Skip to content

docs: update struct examples. #953

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
Genesis929 merged 3 commits into from
Sep 4, 2024
Merged

docs: update struct examples. #953

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
4a8e7f3
docs:update struct examples.
Genesis929 Aug 29, 2024
c106955
Merge branch 'main' into struct-doc-huanc
Genesis929 Sep 4, 2024
d23a702
format fix
Genesis929 Sep 4, 2024
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
44 changes: 22 additions & 22 deletions third_party/bigframes_vendored/pandas/core/arrays/arrow/accessors.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,12 +22,12 @@ def field(self, name_or_index: str | int):
>>> bpd.options.display.progress_bar = None
>>> s = bpd.Series(
... [
... {"version": 1, "project": "pandas"},
... {"version": 2, "project": "pandas"},
... {"version": 1, "project": "numpy"},
... {"project": "pandas", "version": 1},
... {"project": "pandas", "version": 2},
... {"project": "numpy", "version": 1},
... ],
... dtype=bpd.ArrowDtype(pa.struct(
... [("version", pa.int64()), ("project", pa.string())]
... [("project", pa.string()), ("version", pa.int64())]
... ))
... )

Expand All @@ -41,7 +41,7 @@ def field(self, name_or_index: str | int):

Extract by field index.

>>> s.struct.field(0)
>>> s.struct.field(1)
0 1
1 2
2 1
Expand All @@ -68,22 +68,22 @@ def explode(self):
>>> bpd.options.display.progress_bar = None
>>> s = bpd.Series(
... [
... {"version": 1, "project": "pandas"},
... {"version": 2, "project": "pandas"},
... {"version": 1, "project": "numpy"},
... {"project": "pandas", "version": 1},
... {"project": "pandas", "version": 2},
... {"project": "numpy", "version": 1},
... ],
... dtype=bpd.ArrowDtype(pa.struct(
... [("version", pa.int64()), ("project", pa.string())]
... [("project", pa.string()), ("version", pa.int64())]
... ))
... )

Extract all child fields.

>>> s.struct.explode()
version project
0 1 pandas
1 2 pandas
2 1 numpy
project version
0 pandas 1
1 pandas 2
2 numpy 1
<BLANKLINE>
[3 rows x 2 columns]

Expand Down Expand Up @@ -113,8 +113,8 @@ def dtypes(self):
... ))
... )
>>> s.struct.dtypes()
version Int64
project string[pyarrow]
version Int64
dtype: object

Returns:
Expand All @@ -140,21 +140,21 @@ def explode(self, column, *, separator: str = "."):
>>> countries = bpd.Series(["cn", "es", "us"])
>>> files = bpd.Series(
... [
... {"version": 1, "project": "pandas"},
... {"version": 2, "project": "pandas"},
... {"version": 1, "project": "numpy"},
... {"project": "pandas", "version": 1},
... {"project": "pandas", "version": 2},
... {"project": "numpy", "version": 1},
... ],
... dtype=bpd.ArrowDtype(pa.struct(
... [("version", pa.int64()), ("project", pa.string())]
... [("project", pa.string()), ("version", pa.int64())]
... ))
... )
>>> downloads = bpd.Series([100, 200, 300])
>>> df = bpd.DataFrame({"country": countries, "file": files, "download_count": downloads})
>>> df.struct.explode("file")
country file.version file.project download_count
0 cn 1 pandas 100
1 es 2 pandas 200
2 us 1 numpy 300
country file.project file.version download_count
0 cn pandas 1 100
1 es pandas 2 200
2 us numpy 1 300
<BLANKLINE>
[3 rows x 4 columns]

Expand Down