.frame.test_operators.TestDataFrameOperators.test_arith_flex_frame:

        with tm.assert_raises_regex(NotImplementedError, 'fill_value'):
           self.frame.add(self.frame.iloc[0], fill_value=3)

fill_value)

if axis is not None:
axis = self._get_axis_name(axis)
if axis == 'index':
return self._combine_match_index(other, func, level=level,
fill_value=fill_value,
try_cast=try_cast)
return self._combine_match_index(other, func, level=level)
else:
return self._combine_match_columns(other, func, level=level,
fill_value=fill_value,
try_cast=try_cast)
return self._combine_series_infer(other, func, level=level,
fill_value=fill_value,
try_cast=try_cast)
else:
if len(other) == 0:
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

not len

return self * np.nan

def _combine_series_infer(self, other, func, level=None,
fill_value=None, try_cast=True):
if len(other) == 0:
return self * np.nan
if len(self) == 0:
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

same

# Ambiguous case, use _series so works with DataFrame
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

what is this comment?

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Not totally sure. Possibly a holdover from higher-dim implementation?

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Blame shows that this comment was introduced in c35a39d in 2011. Looks like it replaced a comment # Ambiguous case, use _series so works with DataMatrix. @wesm is this still relevant? Suggestions for fleshing this out?

return self._constructor(data=self._series, index=self.index,
columns=self.columns)

if len(self) == 0:
# Ambiguous case, use _series so works with DataFrame
return self._constructor(data=self._series, index=self.index,
columns=self.columns)
# default axis is columns
return self._combine_match_columns(other, func, level=level,
try_cast=try_cast)

return self._combine_match_columns(other, func, level=level,
fill_value=fill_value,
try_cast=try_cast)

def _combine_match_index(self, other, func, level=None,
fill_value=None, try_cast=True):
def _combine_match_index(self, other, func, level=None):
left, right = self.align(other, join='outer', axis=0, level=level,
copy=False)
if fill_value is not None:
raise NotImplementedError("fill_value %r not supported." %
fill_value)
return self._constructor(func(left.values.T, right.values).T,
index=left.index, columns=self.columns,
copy=False)

def _combine_match_columns(self, other, func, level=None,
fill_value=None, try_cast=True):
def _combine_match_columns(self, other, func, level=None, try_cast=True):
left, right = self.align(other, join='outer', axis=1, level=level,
copy=False)
if fill_value is not None:
raise NotImplementedError("fill_value %r not supported" %
fill_value)

new_data = left._data.eval(func=func, other=right,
axes=[left.columns, self.index],
Expand Down
47 changes: 20 additions & 27 deletions pandas/core/indexes/base.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -80,6 +80,26 @@ def _try_get_item(x):
return x


def _make_invalid_op(name):
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

consider moving this function to core/ops (and parameterizing so you can use it for index/series)

"""
Return a binary method that always raises a TypeError.

Parameters
----------
name : str

Returns
-------
invalid_op : function
"""
def invalid_op(self, other=None):
raise TypeError("cannot perform {name} with this index type: "
"{typ}".format(name=name, typ=type(self)))

invalid_op.__name__ = name
return invalid_op


class InvalidIndexError(Exception):
pass

Expand Down Expand Up @@ -3916,30 +3936,12 @@ def _evaluate_compare(self, other):
@classmethod
def _add_numeric_methods_add_sub_disabled(cls):
""" add in the numeric add/sub methods to disable """

def _make_invalid_op(name):
def invalid_op(self, other=None):
raise TypeError("cannot perform {name} with this index type: "
"{typ}".format(name=name, typ=type(self)))

invalid_op.__name__ = name
return invalid_op

cls.__add__ = cls.__radd__ = __iadd__ = _make_invalid_op('__add__') # noqa
cls.__sub__ = __isub__ = _make_invalid_op('__sub__') # noqa

@classmethod
def _add_numeric_methods_disabled(cls):
""" add in numeric methods to disable other than add/sub """

def _make_invalid_op(name):
def invalid_op(self, other=None):
raise TypeError("cannot perform {name} with this index type: "
"{typ}".format(name=name, typ=type(self)))

invalid_op.__name__ = name
return invalid_op

cls.__pow__ = cls.__rpow__ = _make_invalid_op('__pow__')
cls.__mul__ = cls.__rmul__ = _make_invalid_op('__mul__')
cls.__floordiv__ = cls.__rfloordiv__ = _make_invalid_op('__floordiv__')
Expand Down Expand Up @@ -4145,15 +4147,6 @@ def logical_func(self, *args, **kwargs):
@classmethod
def _add_logical_methods_disabled(cls):
""" add in logical methods to disable """

def _make_invalid_op(name):
def invalid_op(self, other=None):
raise TypeError("cannot perform {name} with this index type: "
"{typ}".format(name=name, typ=type(self)))

invalid_op.__name__ = name
return invalid_op

cls.all = _make_invalid_op('all')
cls.any = _make_invalid_op('any')

Expand Down
8 changes: 5 additions & 3 deletions pandas/core/ops.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1070,12 +1070,13 @@ def f(self, other, axis=default_axis, level=None, fill_value=None):
if isinstance(other, ABCDataFrame): # Another DataFrame
return self._combine_frame(other, na_op, fill_value, level)
elif isinstance(other, ABCSeries):
return self._combine_series(other, na_op, fill_value, axis, level)
return self._combine_series(other, na_op, fill_value, axis, level,
try_cast=True)
else:
if fill_value is not None:
self = self.fillna(fill_value)

return self._combine_const(other, na_op)
return self._combine_const(other, na_op, try_cast=True)

f.__name__ = name

Expand Down Expand Up @@ -1136,7 +1137,8 @@ def f(self, other):
if isinstance(other, ABCDataFrame): # Another DataFrame
return self._compare_frame(other, func, str_rep)
elif isinstance(other, ABCSeries):
return self._combine_series_infer(other, func, try_cast=False)
return self._combine_series(other, func,
axis=None, try_cast=False)
else:

# straight boolean comparisons we want to allow all columns
Expand Down
14 changes: 4 additions & 10 deletions pandas/core/sparse/frame.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -540,8 +540,7 @@ def xs(self, key, axis=0, copy=False):
# ----------------------------------------------------------------------
# Arithmetic-related methods

def _combine_frame(self, other, func, fill_value=None, level=None,
try_cast=True):
def _combine_frame(self, other, func, fill_value=None, level=None):
this, other = self.align(other, join='outer', level=level, copy=False)
new_index, new_columns = this.index, this.columns

Expand Down Expand Up @@ -584,12 +583,9 @@ def _combine_frame(self, other, func, fill_value=None, level=None,
default_fill_value=new_fill_value
).__finalize__(self)

def _combine_match_index(self, other, func, level=None, fill_value=None,
try_cast=True):
def _combine_match_index(self, other, func, level=None):
new_data = {}

if fill_value is not None:
raise NotImplementedError("'fill_value' argument is not supported")
if level is not None:
raise NotImplementedError("'level' argument is not supported")

Expand All @@ -605,6 +601,7 @@ def _combine_match_index(self, other, func, level=None, fill_value=None,
new_data[col] = func(series.values, other.values)

# fill_value is a function of our operator
fill_value = None
if isna(other.fill_value) or isna(self.default_fill_value):
fill_value = np.nan
else:
Expand All @@ -615,15 +612,12 @@ def _combine_match_index(self, other, func, level=None, fill_value=None,
new_data, index=new_index, columns=self.columns,
default_fill_value=fill_value).__finalize__(self)

def _combine_match_columns(self, other, func, level=None, fill_value=None,
try_cast=True):
def _combine_match_columns(self, other, func, level=None, try_cast=True):
# patched version of DataFrame._combine_match_columns to account for
# NumPy circumventing __rsub__ with float64 types, e.g.: 3.0 - series,
# where 3.0 is numpy.float64 and series is a SparseSeries. Still
# possible for this to happen, which is bothersome

if fill_value is not None:
raise NotImplementedError("'fill_value' argument is not supported")
if level is not None:
raise NotImplementedError("'level' argument is not supported")

Expand Down