Skip to content
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.

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

fix: ak.unzip visits all contents #2373

Merged
merged 4 commits into from
Apr 7, 2023
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
7 changes: 2 additions & 5 deletions src/awkward/operations/ak_unzip.py
Original file line number Diff line number Diff line change
Expand Up @@ -48,18 +48,15 @@ def _impl(array, highlevel, behavior):

def check_for_union(layout, **kwargs):
if isinstance(layout, (ak.contents.RecordArray, ak.Record)):
pass # don't descend into nested records
return layout # don't descend into nested records

elif isinstance(layout, ak.contents.UnionArray):
elif layout.is_union:
for content in layout.contents:
if set(ak.operations.fields(content)) != set(fields):
raise ak._errors.wrap_error(
ValueError("union of different sets of fields, cannot ak.unzip")
)

elif hasattr(layout, "content"):
check_for_union(layout.content)

ak._do.recursively_apply(layout, check_for_union, behavior, return_array=False)

if len(fields) == 0:
Expand Down
124 changes: 124 additions & 0 deletions tests/test_2373_unzip_touching.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,124 @@
import awkward as ak


def test():
form = ak.forms.from_dict(
{
"class": "RecordArray",
"fields": ["muon", "jet"],
"contents": [
{
"class": "ListOffsetArray",
"offsets": "i64",
"content": {
"class": "RecordArray",
"fields": ["pt", "eta", "phi", "crossref"],
"contents": [
{
"class": "NumpyArray",
"primitive": "int64",
"inner_shape": [],
"parameters": {},
"form_key": "muon_pt!",
},
{
"class": "NumpyArray",
"primitive": "int64",
"inner_shape": [],
"parameters": {},
"form_key": "muon_eta!",
},
{
"class": "NumpyArray",
"primitive": "int64",
"inner_shape": [],
"parameters": {},
"form_key": "muon_phi!",
},
{
"class": "ListOffsetArray",
"offsets": "i64",
"content": {
"class": "NumpyArray",
"primitive": "int64",
"inner_shape": [],
"parameters": {},
"form_key": "muon_crossref_content!",
},
"parameters": {},
"form_key": "muon_crossref_index!",
},
],
"parameters": {},
"form_key": "muon_record!",
},
"parameters": {},
"form_key": "muon_list!",
},
{
"class": "ListOffsetArray",
"offsets": "i64",
"content": {
"class": "RecordArray",
"fields": ["pt", "eta", "phi", "crossref", "thing1"],
"contents": [
{
"class": "NumpyArray",
"primitive": "int64",
"inner_shape": [],
"parameters": {},
"form_key": "jet_pt!",
},
{
"class": "NumpyArray",
"primitive": "int64",
"inner_shape": [],
"parameters": {},
"form_key": "jet_eta!",
},
{
"class": "NumpyArray",
"primitive": "int64",
"inner_shape": [],
"parameters": {},
"form_key": "jet_phi!",
},
{
"class": "ListOffsetArray",
"offsets": "i64",
"content": {
"class": "NumpyArray",
"primitive": "int64",
"inner_shape": [],
"parameters": {},
"form_key": "jet_crossref_content!",
},
"parameters": {},
"form_key": "jet_crossref_index!",
},
{
"class": "NumpyArray",
"primitive": "int64",
"inner_shape": [],
"parameters": {},
"form_key": "jet_thing1!",
},
],
"parameters": {},
"form_key": "jet_record!",
},
"parameters": {},
"form_key": "jet_list!",
},
],
"parameters": {},
"form_key": "outer!",
}
)

ttlayout, report = ak._nplikes.typetracer.typetracer_with_report(form)

ttarray = ak.Array(ttlayout)
pairs = ak.cartesian([ttarray.muon, ttarray.jet], axis=1, nested=True)
a, b = ak.unzip(pairs)
assert report.data_touched == ["muon_list!", "jet_list!"]