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.

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

Enhancment/1886 Add json_normalize to pandas read formats #1892

Merged
merged 3 commits into from
Jan 15, 2025
Merged

Enhancment/1886 Add json_normalize to pandas read formats #1892

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
f78bc07
add json_normalize to pandas read formats
Jarek-Rolski Jan 6, 2025
a049763
add unit test
Jarek-Rolski Jan 14, 2025
55bcbfa
format code with black/fix unit test
Jarek-Rolski Jan 14, 2025
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: 4 additions & 0 deletions pandera/typing/formats.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,6 +42,9 @@ class Formats(Enum):
#: python pickle file format
pickle = "pickle"

#: python json_normalize
json_normalize = "json_normalize"


Format = Union[
Literal[Formats.csv],
Expand All @@ -50,4 +53,5 @@ class Formats(Enum):
Literal[Formats.feather],
Literal[Formats.parquet],
Literal[Formats.pickle],
Literal[Formats.json_normalize],
]
1 change: 1 addition & 0 deletions pandera/typing/pandas.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -122,6 +122,7 @@ def from_format(cls, obj: Any, config) -> pd.DataFrame:
Formats.feather: pd.read_feather,
Formats.parquet: pd.read_parquet,
Formats.pickle: pd.read_pickle,
Formats.json_normalize: pd.json_normalize,
}[Formats(config.from_format)]

return reader(obj, **(config.from_format_kwargs or {})) # type: ignore
Expand Down
6 changes: 6 additions & 0 deletions tests/core/test_from_to_format_conversions.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -64,6 +64,11 @@ class Config:
from_format = pd.read_pickle


class InSchemaJsonNormalize(InSchema):
class Config:
from_format = "json_normalize"


class OutSchema(InSchema):
float_col: pa.typing.Series[float]

Expand Down Expand Up @@ -194,6 +199,7 @@ def _needs_pyarrow(schema) -> bool:
[InSchemaParquet, lambda df, x: df.to_parquet(x), io.BytesIO],
[InSchemaPickle, lambda df, x: df.to_pickle(x), io.BytesIO],
[InSchemaPickleCallable, lambda df, x: df.to_pickle(x), io.BytesIO],
[InSchemaJsonNormalize, lambda df: df.to_dict(orient="records"), None],
],
)
def test_from_format(schema, to_fn, buf_cls):
Expand Down
Loading