-
Notifications
You must be signed in to change notification settings - Fork 3
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Signed-off-by: Anatoly Myachev <anatoly.myachev@intel.com>
- Loading branch information
Showing
17 changed files
with
490 additions
and
128 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,42 +1,84 @@ | ||
| # ruff: noqa | ||
| import sys | ||
| import argparse | ||
|
|
||
| sys.path.append("..") | ||
|
|
||
| import pandas as pd | ||
| import polars as pl | ||
|
|
||
| pd_series = pd.Series([1], name="a").__column_consortium_standard__() | ||
| pl_series = pl.Series("a", [1]).__column_consortium_standard__() | ||
| pd_df = pd.DataFrame({"a": [1]}).__dataframe_consortium_standard__() | ||
| pl_df = pl.DataFrame({"a": [1]}).__dataframe_consortium_standard__() | ||
| pd_scalar = pd_df.col("a").mean() | ||
| pl_scalar = pl_df.col("a").mean() | ||
| pd_namespace = pd_df.__dataframe_namespace__() | ||
| pl_namespace = pl_df.__dataframe_namespace__() | ||
|
|
||
| for name, object in [ | ||
| ("pandas-column.md", pd_series), | ||
| ("polars-column.md", pl_series), | ||
| ("pandas-dataframe.md", pd_df), | ||
| ("polars-dataframe.md", pl_df), | ||
| ("pandas-scalar.md", pd_scalar), | ||
| ("polars-scalar.md", pl_scalar), | ||
| ("pandas-namespace.md", pd_scalar), | ||
| ("polars-namespace.md", pl_scalar), | ||
| ]: | ||
| members = [ | ||
| i for i in object.__dir__() if not (i.startswith("_") and not i.startswith("__")) | ||
| ] | ||
|
|
||
| with open(name) as fd: | ||
| content = fd.read() | ||
|
|
||
| members_txt = "\n - ".join(sorted(members)) + "\n " | ||
|
|
||
| start = content.index("members:") | ||
| end = content.index("show_signature") | ||
| content = content[:start] + f"members:\n - {members_txt}" + content[end:] | ||
|
|
||
| with open(name, "w") as fd: | ||
| fd.write(content) | ||
|
|
||
| def get_polars_objects(): | ||
| import polars as pl | ||
|
|
||
| dataframe = pl.DataFrame({"a": [1]}).__dataframe_consortium_standard__() | ||
| column = pl.Series("a", [1]).__column_consortium_standard__() | ||
| scalar = dataframe.col("a").mean() | ||
| namespace = dataframe.__dataframe_namespace__() | ||
| return dataframe, column, scalar, namespace | ||
|
|
||
|
|
||
| def get_pandas_objects(): | ||
| import pandas as pd | ||
|
|
||
| dataframe = pd.DataFrame({"a": [1]}).__dataframe_consortium_standard__() | ||
| column = pd.Series([1], name="a").__column_consortium_standard__() | ||
| scalar = dataframe.col("a").mean() | ||
| namespace = dataframe.__dataframe_namespace__() | ||
| return dataframe, column, scalar, namespace | ||
|
|
||
|
|
||
| def get_modin_objects(): | ||
| import modin.pandas as pd | ||
|
|
||
| dataframe = pd.DataFrame({"a": [1]}).__dataframe_consortium_standard__() | ||
| column = pd.Series([1], name="a").__column_consortium_standard__() | ||
| scalar = dataframe.col("a").mean() | ||
| namespace = dataframe.__dataframe_namespace__() | ||
| return dataframe, column, scalar, namespace | ||
|
|
||
|
|
||
| def generate_members(library: str): | ||
| mapper = { | ||
| "pandas": get_pandas_objects, | ||
| "polars": get_polars_objects, | ||
| "modin": get_modin_objects, | ||
| } | ||
| dataframe, column, scalar, namespace = mapper[library]() | ||
|
|
||
| for name, object in [ | ||
| (f"{library}-dataframe.md", dataframe), | ||
| (f"{library}-column.md", column), | ||
| (f"{library}-scalar.md", scalar), | ||
| (f"{library}-namespace.md", namespace), | ||
| ]: | ||
| members = [ | ||
| i | ||
| for i in object.__dir__() | ||
| if not (i.startswith("_") and not i.startswith("__")) | ||
| ] | ||
|
|
||
| with open(name) as fd: | ||
| content = fd.read() | ||
|
|
||
| members_txt = "\n - ".join(sorted(members)) + "\n " | ||
|
|
||
| start = content.index("members:") | ||
| end = content.index("show_signature") | ||
| content = content[:start] + f"members:\n - {members_txt}" + content[end:] | ||
|
|
||
| with open(name, "w") as fd: | ||
| fd.write(content) | ||
|
|
||
|
|
||
| def main(): | ||
| parse = argparse.ArgumentParser() | ||
| parse.add_argument( | ||
| "--library", | ||
| type=str, | ||
| default="pandas", | ||
| help="Library for which members will be generated.", | ||
| ) | ||
| args = parse.parse_args() | ||
| sys.exit(generate_members(args.library)) | ||
|
|
||
|
|
||
| if __name__ == "__main__": | ||
| main() |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,105 @@ | ||
| # Pandas Column | ||
| ::: dataframe_api_compat.modin_standard.Column | ||
| handler: python | ||
| paths: [] | ||
| options: | ||
| members: | ||
| - __add__ | ||
| - __and__ | ||
| - __class__ | ||
| - __column_namespace__ | ||
| - __delattr__ | ||
| - __dict__ | ||
| - __dir__ | ||
| - __divmod__ | ||
| - __doc__ | ||
| - __eq__ | ||
| - __floordiv__ | ||
| - __format__ | ||
| - __ge__ | ||
| - __getattribute__ | ||
| - __gt__ | ||
| - __hash__ | ||
| - __init__ | ||
| - __init_subclass__ | ||
| - __invert__ | ||
| - __iter__ | ||
| - __le__ | ||
| - __lt__ | ||
| - __mod__ | ||
| - __module__ | ||
| - __mul__ | ||
| - __ne__ | ||
| - __new__ | ||
| - __or__ | ||
| - __pow__ | ||
| - __radd__ | ||
| - __rand__ | ||
| - __reduce__ | ||
| - __reduce_ex__ | ||
| - __repr__ | ||
| - __rfloordiv__ | ||
| - __rmod__ | ||
| - __rmul__ | ||
| - __ror__ | ||
| - __rpow__ | ||
| - __rsub__ | ||
| - __rtruediv__ | ||
| - __setattr__ | ||
| - __sizeof__ | ||
| - __str__ | ||
| - __sub__ | ||
| - __subclasshook__ | ||
| - __truediv__ | ||
| - __weakref__ | ||
| - all | ||
| - any | ||
| - cast | ||
| - column | ||
| - cumulative_max | ||
| - cumulative_min | ||
| - cumulative_prod | ||
| - cumulative_sum | ||
| - day | ||
| - dtype | ||
| - fill_nan | ||
| - fill_null | ||
| - filter | ||
| - floor | ||
| - get_value | ||
| - hour | ||
| - is_in | ||
| - is_nan | ||
| - is_null | ||
| - iso_weekday | ||
| - len | ||
| - max | ||
| - mean | ||
| - median | ||
| - microsecond | ||
| - min | ||
| - minute | ||
| - month | ||
| - n_unique | ||
| - name | ||
| - nanosecond | ||
| - parent_dataframe | ||
| - persist | ||
| - prod | ||
| - rename | ||
| - second | ||
| - shift | ||
| - slice_rows | ||
| - sort | ||
| - sorted_indices | ||
| - std | ||
| - sum | ||
| - take | ||
| - to_array | ||
| - unique_indices | ||
| - unix_timestamp | ||
| - var | ||
| - year | ||
| show_signature_annotations: true | ||
| show_bases: false | ||
| show_source: false |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,90 @@ | ||
| # Pandas DataFrame | ||
| ::: dataframe_api_compat.modin_standard.DataFrame | ||
| handler: python | ||
| paths: [] | ||
| options: | ||
| members: | ||
| - __add__ | ||
| - __and__ | ||
| - __class__ | ||
| - __dataframe_namespace__ | ||
| - __delattr__ | ||
| - __dict__ | ||
| - __dir__ | ||
| - __divmod__ | ||
| - __doc__ | ||
| - __eq__ | ||
| - __floordiv__ | ||
| - __format__ | ||
| - __ge__ | ||
| - __getattribute__ | ||
| - __gt__ | ||
| - __hash__ | ||
| - __init__ | ||
| - __init_subclass__ | ||
| - __invert__ | ||
| - __iter__ | ||
| - __le__ | ||
| - __lt__ | ||
| - __mod__ | ||
| - __module__ | ||
| - __mul__ | ||
| - __ne__ | ||
| - __new__ | ||
| - __or__ | ||
| - __pow__ | ||
| - __radd__ | ||
| - __rand__ | ||
| - __reduce__ | ||
| - __reduce_ex__ | ||
| - __repr__ | ||
| - __rfloordiv__ | ||
| - __rmod__ | ||
| - __rmul__ | ||
| - __ror__ | ||
| - __rpow__ | ||
| - __rsub__ | ||
| - __rtruediv__ | ||
| - __setattr__ | ||
| - __sizeof__ | ||
| - __str__ | ||
| - __sub__ | ||
| - __subclasshook__ | ||
| - __truediv__ | ||
| - __weakref__ | ||
| - all | ||
| - any | ||
| - assign | ||
| - cast | ||
| - col | ||
| - column_names | ||
| - dataframe | ||
| - drop | ||
| - drop_nulls | ||
| - fill_nan | ||
| - fill_null | ||
| - filter | ||
| - get_column_names | ||
| - group_by | ||
| - is_nan | ||
| - is_null | ||
| - iter_columns | ||
| - join | ||
| - max | ||
| - mean | ||
| - median | ||
| - min | ||
| - persist | ||
| - prod | ||
| - rename | ||
| - schema | ||
| - select | ||
| - shape | ||
| - slice_rows | ||
| - sort | ||
| - std | ||
| - sum | ||
| - take | ||
| - to_array | ||
| - var | ||
| show_signature_annotations: true |
Oops, something went wrong.