def _overlap(scdf, ocdf, **kwargs):
invert = kwargs["invert"]
return_indexes = kwargs.get("return_indexes", False)
if scdf.empty or ocdf.empty:
return None
how = kwargs["how"]
assert how in "containment first".split() + [False, None]
starts = scdf.Start.values
ends = scdf.End.values
indexes = scdf.index.values
it = NCLS(ocdf.Start.values, ocdf.End.values, ocdf.index.values)
if not how:
_indexes = it.all_overlaps_self(starts, ends, indexes)
elif how == "containment":
_indexes, _ = it.all_containments_both(starts, ends, indexes)
else:
_indexes = it.has_overlaps(starts, ends, indexes)
if invert:
_indexes = scdf.index.difference(_indexes)
if return_indexes:
return _indexes
return scdf.reindex(_indexes)
def _both_dfs(scdf, ocdf, how=False):
assert how in "containment first".split() + [False, None]
starts = scdf.Start.values
ends = scdf.End.values
indexes = scdf.index.values
ocdf = ocdf.reset_index(drop=True)
it = NCLS(ocdf.Start.values, ocdf.End.values, ocdf.index.values)
if not how:
_self_indexes, _other_indexes = it.all_overlaps_both(
starts, ends, indexes)
elif how == "containment":
_self_indexes, _other_indexes = it.all_containments_both(
starts, ends, indexes)
else:
_self_indexes, _other_indexes = it.first_overlap_both(
starts, ends, indexes)
_self_indexes = _self_indexes
_other_indexes = _other_indexes
scdf = scdf.reindex(_self_indexes)
ocdf = ocdf.reindex(_other_indexes)
return scdf, ocdf
def _intersection(scdf, ocdf, kwargs):
how = kwargs["how"]
if ocdf.empty or scdf.empty:
return None
assert how in "containment first last".split() + [False, None]
starts = scdf.Start.values
ends = scdf.End.values
indexes = scdf.index.values
in_dtype = ocdf.Start.dtype
oncls = NCLS(ocdf.Start.values, ocdf.End.values, ocdf.index.values)
if not how or how is None:
_self_indexes, _other_indexes = oncls.all_overlaps_both(
starts, ends, indexes)
elif how == "containment":
_self_indexes, _other_indexes = oncls.all_containments_both(
starts, ends, indexes)
elif how == "first":
_self_indexes, _other_indexes = oncls.first_overlap_both(
starts, ends, indexes)
elif how == "last":
_self_indexes, _other_indexes = oncls.last_overlap_both(
starts, ends, indexes)
_self_indexes = _self_indexes
_other_indexes = _other_indexes
scdf, ocdf = scdf.reindex(_self_indexes), ocdf.reindex(_other_indexes)
new_starts = pd.Series(
np.where(scdf.Start.values > ocdf.Start.values, scdf.Start,
ocdf.Start),
index=scdf.index,
dtype=in_dtype)
new_ends = pd.Series(
np.where(scdf.End.values < ocdf.End.values, scdf.End, ocdf.End),
index=scdf.index,
dtype=in_dtype)
pd.options.mode.chained_assignment = None # default='warn'
scdf.loc[:, "Start"] = new_starts
scdf.loc[:, "End"] = new_ends
pd.options.mode.chained_assignment = 'warn'
if not scdf.empty:
return scdf
else:
return None
def test_all_containments_both():
starts = np.array([1291845632, 3002335232], dtype=int)
ends = np.array([1292894207, 3002597375], dtype=int)
ids = np.array([0, 1], dtype=int)
ncls = NCLS(starts, ends, ids)
subs, covers = ncls.all_containments_both(starts, ends, ids)
print(ncls.intervals())
assert list(subs) == [0, 1] == list(covers)
def test_all_containments_both():
starts = np.array([5, 10], dtype=np.int64)
ends = np.array([6, 50], dtype=np.int64)
ids = np.array([0, 1], dtype=np.int64)
ncls = NCLS(starts, ends, ids)
subs, covers = ncls.all_containments_both(starts, ends, ids)
print(ncls.intervals())
assert list(subs) == [0, 1] == list(covers)
def _both_indexes(scdf, ocdf, how=False):
assert (how in "containment first last outer right left".split() +
[False, None]) or isinstance(how, int)
starts = scdf.Start.values
ends = scdf.End.values
indexes = scdf.index.values
it = NCLS(ocdf.Start.values, ocdf.End.values, ocdf.index.values)
if not how:
_self_indexes, _other_indexes = it.all_overlaps_both(
starts, ends, indexes)
elif how == "containment":
_self_indexes, _other_indexes = it.all_containments_both(
starts, ends, indexes)
elif how == "first":
_self_indexes, _other_indexes = it.first_overlap_both(
starts, ends, indexes)
elif how == "last":
_self_indexes, _other_indexes = it.last_overlap_both(
starts, ends, indexes)
six = scdf.index
oix = ocdf.index
elif how in ["outer", "left", "right"]:
_self_indexes, _other_indexes = it.all_overlaps_both(
starts, ends, indexes)
missing_in_s = scdf.index.difference(_self_indexes)
missing_in_o = ocdf.index.difference(_other_indexes)
filler_s = np.ones(len(missing_in_o), dtype=int) * -1
filler_o = np.ones(len(missing_in_s), dtype=int) * -1
if how == "outer":
_self_indexes = np.concatenate(
[_self_indexes, missing_in_s, filler_s])
_other_indexes = np.concatenate(
[_other_indexes, filler_o, missing_in_o])
elif how == "left":
_self_indexes = np.concatenate([_self_indexes, missing_in_s])
_other_indexes = np.concatenate([_other_indexes, filler_o])
elif how == "right":
_self_indexes = np.concatenate([_self_indexes, filler_s])
_other_indexes = np.concatenate([_other_indexes, missing_in_o])
return _self_indexes, _other_indexes
def _both_indexes(scdf, ocdf, how=False):
assert (how in "containment first".split() + [False, None]) or isinstance(
how, int)
starts = scdf.Start.values
ends = scdf.End.values
indexes = scdf.index.values
it = NCLS(ocdf.Start.values, ocdf.End.values, ocdf.index.values)
if not how:
_self_indexes, _other_indexes = it.all_overlaps_both(
starts, ends, indexes)
elif how == "containment":
_self_indexes, _other_indexes = it.all_containments_both(
starts, ends, indexes)
else:
_self_indexes, _other_indexes = it.first_overlap_both(
starts, ends, indexes)
return _self_indexes, _other_indexes
def _both_dfs(scdf, ocdf, how=False, **kwargs):
assert how in "containment first".split() + [False, None]
starts = scdf.Start.values
ends = scdf.End.values
indexes = scdf.index.values
it = NCLS(ocdf.Start.values, ocdf.End.values, ocdf.index.values)
if not how:
_self_indexes, _other_indexes = it.all_overlaps_both(
starts, ends, indexes)
elif how == "containment":
_self_indexes, _other_indexes = it.all_containments_both(
starts, ends, indexes)
else:
_self_indexes, _other_indexes = it.first_overlap_both(
starts, ends, indexes)
_self_indexes = _self_indexes
_other_indexes = _other_indexes
return scdf.loc[_self_indexes], ocdf.loc[_other_indexes]