across

In [1]:

%run nb_helpers.py

from datar.data import iris
from datar.all import *

nb_header(across, if_any, if_all, c_across)

%run nb_helpers.py from datar.data import iris from datar.all import * nb_header(across, if_any, if_all, c_across)

Try this notebook on binder.

★ across

¶

Apply the same transformation to multiple columns

The original API:
https://dplyr.tidyverse.org/reference/across.html

Examples:
    #
    >>> iris >> mutate(across(c(f.Sepal_Length, f.Sepal_Width), round))
        Sepal_Length  Sepal_Width  Petal_Length  Petal_Width    Species
           <float64>    <float64>     <float64>    <float64>   <object>
    0            5.0          4.0           1.4          0.2     setosa
    1            5.0          3.0           1.4          0.2     setosa
    ..           ...          ...           ...          ...        ...

    >>> iris >> group_by(f.Species) >> summarise(
    >>>     across(starts_with("Sepal"), mean)
    >>> )
          Species  Sepal_Length  Sepal_Width
         <object>     <float64>    <float64>
    0      setosa         5.006        3.428
    1  versicolor         5.936        2.770
    2   virginica         6.588        2.974

Args:
    _data: The dataframe.
    *args: If given, the first 2 elements should be columns and functions
        apply to each of the selected columns. The rest of them will be
        the arguments for the functions.
    _names: A glue specification that describes how to name
        the output columns. This can use `{_col}` to stand for the
        selected column name, and `{_fn}` to stand for the name of
        the function being applied.
        The default (None) is equivalent to `{_col}` for the
        single function case and `{_col}_{_fn}` for the case where
        a list is used for _fns. In such a case, `{_fn}` is 0-based.
        To use 1-based index, use `{_fn1}`
    _fn_context: Defines the context to evaluate the arguments for functions
        if they are plain functions.
        Note that registered functions will use its own context
    **kwargs: Keyword arguments for the functions

Returns:
    A dataframe with one column for each column and each function.

★ if_any

¶

Apply the same predicate function to a selection of columns and combine¶

the results True if any element is True.

See Also:
  across()

★ if_all

¶

Apply the same predicate function to a selection of columns and combine¶

the results True if all elements are True.

See Also:
  across()

★ c_across

¶

Apply the same transformation to multiple columns rowwisely¶

Args:¶

  _data: The dataframe
  _cols: The columns

Returns:¶

  A rowwise tibble

In [2]:

# round not changing dtypes (Series.round)
iris >> mutate(across(c(f.Sepal_Length, f.Sepal_Width), round))

# round not changing dtypes (Series.round) iris >> mutate(across(c(f.Sepal_Length, f.Sepal_Width), round))

Out[2]:

	Sepal_Length	Sepal_Width	Petal_Length	Petal_Width	Species
	<float64>	<float64>	<float64>	<float64>	<object>
0	5.0	4.0	1.4	0.2	setosa
1	5.0	3.0	1.4	0.2	setosa
2	5.0	3.0	1.3	0.2	setosa
3	5.0	3.0	1.5	0.2	setosa
...	...	...	...	...	...
4	5.0	4.0	1.4	0.2	setosa
145	7.0	3.0	5.2	2.3	virginica
146	6.0	2.0	5.0	1.9	virginica
147	6.0	3.0	5.2	2.0	virginica
148	6.0	3.0	5.4	2.3	virginica
149	6.0	3.0	5.1	1.8	virginica

150 rows × 5 columns

In [3]:

iris >> mutate(across(c(0, 1), round))

iris >> mutate(across(c(0, 1), round))

Out[3]:

	Sepal_Length	Sepal_Width	Petal_Length	Petal_Width	Species
	<float64>	<float64>	<float64>	<float64>	<object>
0	5.0	4.0	1.4	0.2	setosa
1	5.0	3.0	1.4	0.2	setosa
2	5.0	3.0	1.3	0.2	setosa
3	5.0	3.0	1.5	0.2	setosa
...	...	...	...	...	...
4	5.0	4.0	1.4	0.2	setosa
145	7.0	3.0	5.2	2.3	virginica
146	6.0	2.0	5.0	1.9	virginica
147	6.0	3.0	5.2	2.0	virginica
148	6.0	3.0	5.4	2.3	virginica
149	6.0	3.0	5.1	1.8	virginica

150 rows × 5 columns

In [4]:

# use slice with column names
iris >> mutate(across(c[:f.Sepal_Width], round))

# use slice with column names iris >> mutate(across(c[:f.Sepal_Width], round))

Out[4]:

	Sepal_Length	Sepal_Width	Petal_Length	Petal_Width	Species
	<float64>	<float64>	<float64>	<float64>	<object>
0	5.0	3.5	1.4	0.2	setosa
1	5.0	3.0	1.4	0.2	setosa
2	5.0	3.2	1.3	0.2	setosa
3	5.0	3.1	1.5	0.2	setosa
...	...	...	...	...	...
4	5.0	3.6	1.4	0.2	setosa
145	7.0	3.0	5.2	2.3	virginica
146	6.0	2.5	5.0	1.9	virginica
147	6.0	3.0	5.2	2.0	virginica
148	6.0	3.4	5.4	2.3	virginica
149	6.0	3.0	5.1	1.8	virginica

150 rows × 5 columns

In [5]:

# to include stop of slice
iris >> mutate(across(c[:f.Sepal_Width:1], round))

# to include stop of slice iris >> mutate(across(c[:f.Sepal_Width:1], round))

Out[5]:

	Sepal_Length	Sepal_Width	Petal_Length	Petal_Width	Species
	<float64>	<float64>	<float64>	<float64>	<object>
0	5.0	4.0	1.4	0.2	setosa
1	5.0	3.0	1.4	0.2	setosa
2	5.0	3.0	1.3	0.2	setosa
3	5.0	3.0	1.5	0.2	setosa
...	...	...	...	...	...
4	5.0	4.0	1.4	0.2	setosa
145	7.0	3.0	5.2	2.3	virginica
146	6.0	2.0	5.0	1.9	virginica
147	6.0	3.0	5.2	2.0	virginica
148	6.0	3.0	5.4	2.3	virginica
149	6.0	3.0	5.1	1.8	virginica

150 rows × 5 columns

In [6]:

iris >> mutate(across(where(is_double) & ~c(f.Petal_Length, f.Petal_Width), round))

iris >> mutate(across(where(is_double) & ~c(f.Petal_Length, f.Petal_Width), round))

Out[6]:

	Sepal_Length	Sepal_Width	Petal_Length	Petal_Width	Species
	<float64>	<float64>	<float64>	<float64>	<object>
0	5.0	4.0	1.4	0.2	setosa
1	5.0	3.0	1.4	0.2	setosa
2	5.0	3.0	1.3	0.2	setosa
3	5.0	3.0	1.5	0.2	setosa
...	...	...	...	...	...
4	5.0	4.0	1.4	0.2	setosa
145	7.0	3.0	5.2	2.3	virginica
146	6.0	2.0	5.0	1.9	virginica
147	6.0	3.0	5.2	2.0	virginica
148	6.0	3.0	5.4	2.3	virginica
149	6.0	3.0	5.1	1.8	virginica

150 rows × 5 columns

In [7]:

iris = iris >> mutate(Species=as_factor(f.Species))
iris

iris = iris >> mutate(Species=as_factor(f.Species)) iris

Out[7]:

	Sepal_Length	Sepal_Width	Petal_Length	Petal_Width	Species
	<float64>	<float64>	<float64>	<float64>	<category>
0	5.1	3.5	1.4	0.2	setosa
1	4.9	3.0	1.4	0.2	setosa
2	4.7	3.2	1.3	0.2	setosa
3	4.6	3.1	1.5	0.2	setosa
...	...	...	...	...	...
4	5.0	3.6	1.4	0.2	setosa
145	6.7	3.0	5.2	2.3	virginica
146	6.3	2.5	5.0	1.9	virginica
147	6.5	3.0	5.2	2.0	virginica
148	6.2	3.4	5.4	2.3	virginica
149	5.9	3.0	5.1	1.8	virginica

150 rows × 5 columns

In [8]:

iris = iris >> mutate(across(where(is_factor), as_character))
iris

iris = iris >> mutate(across(where(is_factor), as_character)) iris

Out[8]:

	Sepal_Length	Sepal_Width	Petal_Length	Petal_Width	Species
	<float64>	<float64>	<float64>	<float64>	<object>
0	5.1	3.5	1.4	0.2	setosa
1	4.9	3.0	1.4	0.2	setosa
2	4.7	3.2	1.3	0.2	setosa
3	4.6	3.1	1.5	0.2	setosa
...	...	...	...	...	...
4	5.0	3.6	1.4	0.2	setosa
145	6.7	3.0	5.2	2.3	virginica
146	6.3	2.5	5.0	1.9	virginica
147	6.5	3.0	5.2	2.0	virginica
148	6.2	3.4	5.4	2.3	virginica
149	5.9	3.0	5.1	1.8	virginica

150 rows × 5 columns

In [10]:

iris >> group_by(f.Species) >> summarise(
    across(starts_with("Sepal"), mean)
)

iris >> group_by(f.Species) >> summarise( across(starts_with("Sepal"), mean) )

Out[10]:

	Species	Sepal_Length	Sepal_Width
	<object>	<float64>	<float64>
0	setosa	5.006	3.428
1	versicolor	5.936	2.770
2	virginica	6.588	2.974

In [11]:

iris >> group_by(f.Species) >> summarise(
    across(starts_with("Sepal"), dict(mean=mean, sd=sd))
)

iris >> group_by(f.Species) >> summarise( across(starts_with("Sepal"), dict(mean=mean, sd=sd)) )

Out[11]:

	Species	Sepal_Length_mean	Sepal_Length_sd	Sepal_Width_mean	Sepal_Width_sd
	<object>	<float64>	<float64>	<float64>	<float64>
0	setosa	5.006	0.352490	3.428	0.379064
1	versicolor	5.936	0.516171	2.770	0.313798
2	virginica	6.588	0.635880	2.974	0.322497

In [12]:

iris >> group_by(f.Species) >> summarise(
    across(starts_with("Sepal"), mean, _names = "mean_{_col}")
)

iris >> group_by(f.Species) >> summarise( across(starts_with("Sepal"), mean, _names = "mean_{_col}") )

Out[12]:

	Species	mean_Sepal_Length	mean_Sepal_Width
	<object>	<float64>	<float64>
0	setosa	5.006	3.428
1	versicolor	5.936	2.770
2	virginica	6.588	2.974

In [13]:

iris >> group_by(f.Species) >> summarise(
    across(starts_with("Sepal"), dict(mean=mean, sd=sd), _names = "{_col}.{_fn}")
)

iris >> group_by(f.Species) >> summarise( across(starts_with("Sepal"), dict(mean=mean, sd=sd), _names = "{_col}.{_fn}") )

Out[13]:

	Species	Sepal_Length.mean	Sepal_Length.sd	Sepal_Width.mean	Sepal_Width.sd
	<object>	<float64>	<float64>	<float64>	<float64>
0	setosa	5.006	0.352490	3.428	0.379064
1	versicolor	5.936	0.516171	2.770	0.313798
2	virginica	6.588	0.635880	2.974	0.322497

In [14]:

iris >> group_by(f.Species) >> summarise(
    across(starts_with("Sepal"), [mean, sd], _names = "{_col}.fn{_fn}")
)

iris >> group_by(f.Species) >> summarise( across(starts_with("Sepal"), [mean, sd], _names = "{_col}.fn{_fn}") )

Out[14]:

	Species	Sepal_Length.fn0	Sepal_Length.fn1	Sepal_Width.fn0	Sepal_Width.fn1
	<object>	<float64>	<float64>	<float64>	<float64>
0	setosa	5.006	0.352490	3.428	0.379064
1	versicolor	5.936	0.516171	2.770	0.313798
2	virginica	6.588	0.635880	2.974	0.322497

In [15]:

iris >> group_by(f.Species) >> summarise(
    across(
        starts_with("Sepal"), 
        [mean, sd], 
        _names="{_col}.fn{_fn}", 
    )
)
# or use _fn0

# iris >> group_by(f.Species) >> summarise(
#     across(
#         starts_with("Sepal"), 
#         [mean, sd], 
#         _names="{_col}.fn{_fn1}", # _fn1 for 1-based
#     )
# )

iris >> group_by(f.Species) >> summarise( across( starts_with("Sepal"), [mean, sd], _names="{_col}.fn{_fn}", ) ) # or use _fn0 # iris >> group_by(f.Species) >> summarise( # across( # starts_with("Sepal"), # [mean, sd], # _names="{_col}.fn{_fn1}", # _fn1 for 1-based # ) # )

Out[15]:

	Species	Sepal_Length.fn0	Sepal_Length.fn1	Sepal_Width.fn0	Sepal_Width.fn1
	<object>	<float64>	<float64>	<float64>	<float64>
0	setosa	5.006	0.352490	3.428	0.379064
1	versicolor	5.936	0.516171	2.770	0.313798
2	virginica	6.588	0.635880	2.974	0.322497

In [16]:

iris >> group_by(f.Species) >> summarise(
    across(starts_with("Sepal"), [mean, sd], _names = "{_col}.fn{_fn1}")
)

iris >> group_by(f.Species) >> summarise( across(starts_with("Sepal"), [mean, sd], _names = "{_col}.fn{_fn1}") )

Out[16]:

	Species	Sepal_Length.fn1	Sepal_Length.fn2	Sepal_Width.fn1	Sepal_Width.fn2
	<object>	<float64>	<float64>	<float64>	<float64>
0	setosa	5.006	0.352490	3.428	0.379064
1	versicolor	5.936	0.516171	2.770	0.313798
2	virginica	6.588	0.635880	2.974	0.322497

In [17]:

iris >> filter(if_any(ends_with("Width"), lambda x: x > 4))

iris >> filter(if_any(ends_with("Width"), lambda x: x > 4))

Out[17]:

	Sepal_Length	Sepal_Width	Petal_Length	Petal_Width	Species
	<float64>	<float64>	<float64>	<float64>	<object>
15	5.7	4.4	1.5	0.4	setosa
32	5.2	4.1	1.5	0.1	setosa
33	5.5	4.2	1.4	0.2	setosa

In [18]:

iris >> filter(if_all(ends_with("Width"), lambda x: x > 2))

iris >> filter(if_all(ends_with("Width"), lambda x: x > 2))

Out[18]:

	Sepal_Length	Sepal_Width	Petal_Length	Petal_Width	Species
	<float64>	<float64>	<float64>	<float64>	<object>
100	6.3	3.3	6.0	2.5	virginica
102	7.1	3.0	5.9	2.1	virginica
104	6.5	3.0	5.8	2.2	virginica
105	7.6	3.0	6.6	2.1	virginica
109	7.2	3.6	6.1	2.5	virginica
112	6.8	3.0	5.5	2.1	virginica
114	5.8	2.8	5.1	2.4	virginica
115	6.4	3.2	5.3	2.3	virginica
117	7.7	3.8	6.7	2.2	virginica
118	7.7	2.6	6.9	2.3	virginica
120	6.9	3.2	5.7	2.3	virginica
124	6.7	3.3	5.7	2.1	virginica
128	6.4	2.8	5.6	2.1	virginica
132	6.4	2.8	5.6	2.2	virginica
135	7.7	3.0	6.1	2.3	virginica
136	6.3	3.4	5.6	2.4	virginica
139	6.9	3.1	5.4	2.1	virginica
140	6.7	3.1	5.6	2.4	virginica
141	6.9	3.1	5.1	2.3	virginica
143	6.8	3.2	5.9	2.3	virginica
144	6.7	3.3	5.7	2.5	virginica
145	6.7	3.0	5.2	2.3	virginica
148	6.2	3.4	5.4	2.3	virginica

In [19]:

df = tibble(
    id=[1, 2, 3, 4],
    w=runif(4), 
    x=runif(4), 
    y=runif(4), 
    z=runif(4)
)
df >> rowwise() >> mutate(
    sum = sum(c_across(c[f.w:f.z])),
    sd = sd(c_across(c[f.w:f.z]))
)

df = tibble( id=[1, 2, 3, 4], w=runif(4), x=runif(4), y=runif(4), z=runif(4) ) df >> rowwise() >> mutate( sum = sum(c_across(c[f.w:f.z])), sd = sd(c_across(c[f.w:f.z])) )

Out[19]:

	id	w	x	y	z	sum	sd
	<int64>	<float64>	<float64>	<float64>	<float64>	<float64>	<float64>
0	1	0.909293	0.880456	0.174213	0.382593	1.963962	0.416324
1	2	0.102912	0.952811	0.632536	0.845920	1.688258	0.429225
2	3	0.425592	0.320275	0.803515	0.831533	1.549382	0.254112
3	4	0.218472	0.849190	0.637853	0.887980	1.705514	0.321026

TibbleRowwise: (n=4)

In [ ]: