Skip to content

API experiment: lambda grouper based on sliding window #3101

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 1 commit into from
Closed

API experiment: lambda grouper based on sliding window #3101

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
4 changes: 2 additions & 2 deletions pandas/core/generic.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -106,7 +106,7 @@ def get(self, key, default=None):
return default

def groupby(self, by=None, axis=0, level=None, as_index=True, sort=True,
group_keys=True):
group_keys=True,offset=0,fill=None):
"""
Group series using mapper (dict or key function, apply given function
to group, return result as series) or by a series of columns
Expand Down Expand Up @@ -148,7 +148,7 @@ def groupby(self, by=None, axis=0, level=None, as_index=True, sort=True,
"""
from pandas.core.groupby import groupby
return groupby(self, by, axis=axis, level=level, as_index=as_index,
sort=sort, group_keys=group_keys)
sort=sort, group_keys=group_keys,offset=offset,fill=fill)

def asfreq(self, freq, method=None, how=None, normalize=False):
"""
Expand Down
63 changes: 57 additions & 6 deletions pandas/core/groupby.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -168,7 +168,8 @@ class GroupBy(object):

def __init__(self, obj, keys=None, axis=0, level=None,
grouper=None, exclusions=None, selection=None, as_index=True,
sort=True, group_keys=True):
sort=True, group_keys=True,
win=None,offset=None,fill=None):
self._selection = selection

if isinstance(obj, NDFrame):
Expand All @@ -191,7 +192,7 @@ def __init__(self, obj, keys=None, axis=0, level=None,

if grouper is None:
grouper, exclusions = _get_grouper(obj, keys, axis=axis,
level=level, sort=sort)
level=level, sort=sort,offset=offset,fill=fill)

self.grouper = grouper
self.exclusions = set(exclusions) if exclusions else set()
Expand Down Expand Up @@ -1130,7 +1131,7 @@ class Grouping(object):
* groups : dict of {group -> label_list}
"""
def __init__(self, index, grouper=None, name=None, level=None,
sort=True):
sort=True,offset=None,fill=None):

self.name = name
self.level = level
Expand Down Expand Up @@ -1204,7 +1205,55 @@ def __init__(self, index, grouper=None, name=None, level=None,

# no level passed
if not isinstance(self.grouper, np.ndarray):
self.grouper = self.index.map(self.grouper)

# TODO: handle tuple of functions
if callable(self.grouper):
nargs =self.grouper.func_code.co_argcount
if nargs > 1: # else, just use index.map
if offset is None:
offset =0
elif not isinstance(offset,int):
raise ValueError("illegal offset, should pos/neg offset")

def windowed(v,win,offset,fill=None):
if not ( abs(offset) < win):
raise ValueError("! offset < win")
offset = offset % win
lpad = offset
rpad = win-offset-1
if not ( lpad < win):
raise ValueError("! lpad < win")

res = [fill]*lpad +v[:win-lpad].tolist()
i = win-lpad
while i < len(v):
yield res
res = res[1:] + [v[i]]
i+=1

for j in range(rpad):
yield res
res = res[1:] + [fill]
i+=1
yield res
def wrap(f,acc_seed=0):
def inner(*args):
f.__globals__['_'] = holder[0]
holder[0] = f(*args)
return holder[0]

holder =[acc_seed]
return inner

tups = windowed(self.index,nargs,offset,fill)
wrapped = wrap(self.grouper)
self.grouper = map(lambda x: wrapped(*x), tups)

else:
self.grouper = self.index.map(self.grouper)
else:
self.grouper = self.index.map(self.grouper)

if not (hasattr(self.grouper,"__len__") and \
len(self.grouper) == len(self.index)):
errmsg = "Grouper result violates len(labels) == len(data)\n"
Expand Down Expand Up @@ -1260,7 +1309,8 @@ def groups(self):
return self._groups


def _get_grouper(obj, key=None, axis=0, level=None, sort=True):
def _get_grouper(obj, key=None, axis=0, level=None, sort=True,
offset=None,fill=None):
group_axis = obj._get_axis(axis)

if level is not None:
Expand Down Expand Up @@ -1327,7 +1377,8 @@ def _get_grouper(obj, key=None, axis=0, level=None, sort=True):
errmsg = "Categorical grouper must have len(grouper) == len(data)"
raise AssertionError(errmsg)

ping = Grouping(group_axis, gpr, name=name, level=level, sort=sort)
ping = Grouping(group_axis, gpr, name=name, level=level, sort=sort,offset=offset,fill=fill)

groupings.append(ping)

if len(groupings) == 0:
Expand Down