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

Jump to bottom

docs(python): Docstrings for frame, lazyframe and time series #5398

Merged
merged 4 commits into from
Nov 2, 2022
Merged

docs(python): Docstrings for frame, lazyframe and time series #5398

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
8e93a12
expanded docstrings for functions var,std,fill_null,sum,mean,select,join
Nov 1, 2022
de24a1c
formatting
Nov 2, 2022
76cecd7
Merge branch 'master' into frame-docstrings
Nov 2, 2022
38ce8b6
fix flake blank lines
Nov 2, 2022
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
211 changes: 211 additions & 0 deletions py-polars/polars/internals/dataframe/frame.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3881,6 +3881,42 @@ def join(
│ 3 ┆ 8.0 ┆ c ┆ null │
└──────┴──────┴─────┴───────┘
>>> df.join(other_df, on="ham", how="left")
shape: (3, 4)
┌─────┬─────┬─────┬───────┐
│ foo ┆ bar ┆ ham ┆ apple │
│ --- ┆ --- ┆ --- ┆ --- │
│ i64 ┆ f64 ┆ str ┆ str │
╞═════╪═════╪═════╪═══════╡
│ 1 ┆ 6.0 ┆ a ┆ x │
├╌╌╌╌╌┼╌╌╌╌╌┼╌╌╌╌╌┼╌╌╌╌╌╌╌┤
│ 2 ┆ 7.0 ┆ b ┆ y │
├╌╌╌╌╌┼╌╌╌╌╌┼╌╌╌╌╌┼╌╌╌╌╌╌╌┤
│ 3 ┆ 8.0 ┆ c ┆ null │
└─────┴─────┴─────┴───────┘
>>> df.join(other_df, on="ham", how="semi")
shape: (2, 3)
┌─────┬─────┬─────┐
│ foo ┆ bar ┆ ham │
│ --- ┆ --- ┆ --- │
│ i64 ┆ f64 ┆ str │
╞═════╪═════╪═════╡
│ 1 ┆ 6.0 ┆ a │
├╌╌╌╌╌┼╌╌╌╌╌┼╌╌╌╌╌┤
│ 2 ┆ 7.0 ┆ b │
└─────┴─────┴─────┘
>>> df.join(other_df, on="ham", how="anti")
shape: (1, 3)
┌─────┬─────┬─────┐
│ foo ┆ bar ┆ ham │
│ --- ┆ --- ┆ --- │
│ i64 ┆ f64 ┆ str │
╞═════╪═════╪═════╡
│ 3 ┆ 8.0 ┆ c │
└─────┴─────┴─────┘
Notes
-----
For joining on columns with categorical data, see ``pl.StringCache()``.
Expand Down Expand Up @@ -4467,6 +4503,53 @@ def fill_null(
├╌╌╌╌╌┼╌╌╌╌╌╌┤
│ 4 ┆ 13.0 │
└─────┴──────┘
>>> df.fill_null(strategy="forward")
shape: (4, 2)
┌─────┬──────┐
│ a ┆ b │
│ --- ┆ --- │
│ i64 ┆ f64 │
╞═════╪══════╡
│ 1 ┆ 0.5 │
├╌╌╌╌╌┼╌╌╌╌╌╌┤
│ 2 ┆ 4.0 │
├╌╌╌╌╌┼╌╌╌╌╌╌┤
│ 2 ┆ 4.0 │
├╌╌╌╌╌┼╌╌╌╌╌╌┤
│ 4 ┆ 13.0 │
└─────┴──────┘
>>> df.fill_null(strategy="max")
shape: (4, 2)
┌─────┬──────┐
│ a ┆ b │
│ --- ┆ --- │
│ i64 ┆ f64 │
╞═════╪══════╡
│ 1 ┆ 0.5 │
├╌╌╌╌╌┼╌╌╌╌╌╌┤
│ 2 ┆ 4.0 │
├╌╌╌╌╌┼╌╌╌╌╌╌┤
│ 4 ┆ 13.0 │
├╌╌╌╌╌┼╌╌╌╌╌╌┤
│ 4 ┆ 13.0 │
└─────┴──────┘
>>> df.fill_null(strategy="zero")
shape: (4, 2)
┌─────┬──────┐
│ a ┆ b │
│ --- ┆ --- │
│ i64 ┆ f64 │
╞═════╪══════╡
│ 1 ┆ 0.5 │
├╌╌╌╌╌┼╌╌╌╌╌╌┤
│ 2 ┆ 4.0 │
├╌╌╌╌╌┼╌╌╌╌╌╌┤
│ 0 ┆ 0.0 │
├╌╌╌╌╌┼╌╌╌╌╌╌┤
│ 4 ┆ 13.0 │
└─────┴──────┘
"""
return self._from_pydf(
Expand Down Expand Up @@ -4983,6 +5066,33 @@ def partition_by(
╞═════╪═════╪═════╡
│ C ┆ 2 ┆ l │
└─────┴─────┴─────┘]
>>> df.partition_by(groups="foo", maintain_order=True, as_dict=True)
{'A': shape: (2, 3)
┌─────┬─────┬─────┐
│ foo ┆ N ┆ bar │
│ --- ┆ --- ┆ --- │
│ str ┆ i64 ┆ str │
╞═════╪═════╪═════╡
│ A ┆ 1 ┆ k │
├╌╌╌╌╌┼╌╌╌╌╌┼╌╌╌╌╌┤
│ A ┆ 2 ┆ l │
└─────┴─────┴─────┘, 'B': shape: (2, 3)
┌─────┬─────┬─────┐
│ foo ┆ N ┆ bar │
│ --- ┆ --- ┆ --- │
│ str ┆ i64 ┆ str │
╞═════╪═════╪═════╡
│ B ┆ 2 ┆ m │
├╌╌╌╌╌┼╌╌╌╌╌┼╌╌╌╌╌┤
│ B ┆ 4 ┆ m │
└─────┴─────┴─────┘, 'C': shape: (1, 3)
┌─────┬─────┬─────┐
│ foo ┆ N ┆ bar │
│ --- ┆ --- ┆ --- │
│ str ┆ i64 ┆ str │
╞═════╪═════╪═════╡
│ C ┆ 2 ┆ l │
└─────┴─────┴─────┘}
"""
if isinstance(groups, str):
Expand Down Expand Up @@ -5218,6 +5328,62 @@ def select(
│ 3 │
└─────┘
>>> df.select(["foo", "bar"])
shape: (3, 2)
┌─────┬─────┐
│ foo ┆ bar │
│ --- ┆ --- │
│ i64 ┆ i64 │
╞═════╪═════╡
│ 1 ┆ 6 │
├╌╌╌╌╌┼╌╌╌╌╌┤
│ 2 ┆ 7 │
├╌╌╌╌╌┼╌╌╌╌╌┤
│ 3 ┆ 8 │
└─────┴─────┘
>>> df.select(pl.col("foo") + 1)
shape: (3, 1)
┌─────┐
│ foo │
│ --- │
│ i64 │
╞═════╡
│ 2 │
├╌╌╌╌╌┤
│ 3 │
├╌╌╌╌╌┤
│ 4 │
└─────┘
>>> df.select([pl.col("foo") + 1, pl.col("bar") + 1])
shape: (3, 2)
┌─────┬─────┐
│ foo ┆ bar │
│ --- ┆ --- │
│ i64 ┆ i64 │
╞═════╪═════╡
│ 2 ┆ 7 │
├╌╌╌╌╌┼╌╌╌╌╌┤
│ 3 ┆ 8 │
├╌╌╌╌╌┼╌╌╌╌╌┤
│ 4 ┆ 9 │
└─────┴─────┘
>>> df.select(pl.when(pl.col("foo") > 2).then(10).otherwise(0))
shape: (3, 1)
┌─────────┐
│ literal │
│ --- │
│ i64 │
╞═════════╡
│ 0 │
├╌╌╌╌╌╌╌╌╌┤
│ 0 │
├╌╌╌╌╌╌╌╌╌┤
│ 10 │
└─────────┘
"""
return self._from_pydf(
self.lazy()
Expand Down Expand Up @@ -5338,6 +5504,8 @@ def n_chunks(self, strategy: str = "first") -> int | list[int]:
... )
>>> df.n_chunks()
1
>>> df.n_chunks(strategy="all")
[1, 1, 1]
"""
if strategy == "first":
Expand Down Expand Up @@ -5495,6 +5663,14 @@ def sum(
╞═════╪═════╪══════╡
│ 6 ┆ 21 ┆ null │
└─────┴─────┴──────┘
>>> df.sum(axis=1)
shape: (3,)
Series: 'foo' [str]
[
"16a"
"27b"
"38c"
]
"""
if axis == 0:
Expand Down Expand Up @@ -5564,6 +5740,23 @@ def mean(
│ 2.0 ┆ 7.0 ┆ null │
└─────┴─────┴──────┘
Note: a PanicException is raised with axis = 1 and a string column.
>>> df = pl.DataFrame(
... {
... "foo": [1, 2, 3],
... "bar": [6, 7, 8],
... }
... )
>>> df.mean(axis=1)
shape: (3,)
Series: 'foo' [f64]
[
3.5
4.5
5.5
]
Note: the mean of booleans evaluates to null.
>>> df = pl.DataFrame(
Expand Down Expand Up @@ -5628,6 +5821,15 @@ def std(self: DF, ddof: int = 1) -> DF:
╞═════╪═════╪══════╡
│ 1.0 ┆ 1.0 ┆ null │
└─────┴─────┴──────┘
>>> df.std(ddof=0)
shape: (1, 3)
┌──────────┬──────────┬──────┐
│ foo ┆ bar ┆ ham │
│ --- ┆ --- ┆ --- │
│ f64 ┆ f64 ┆ str │
╞══════════╪══════════╪══════╡
│ 0.816497 ┆ 0.816497 ┆ null │
└──────────┴──────────┴──────┘
"""
return self._from_pydf(self._df.std(ddof))
Expand Down Expand Up @@ -5659,6 +5861,15 @@ def var(self: DF, ddof: int = 1) -> DF:
╞═════╪═════╪══════╡
│ 1.0 ┆ 1.0 ┆ null │
└─────┴─────┴──────┘
>>> df.var(ddof=0)
shape: (1, 3)
┌──────────┬──────────┬──────┐
│ foo ┆ bar ┆ ham │
│ --- ┆ --- ┆ --- │
│ f64 ┆ f64 ┆ str │
╞══════════╪══════════╪══════╡
│ 0.666667 ┆ 0.666667 ┆ null │
└──────────┴──────────┴──────┘
"""
return self._from_pydf(self._df.var(ddof))
Expand Down
57 changes: 57 additions & 0 deletions py-polars/polars/internals/expr/datetime.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,6 +27,8 @@ def truncate(
"""
Divide the date/datetime range into buckets.
Each date/datetime is mapped to the start of its bucket.
Parameters
----------
every
Expand Down Expand Up @@ -111,6 +113,31 @@ def truncate(
... )
True
>>> start = datetime(2001, 1, 1)
>>> stop = datetime(2001, 1, 1, 1)
>>> df = pl.date_range(start, stop, "10m", name="dates").to_frame()
>>> df.select(["dates", pl.col("dates").dt.truncate("30m").alias("truncate")])
shape: (7, 2)
┌─────────────────────┬─────────────────────┐
│ dates ┆ truncate │
│ --- ┆ --- │
│ datetime[μs] ┆ datetime[μs] │
╞═════════════════════╪═════════════════════╡
│ 2001-01-01 00:00:00 ┆ 2001-01-01 00:00:00 │
├╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┤
│ 2001-01-01 00:10:00 ┆ 2001-01-01 00:00:00 │
├╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┤
│ 2001-01-01 00:20:00 ┆ 2001-01-01 00:00:00 │
├╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┤
│ 2001-01-01 00:30:00 ┆ 2001-01-01 00:30:00 │
├╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┤
│ 2001-01-01 00:40:00 ┆ 2001-01-01 00:30:00 │
├╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┤
│ 2001-01-01 00:50:00 ┆ 2001-01-01 00:30:00 │
├╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┤
│ 2001-01-01 01:00:00 ┆ 2001-01-01 01:00:00 │
└─────────────────────┴─────────────────────┘
"""
if offset is None:
offset = "0ns"
Expand All @@ -128,6 +155,11 @@ def round(
"""
Divide the date/datetime range into buckets.
Each date/datetime in the first half of the interval
is mapped to the start of its bucket.
Each date/datetime in the seconod half of the interval
is mapped to the end of its bucket.
Parameters
----------
every
Expand Down Expand Up @@ -217,6 +249,31 @@ def round(
... )
True
>>> start = datetime(2001, 1, 1)
>>> stop = datetime(2001, 1, 1, 1)
>>> df = pl.date_range(start, stop, "10m", name="dates").to_frame()
>>> df.select(["dates", pl.col("dates").dt.round("30m").alias("round")])
shape: (7, 2)
┌─────────────────────┬─────────────────────┐
│ dates ┆ round │
│ --- ┆ --- │
│ datetime[μs] ┆ datetime[μs] │
╞═════════════════════╪═════════════════════╡
│ 2001-01-01 00:00:00 ┆ 2001-01-01 00:00:00 │
├╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┤
│ 2001-01-01 00:10:00 ┆ 2001-01-01 00:00:00 │
├╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┤
│ 2001-01-01 00:20:00 ┆ 2001-01-01 00:30:00 │
├╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┤
│ 2001-01-01 00:30:00 ┆ 2001-01-01 00:30:00 │
├╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┤
│ 2001-01-01 00:40:00 ┆ 2001-01-01 00:30:00 │
├╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┤
│ 2001-01-01 00:50:00 ┆ 2001-01-01 01:00:00 │
├╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┤
│ 2001-01-01 01:00:00 ┆ 2001-01-01 01:00:00 │
└─────────────────────┴─────────────────────┘
"""
if offset is None:
offset = "0ns"
Expand Down
Loading