def _groupby_and_aggregate(self, grouper, how, *args, **kwargs):
""" revaluate the obj with a groupby aggregation """
if grouper is None:
self._set_binner()
grouper = self.grouper
obj = self._selected_obj
try:
grouped = groupby(obj, by=None, grouper=grouper, axis=self.axis)
except TypeError:
# panel grouper
grouped = PanelGroupBy(obj, grouper=grouper, axis=self.axis)
try:
result = grouped.aggregate(how, *args, **kwargs)
except Exception:
# we have a non-reducing function
# try to evaluate
result = grouped.apply(how, *args, **kwargs)
return self._wrap_result(result)
def _groupby_and_aggregate(self, how, grouper=None, *args, **kwargs):
""" re-evaluate the obj with a groupby aggregation """
if grouper is None:
self._set_binner()
grouper = self.grouper
obj = self._selected_obj
try:
grouped = groupby(obj, by=None, grouper=grouper, axis=self.axis)
except TypeError:
# panel grouper
grouped = PanelGroupBy(obj, grouper=grouper, axis=self.axis)
try:
if isinstance(obj, ABCDataFrame) and compat.callable(how):
# Check if the function is reducing or not.
result = grouped._aggregate_item_by_item(how, *args, **kwargs)
else:
result = grouped.aggregate(how, *args, **kwargs)
except Exception:
# we have a non-reducing function
# try to evaluate
result = grouped.apply(how, *args, **kwargs)
result = self._apply_loffset(result)
return self._wrap_result(result)
def groupby(self,
by=None,
axis=0,
level=None,
as_index=True,
sort=True,
group_keys=True,
squeeze=False):
"""
Group series using mapper (dict or key function, apply given function
to group, return result as series) or by a series of columns
Parameters
----------
by : mapping function / list of functions, dict, Series, or tuple /
list of column names.
Called on each element of the object index to determine the groups.
If a dict or Series is passed, the Series or dict VALUES will be
used to determine the groups
axis : int, default 0
level : int, level name, or sequence of such, default None
If the axis is a MultiIndex (hierarchical), group by a particular
level or levels
as_index : boolean, default True
For aggregated output, return object with group labels as the
index. Only relevant for DataFrame input. as_index=False is
effectively "SQL-style" grouped output
sort : boolean, default True
Sort group keys. Get better performance by turning this off
group_keys : boolean, default True
When calling apply, add group keys to index to identify pieces
squeeze : boolean, default False
reduce the dimensionaility of the return type if possible, otherwise
return a consistent type
Examples
--------
# DataFrame result
>>> data.groupby(func, axis=0).mean()
# DataFrame result
>>> data.groupby(['col1', 'col2'])['col3'].mean()
# DataFrame with hierarchical index
>>> data.groupby(['col1', 'col2']).mean()
Returns
-------
GroupBy object
"""
from pandas.core.groupby import groupby
axis = self._get_axis_number(axis)
return groupby(self,
by,
axis=axis,
level=level,
as_index=as_index,
sort=sort,
group_keys=group_keys,
squeeze=squeeze)
def _groupby_and_aggregate(self, how, grouper=None, *args, **kwargs):
""" revaluate the obj with a groupby aggregation """
if grouper is None:
self._set_binner()
grouper = self.grouper
obj = self._selected_obj
try:
grouped = groupby(obj, by=None, grouper=grouper, axis=self.axis)
except TypeError:
# panel grouper
grouped = PanelGroupBy(obj, grouper=grouper, axis=self.axis)
try:
result = grouped.aggregate(how, *args, **kwargs)
except Exception:
# we have a non-reducing function
# try to evaluate
result = grouped.apply(how, *args, **kwargs)
result = self._apply_loffset(result)
return self._wrap_result(result)
def _groupby_and_aggregate(self, how, grouper=None, *args, **kwargs):
""" re-evaluate the obj with a groupby aggregation """
if grouper is None:
self._set_binner()
grouper = self.grouper
obj = self._selected_obj
try:
grouped = groupby(obj, by=None, grouper=grouper, axis=self.axis)
except TypeError:
# panel grouper
grouped = PanelGroupBy(obj, grouper=grouper, axis=self.axis)
try:
if isinstance(obj, ABCDataFrame) and compat.callable(how):
# Check if the function is reducing or not.
result = grouped._aggregate_item_by_item(how, *args, **kwargs)
else:
result = grouped.aggregate(how, *args, **kwargs)
except Exception:
# we have a non-reducing function
# try to evaluate
result = grouped.apply(how, *args, **kwargs)
result = self._apply_loffset(result)
return self._wrap_result(result)
def groupby(self, by=None, axis=0, level=None):
"""
Group series using mapper (dict or key function, apply given function
to group, return result as series) or by a series of columns
Parameters
----------
by : mapping function / list of functions, dict, Series, or tuple /
list of column names.
Called on each element of the object index to determine the groups.
If a dict or Series is passed, the Series or dict VALUES will be
used to determine the groups
axis : int, default 0
level : int, default None
If the axis is a MultiIndex (hierarchical), group by a particular
level
Examples
--------
# DataFrame result
>>> data.groupby(func, axis=0).mean()
# DataFrame result
>>> data.groupby(['col1', 'col2'])['col3'].mean()
# DataFrame with hierarchical index
>>> data.groupby(['col1', 'col2']).mean()
Returns
-------
GroupBy object
"""
from pandas.core.groupby import groupby
return groupby(self, by, axis=axis, level=level)
def groupby(self, by=None, axis=0, level=None, as_index=True, sort=True,
group_keys=True, squeeze=False):
"""
Group series using mapper (dict or key function, apply given function
to group, return result as series) or by a series of columns
Parameters
----------
by : mapping function / list of functions, dict, Series, or tuple /
list of column names.
Called on each element of the object index to determine the groups.
If a dict or Series is passed, the Series or dict VALUES will be
used to determine the groups
axis : int, default 0
level : int, level name, or sequence of such, default None
If the axis is a MultiIndex (hierarchical), group by a particular
level or levels
as_index : boolean, default True
For aggregated output, return object with group labels as the
index. Only relevant for DataFrame input. as_index=False is
effectively "SQL-style" grouped output
sort : boolean, default True
Sort group keys. Get better performance by turning this off
group_keys : boolean, default True
When calling apply, add group keys to index to identify pieces
squeeze : boolean, default False
reduce the dimensionaility of the return type if possible, otherwise
return a consistent type
Examples
--------
# DataFrame result
>>> data.groupby(func, axis=0).mean()
# DataFrame result
>>> data.groupby(['col1', 'col2'])['col3'].mean()
# DataFrame with hierarchical index
>>> data.groupby(['col1', 'col2']).mean()
Returns
-------
GroupBy object
"""
from pandas.core.groupby import groupby
axis = self._get_axis_number(axis)
return groupby(self, by, axis=axis, level=level, as_index=as_index,
sort=sort, group_keys=group_keys,
squeeze=squeeze)
def groupby(self, mapper):
"""
Goup series using mapper (dict or key function, apply given
function to group, return result as series).
Parameters
----------
mapper: function, dict or Series
Called on each element of the object index to determine
the groups. If a dict or Series is passed, the Series or
dict VALUES will be used to determine the groups
Returns
-------
GroupBy object
"""
from pandas.core.groupby import groupby
return groupby(self, mapper)
def groupby(self, by=None, axis=0, level=None, as_index=True):
"""
Group series using mapper (dict or key function, apply given function
to group, return result as series) or by a series of columns
Parameters
----------
by : mapping function / list of functions, dict, Series, or tuple /
list of column names.
Called on each element of the object index to determine the groups.
If a dict or Series is passed, the Series or dict VALUES will be
used to determine the groups
axis : int, default 0
level : int, level name, or sequence of such, default None
If the axis is a MultiIndex (hierarchical), group by a particular
level or levels
as_index : boolean, default True
For aggregated output, return object with group labels as the
index. Only relevant for DataFrame input. as_index=False is
effectively "SQL-style" grouped output
Examples
--------
# DataFrame result
>>> data.groupby(func, axis=0).mean()
# DataFrame result
>>> data.groupby(['col1', 'col2'])['col3'].mean()
# DataFrame with hierarchical index
>>> data.groupby(['col1', 'col2']).mean()
Returns
-------
GroupBy object
"""
from pandas.core.groupby import groupby
return groupby(self, by, axis=axis, level=level, as_index=as_index)
def groupby(self, by=None, axis=0, level=None, as_index=True):
"""
Group series using mapper (dict or key function, apply given function
to group, return result as series) or by a series of columns
Parameters
----------
by : mapping function / list of functions, dict, Series, or tuple /
list of column names.
Called on each element of the object index to determine the groups.
If a dict or Series is passed, the Series or dict VALUES will be
used to determine the groups
axis : int, default 0
level : int, level name, or sequence of such, default None
If the axis is a MultiIndex (hierarchical), group by a particular
level or levels
as_index : boolean, default True
For aggregated output, return object with group labels as the
index. Only relevant for DataFrame input. as_index=False is
effectively "SQL-style" grouped output
Examples
--------
# DataFrame result
>>> data.groupby(func, axis=0).mean()
# DataFrame result
>>> data.groupby(['col1', 'col2'])['col3'].mean()
# DataFrame with hierarchical index
>>> data.groupby(['col1', 'col2']).mean()
Returns
-------
GroupBy object
"""
from pandas.core.groupby import groupby
return groupby(self, by, axis=axis, level=level, as_index=as_index)
def _gotitem(self, key, ndim, subset=None):
"""
sub-classes to define
return a sliced object
Parameters
----------
key : string / list of selections
ndim : 1,2
requested ndim of result
subset : object, default None
subset to act on
"""
self._set_binner()
grouper = self.grouper
if subset is None:
subset = self.obj
grouped = groupby(subset, by=None, grouper=grouper, axis=self.axis)
# try the key selection
try:
return grouped[key]
except KeyError:
return grouped
def _gotitem(self, key, ndim, subset=None):
"""
sub-classes to define
return a sliced object
Parameters
----------
key : string / list of selections
ndim : 1,2
requested ndim of result
subset : object, default None
subset to act on
"""
self._set_binner()
grouper = self.grouper
if subset is None:
subset = self.obj
grouped = groupby(subset, by=None, grouper=grouper, axis=self.axis)
# try the key selection
try:
return grouped[key]
except KeyError:
return grouped