Skip to content

fix: raise error when calling to csv or to dataframe on non homegenou… #1467

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
samsja merged 1 commit into from
Apr 27, 2023
Merged

fix: raise error when calling to csv or to dataframe on non homegenou… #1467

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
13 changes: 13 additions & 0 deletions docarray/array/doc_list/io.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -432,6 +432,12 @@ def to_csv(
`'unix'` (for csv file generated on UNIX systems).

"""
if self.doc_type == AnyDoc:
raise TypeError(
'DocList must be homogeneous to be converted to a csv.'
'There is no document schema defined. '
'Please specify the DocList\'s Document type using `DocList[MyDoc]`.'
)
fields = self.doc_type._get_access_paths()

with open(file_path, 'w') as csv_file:
Expand Down Expand Up @@ -532,6 +538,13 @@ def to_dataframe(self) -> 'pd.DataFrame':
else:
pd = import_library('pandas', raise_error=True)

if self.doc_type == AnyDoc:
raise TypeError(
'DocList must be homogeneous to be converted to a DataFrame.'
'There is no document schema defined. '
'Please specify the DocList\'s Document type using `DocList[MyDoc]`.'
)

fields = self.doc_type._get_access_paths()
df = pd.DataFrame(columns=fields)

Expand Down
10 changes: 10 additions & 0 deletions tests/units/array/test_array_from_to_csv.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -110,3 +110,13 @@ class Book(BaseDoc):
books = DocList[Book].from_csv(file_path=remote_url)

assert len(books) == 3


def test_doc_list_error(tmpdir):
class Book(BaseDoc):
title: str

docs = DocList([Book(title='hello'), Book(title='world')])
tmp_file = str(tmpdir / 'tmp.csv')
with pytest.raises(TypeError):
docs.to_csv(tmp_file)
9 changes: 9 additions & 0 deletions tests/units/array/test_array_from_to_pandas.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -85,3 +85,12 @@ def test_from_pandas_with_wrong_schema_raise_exception(nested_doc):
columns=['title', 'count'], data=[['title 0', 0], ['title 1', 1]]
)
DocList[nested_doc.__class__].from_dataframe(df=df)


def test_doc_list_error():
class Book(BaseDoc):
title: str

docs = DocList([Book(title='hello'), Book(title='world')])
with pytest.raises(TypeError):
docs.to_dataframe()