Class SeriesGroupBy (1.9.0)

SeriesGroupBy(
    block: bigframes.core.blocks.Block,
    value_column: str,
    by_col_ids: typing.Sequence[str],
    value_name: typing.Hashable = None,
    dropna=True,
)

Class for grouping and aggregating relational data.

Methods

agg

agg(
    func=None,
) -> typing.Union[bigframes.dataframe.DataFrame, bigframes.series.Series]

Aggregate using one or more operations.

Examples:

>>> import bigframes.pandas as bpd
>>> import numpy as np
>>> bpd.options.display.progress_bar = None

>>> s = bpd.Series([1, 2, 3, 4], index=[1, 1, 2, 2])
>>> s.groupby(level=0).agg(['min', 'max'])
   min  max
1    1    2
2    3    4
<BLANKLINE>
[2 rows x 2 columns]

aggregate

aggregate(
    func=None,
) -> typing.Union[bigframes.dataframe.DataFrame, bigframes.series.Series]

Aggregate using one or more operations.

Examples:

>>> import bigframes.pandas as bpd
>>> import numpy as np
>>> bpd.options.display.progress_bar = None

>>> s = bpd.Series([1, 2, 3, 4], index=[1, 1, 2, 2])
>>> s.groupby(level=0).aggregate(['min', 'max'])
   min  max
1    1    2
2    3    4
<BLANKLINE>
[2 rows x 2 columns]

all

all() -> bigframes.series.Series

Return True if all values in the group are true, else False.

Examples:

For SeriesGroupBy:

>>> import bigframes.pandas as bpd
>>> bpd.options.display.progress_bar = None

>>> lst = ['a', 'a', 'b']
>>> ser = bpd.Series([1, 2, 0], index=lst)
>>> ser.groupby(level=0).all()
a     True
b    False
dtype: boolean

For DataFrameGroupBy:

>>> data = [[1, 0, 3], [1, 5, 6], [7, 8, 9]]
>>> df = bpd.DataFrame(data, columns=["a", "b", "c"],
...                    index=["ostrich", "penguin", "parrot"])
>>> df.groupby(by=["a"]).all()
        b       c
a
1   False    True
7   True    True
<BLANKLINE>
[2 rows x 2 columns]
Returns
Type Description
Series or DataFrame DataFrame or Series of boolean values, where a value is True if all elements are True within its respective group; otherwise False.

any

any() -> bigframes.series.Series

Return True if any value in the group is true, else False.

Examples:

For SeriesGroupBy:

>>> import bigframes.pandas as bpd
>>> bpd.options.display.progress_bar = None

>>> lst = ['a', 'a', 'b']
>>> ser = bpd.Series([1, 2, 0], index=lst)
>>> ser.groupby(level=0).any()
a     True
b    False
dtype: boolean

For DataFrameGroupBy:

>>> data = [[1, 0, 3], [1, 0, 6], [7, 1, 9]]
>>> df = bpd.DataFrame(data, columns=["a", "b", "c"],
...                    index=["ostrich", "penguin", "parrot"])
>>> df.groupby(by=["a"]).any()
        b       c
a
1   False    True
7   True    True
<BLANKLINE>
[2 rows x 2 columns]
Returns
Type Description
Series or DataFrame DataFrame or Series of boolean values, where a value is True if any element is True within its respective group; otherwise False.

count

count() -> bigframes.series.Series

Compute count of group, excluding missing values.

Examples:

For SeriesGroupBy:

>>> import bigframes.pandas as bpd
>>> import numpy as np
>>> bpd.options.display.progress_bar = None

>>> lst = ['a', 'a', 'b']
>>> ser = bpd.Series([1, 2, np.nan], index=lst)
>>> ser.groupby(level=0).count()
a     2
b     0
dtype: Int64

For DataFrameGroupBy:

>>> data = [[1, np.nan, 3], [1, np.nan, 6], [7, 8, 9]]
>>> df = bpd.DataFrame(data, columns=["a", "b", "c"],
...                    index=["cow", "horse", "bull"])
>>> df.groupby(by=["a"]).count()
   b  c
a
1  0  2
7  1  1
<BLANKLINE>
[2 rows x 2 columns]
Returns
Type Description
Series or DataFrame Count of values within each group.

cumcount

cumcount(*args, **kwargs) -> bigframes.series.Series

Number each item in each group from 0 to the length of that group - 1. (DataFrameGroupBy functionality is not yet available.)

Examples:

For SeriesGroupBy:

>>> import bigframes.pandas as bpd
>>> bpd.options.display.progress_bar = None

>>> lst = ['a', 'a', 'b', 'b', 'c']
>>> ser = bpd.Series([5, 1, 2, 3, 4], index=lst)
>>> ser.groupby(level=0).cumcount()
a    0
a    1
b    0
b    1
c    0
dtype: Int64
>>> ser.groupby(level=0).cumcount(ascending=False)
a    0
a    1
b    0
b    1
c    0
dtype: Int64
Parameter
Name Description
ascending bool, default True

If False, number in reverse, from length of group - 1 to 0.

Returns
Type Description
Series Sequence number of each element within each group.

cummax

cummax(*args, **kwargs) -> bigframes.series.Series

Cumulative max for each group.

Examples:

For SeriesGroupBy:

>>> import bigframes.pandas as bpd
>>> import numpy as np
>>> bpd.options.display.progress_bar = None

>>> lst = ['a', 'a', 'b']
>>> ser = bpd.Series([6, 2, 0], index=lst)
>>> ser.groupby(level=0).cummax()
a    6
a    6
b    0
dtype: Int64

For DataFrameGroupBy:

>>> data = [[1, 8, 2], [1, 2, 5], [2, 6, 9]]
>>> df = bpd.DataFrame(data, columns=["a", "b", "c"],
...                   index=["fox", "gorilla", "lion"])
>>> df.groupby("a").cummax()
         b  c
fox      8  2
gorilla  8  5
lion     6  9
<BLANKLINE>
[3 rows x 2 columns]
Returns
Type Description
Series or DataFrame Cumulative max for each group.

cummin

cummin(*args, **kwargs) -> bigframes.series.Series

Cumulative min for each group.

Examples:

For SeriesGroupBy:

>>> import bigframes.pandas as bpd
>>> import numpy as np
>>> bpd.options.display.progress_bar = None

>>> lst = ['a', 'a', 'b']
>>> ser = bpd.Series([6, 2, 0], index=lst)
>>> ser.groupby(level=0).cummin()
a    6
a    2
b    0
dtype: Int64

For DataFrameGroupBy:

>>> data = [[1, 8, 2], [1, 2, 5], [2, 6, 9]]
>>> df = bpd.DataFrame(data, columns=["a", "b", "c"],
...                   index=["fox", "gorilla", "lion"])
>>> df.groupby("a").cummin()
         b  c
fox      8  2
gorilla  2  2
lion     6  9
<BLANKLINE>
[3 rows x 2 columns]
Returns
Type Description
Series or DataFrame Cumulative min for each group.

cumprod

cumprod(*args, **kwargs) -> bigframes.series.Series

Cumulative product for each group.

Examples:

For SeriesGroupBy:

>>> import bigframes.pandas as bpd
>>> import numpy as np
>>> bpd.options.display.progress_bar = None

>>> lst = ['a', 'a', 'b']
>>> ser = bpd.Series([6, 2, 0], index=lst)
>>> ser.groupby(level=0).cumprod()
a     6.0
a    12.0
b     0.0
dtype: Float64

For DataFrameGroupBy:

>>> data = [[1, 8, 2], [1, 2, 5], [2, 6, 9]]
>>> df = bpd.DataFrame(data, columns=["a", "b", "c"],
...                   index=["cow", "horse", "bull"])
>>> df.groupby("a").cumprod()
          b     c
cow     8.0   2.0
horse  16.0  10.0
bull    6.0   9.0
<BLANKLINE>
[3 rows x 2 columns]
Returns
Type Description
Series or DataFrame Cumulative product for each group.

cumsum

cumsum(*args, **kwargs) -> bigframes.series.Series

Cumulative sum for each group.

Examples:

For SeriesGroupBy:

>>> import bigframes.pandas as bpd
>>> import numpy as np
>>> bpd.options.display.progress_bar = None

>>> lst = ['a', 'a', 'b']
>>> ser = bpd.Series([6, 2, 0], index=lst)
>>> ser.groupby(level=0).cumsum()
a    6
a    8
b    0
dtype: Int64

For DataFrameGroupBy:

>>> data = [[1, 8, 2], [1, 2, 5], [2, 6, 9]]
>>> df = bpd.DataFrame(data, columns=["a", "b", "c"],
...                   index=["fox", "gorilla", "lion"])
>>> df.groupby("a").cumsum()
          b  c
fox       8  2
gorilla  10  7
lion      6  9
<BLANKLINE>
[3 rows x 2 columns]
Returns
Type Description
Series or DataFrame Cumulative sum for each group.

diff

diff(periods=1) -> bigframes.series.Series

First discrete difference of element. Calculates the difference of each element compared with another element in the group (default is element in previous row).

Examples:

For SeriesGroupBy:

>>> import bigframes.pandas as bpd
>>> import numpy as np
>>> bpd.options.display.progress_bar = None

>>> lst = ['a', 'a', 'a', 'b', 'b', 'b']
>>> ser = bpd.Series([7, 2, 8, 4, 3, 3], index=lst)
>>> ser.groupby(level=0).diff()
a    <NA>
a      -5
a       6
b    <NA>
b      -1
b       0
dtype: Int64

For DataFrameGroupBy:

>>> data = {'a': [1, 3, 5, 7, 7, 8, 3], 'b': [1, 4, 8, 4, 4, 2, 1]}
>>> df = bpd.DataFrame(data, index=['dog', 'dog', 'dog',
...                   'mouse', 'mouse', 'mouse', 'mouse'])
>>> df.groupby(level=0).diff()
          a     b
dog    <NA>  <NA>
dog       2     3
dog       2     4
mouse  <NA>  <NA>
mouse     0     0
mouse     1    -2
mouse    -5    -1
<BLANKLINE>
[7 rows x 2 columns]
Returns
Type Description
Series or DataFrame First differences.

expanding

expanding(min_periods: int = 1) -> bigframes.core.window.Window

Provides expanding functionality.

Examples:

>>> import bigframes.pandas as bpd
>>> import numpy as np
>>> bpd.options.display.progress_bar = None

>>> lst = ['a', 'a', 'c', 'c', 'e']
>>> ser = bpd.Series([1, 0, -2, -1, 2], index=lst)
>>> ser.groupby(level=0).expanding().min()
index  index
a      a         1
       a         0
c      c        -2
       c        -2
e      e         2
dtype: Int64
Returns
Type Description
Series or DataFrame An expanding grouper, providing expanding functionality per group.

kurt

kurt(*args, **kwargs) -> bigframes.series.Series

Return unbiased kurtosis over requested axis.

Kurtosis obtained using Fisher's definition of kurtosis (kurtosis of normal == 0.0). Normalized by N-1.

Examples:

>>> import bigframes.pandas as bpd
>>> bpd.options.display.progress_bar = None

>>> lst = ['a', 'a', 'a', 'a', 'b', 'b', 'b', 'b', 'b']
>>> ser = bpd.Series([0, 1, 1, 0, 0, 1, 2, 4, 5], index=lst)
>>> ser.groupby(level=0).kurt()
a        -6.0
b   -1.963223
dtype: Float64
Parameter
Name Description
numeric_only bool, default False

Include only float, int or boolean data.

kurtosis

kurtosis(*args, **kwargs) -> bigframes.series.Series

Return unbiased kurtosis over requested axis.

Kurtosis obtained using Fisher's definition of kurtosis (kurtosis of normal == 0.0). Normalized by N-1.

Examples:

>>> import bigframes.pandas as bpd
>>> bpd.options.display.progress_bar = None

>>> lst = ['a', 'a', 'a', 'a', 'b', 'b', 'b', 'b', 'b']
>>> ser = bpd.Series([0, 1, 1, 0, 0, 1, 2, 4, 5], index=lst)
>>> ser.groupby(level=0).kurtosis()
a        -6.0
b   -1.963223
dtype: Float64
Parameter
Name Description
numeric_only bool, default False

Include only float, int or boolean data.

max

max(*args) -> bigframes.series.Series

Compute max of group values.

Examples:

For SeriesGroupBy:

>>> import bigframes.pandas as bpd
>>> bpd.options.display.progress_bar = None

>>> lst = ['a', 'a', 'b', 'b']
>>> ser = bpd.Series([1, 2, 3, 4], index=lst)
>>> ser.groupby(level=0).max()
a     2
b     4
dtype: Int64

For DataFrameGroupBy:

>>> data = [[1, 8, 2], [1, 2, 5], [2, 5, 8], [2, 6, 9]]
>>> df = bpd.DataFrame(data, columns=["a", "b", "c"],
...                    index=["tiger", "leopard", "cheetah", "lion"])
>>> df.groupby(by=["a"]).max()
   b  c
a
1  8  5
2  6  9
<BLANKLINE>
[2 rows x 2 columns]
Parameters
Name Description
numeric_only bool, default False

Include only float, int, boolean columns.

min_count int, default 0

The required number of valid values to perform the operation. If fewer than min_count and non-NA values are present, the result will be NA.

Returns
Type Description
Series or DataFrame Computed max of values within each group.

mean

mean(*args) -> bigframes.series.Series

Compute mean of groups, excluding missing values.

Examples:

>>> import bigframes.pandas as bpd
>>> import numpy as np
>>> bpd.options.display.progress_bar = None
>>> df = bpd.DataFrame({'A': [1, 1, 2, 1, 2],
...                    'B': [np.nan, 2, 3, 4, 5],
...                    'C': [1, 2, 1, 1, 2]}, columns=['A', 'B', 'C'])

Groupby one column and return the mean of the remaining columns in each group.

>>> df.groupby('A').mean()
    B         C
A
1  3.0  1.333333
2  4.0       1.5
<BLANKLINE>
[2 rows x 2 columns]

Groupby two columns and return the mean of the remaining column.

>>> df.groupby(['A', 'B']).mean()
         C
A B
1 2.0  2.0
  4.0  1.0
2 3.0  1.0
  5.0  2.0
<BLANKLINE>
[4 rows x 1 columns]

Groupby one column and return the mean of only particular column in the group.

>>> df.groupby('A')['B'].mean()
A
1    3.0
2    4.0
Name: B, dtype: Float64
Parameter
Name Description
numeric_only bool, default False

Include only float, int, boolean columns.

Returns
Type Description
pandas.Series or pandas.DataFrame Mean of groups.

median

median(*args, exact: bool = True, **kwargs) -> bigframes.series.Series

Compute median of groups, excluding missing values.

Examples:

For SeriesGroupBy:

>>> import bigframes.pandas as bpd
>>> import numpy as np
>>> bpd.options.display.progress_bar = None

>>> lst = ['a', 'a', 'a', 'b', 'b', 'b']
>>> ser = bpd.Series([7, 2, 8, 4, 3, 3], index=lst)
>>> ser.groupby(level=0).median()
a    7.0
b    3.0
dtype: Float64

For DataFrameGroupBy:

>>> data = {'a': [1, 3, 5, 7, 7, 8, 3], 'b': [1, 4, 8, 4, 4, 2, 1]}
>>> df = bpd.DataFrame(data, index=['dog', 'dog', 'dog',
...                    'mouse', 'mouse', 'mouse', 'mouse'])
>>> df.groupby(level=0).median()
        a    b
dog    3.0  4.0
mouse  7.0  3.0
<BLANKLINE>
[2 rows x 2 columns]
Parameters
Name Description
numeric_only bool, default False

Include only float, int, boolean columns.

exact bool, default True

Calculate the exact median instead of an approximation.

Returns
Type Description
pandas.Series or pandas.DataFrame Median of groups.

min

min(*args) -> bigframes.series.Series

Compute min of group values.

Examples:

For SeriesGroupBy:

>>> import bigframes.pandas as bpd
>>> import numpy as np
>>> bpd.options.display.progress_bar = None

>>> lst = ['a', 'a', 'b', 'b']
>>> ser = bpd.Series([1, 2, 3, 4], index=lst)
>>> ser.groupby(level=0).min()
a     1
b     3
dtype: Int64

For DataFrameGroupBy:

>>> data = [[1, 8, 2], [1, 2, 5], [2, 5, 8], [2, 6, 9]]
>>> df = bpd.DataFrame(data, columns=["a", "b", "c"],
...                    index=["tiger", "leopard", "cheetah", "lion"])
>>> df.groupby(by=["a"]).min()
   b  c
a
1  2  2
2  5  8
<BLANKLINE>
[2 rows x 2 columns]
Parameters
Name Description
numeric_only bool, default False

Include only float, int, boolean columns.

min_count int, default 0

The required number of valid values to perform the operation. If fewer than min_count and non-NA values are present, the result will be NA.

Returns
Type Description
Series or DataFrame Computed min of values within each group.

nunique

nunique() -> bigframes.series.Series

Return number of unique elements in the group.

Examples:

>>> import bigframes.pandas as bpd
>>> import numpy as np
>>> bpd.options.display.progress_bar = None

>>> lst = ['a', 'a', 'b', 'b']
>>> ser = bpd.Series([1, 2, 3, 3], index=lst)
>>> ser.groupby(level=0).nunique()
a    2
b    1
dtype: Int64
Returns
Type Description
Series Number of unique values within each group.

prod

prod(*args) -> bigframes.series.Series

Compute prod of group values. (DataFrameGroupBy functionality is not yet available.)

Examples:

For SeriesGroupBy:

>>> import bigframes.pandas as bpd
>>> import numpy as np
>>> bpd.options.display.progress_bar = None

>>> lst = ['a', 'a', 'b', 'b']
>>> ser = bpd.Series([1, 2, 3, 4], index=lst)
>>> ser.groupby(level=0).prod()
a     2.0
b    12.0
dtype: Float64
Parameters
Name Description
numeric_only bool, default False

Include only float, int, boolean columns.

min_count int, default 0

The required number of valid values to perform the operation. If fewer than min_count and non-NA values are present, the result will be NA.

Returns
Type Description
Series or DataFrame Computed prod of values within each group.

quantile

quantile(
    q: typing.Union[float, typing.Sequence[float]] = 0.5, *, numeric_only: bool = False
) -> bigframes.series.Series

Return group values at the given quantile, a la numpy.percentile.

Examples:

>>> import bigframes.pandas as bpd
>>> bpd.options.display.progress_bar = None
>>> df = bpd.DataFrame([
...     ['a', 1], ['a', 2], ['a', 3],
...     ['b', 1], ['b', 3], ['b', 5]
... ], columns=['key', 'val'])
>>> df.groupby('key').quantile()
     val
key
a    2.0
b    3.0
<BLANKLINE>
[2 rows x 1 columns]
Parameters
Name Description
q float or array-like, default 0.5 (50% quantile)

Value(s) between 0 and 1 providing the quantile(s) to compute.

numeric_only bool, default False

Include only float, int or boolean data.

Returns
Type Description
Series or DataFrame Return type determined by caller of GroupBy object.

rolling

rolling(window: int, min_periods=None) -> bigframes.core.window.Window

Returns a rolling grouper, providing rolling functionality per group.

Examples:

>>> import bigframes.pandas as bpd
>>> import numpy as np
>>> bpd.options.display.progress_bar = None

>>> lst = ['a', 'a', 'a', 'a', 'e']
>>> ser = bpd.Series([1, 0, -2, -1, 2], index=lst)
>>> ser.groupby(level=0).rolling(2).min()
index  index
a      a        <NA>
    a           0
    a          -2
    a          -2
e      e        <NA>
dtype: Int64
Parameter
Name Description
min_periods int, default None

Minimum number of observations in window required to have a value; otherwise, result is np.nan. For a window that is specified by an offset, min_periods will default to 1. For a window that is specified by an integer, min_periods will default to the size of the window.

Returns
Type Description
Series or DataFrame Return a new grouper with our rolling appended.

shift

shift(periods=1) -> bigframes.series.Series

Shift index by desired number of periods.

size

size() -> bigframes.series.Series

API documentation for size method.

skew

skew(*args, **kwargs) -> bigframes.series.Series

Return unbiased skew within groups.

Normalized by N-1.

Examples:

For SeriesGroupBy:

>>> import bigframes.pandas as bpd
>>> import numpy as np
>>> bpd.options.display.progress_bar = None

>>> ser = bpd.Series([390., 350., 357., np.nan, 22., 20., 30.],
...                  index=['Falcon', 'Falcon', 'Falcon', 'Falcon',
...                         'Parrot', 'Parrot', 'Parrot'],
...                  name="Max Speed")
>>> ser.groupby(level=0).skew()
Falcon    1.525174
Parrot    1.457863
Name: Max Speed, dtype: Float64
Parameter
Name Description
numeric_only bool, default False

Include only float, int or boolean data.

std

std(*args, **kwargs) -> bigframes.series.Series

Compute standard deviation of groups, excluding missing values.

For multiple groupings, the result index will be a MultiIndex.

Examples:

For SeriesGroupBy:

>>> import bigframes.pandas as bpd
>>> import numpy as np
>>> bpd.options.display.progress_bar = None

>>> lst = ['a', 'a', 'a', 'b', 'b', 'b']
>>> ser = bpd.Series([7, 2, 8, 4, 3, 3], index=lst)
>>> ser.groupby(level=0).std()
a     3.21455
b     0.57735
dtype: Float64

For DataFrameGroupBy:

>>> data = {'a': [1, 3, 5, 7, 7, 8, 3], 'b': [1, 4, 8, 4, 4, 2, 1]}
>>> df = bpd.DataFrame(data, index=['dog', 'dog', 'dog',
...                    'mouse', 'mouse', 'mouse', 'mouse'])
>>> df.groupby(level=0).std()
              a         b
dog         2.0  3.511885
mouse  2.217356       1.5
<BLANKLINE>
[2 rows x 2 columns]
Parameter
Name Description
numeric_only bool, default False

Include only float, int or boolean data.

Returns
Type Description
Series or DataFrame Standard deviation of values within each group.

sum

sum(*args) -> bigframes.series.Series

Compute sum of group values.

Examples:

For SeriesGroupBy:

>>> import bigframes.pandas as bpd
>>> bpd.options.display.progress_bar = None

>>> lst = ['a', 'a', 'b', 'b']
>>> ser = bpd.Series([1, 2, 3, 4], index=lst)
>>> ser.groupby(level=0).sum()
a     3
b     7
dtype: Int64

For DataFrameGroupBy:

>>> data = [[1, 8, 2], [1, 2, 5], [2, 5, 8], [2, 6, 9]]
>>> df = bpd.DataFrame(data, columns=["a", "b", "c"],
...                   index=["tiger", "leopard", "cheetah", "lion"])
>>> df.groupby("a").sum()
    b   c
a
1  10   7
2  11  17
<BLANKLINE>
[2 rows x 2 columns]
Parameters
Name Description
numeric_only bool, default False

Include only float, int, boolean columns.

min_count int, default 0

The required number of valid values to perform the operation. If fewer than min_count and non-NA values are present, the result will be NA.

Returns
Type Description
Series or DataFrame Computed sum of values within each group.

var

var(*args, **kwargs) -> bigframes.series.Series

Compute variance of groups, excluding missing values.

For multiple groupings, the result index will be a MultiIndex.

Examples:

For SeriesGroupBy:

>>> import bigframes.pandas as bpd
>>> import numpy as np
>>> bpd.options.display.progress_bar = None

>>> lst = ['a', 'a', 'a', 'b', 'b', 'b']
>>> ser = bpd.Series([7, 2, 8, 4, 3, 3], index=lst)
>>> ser.groupby(level=0).var()
a   10.333333
b    0.333333
dtype: Float64

For DataFrameGroupBy:

>>> data = {'a': [1, 3, 5, 7, 7, 8, 3], 'b': [1, 4, 8, 4, 4, 2, 1]}
>>> df = bpd.DataFrame(data, index=['dog', 'dog', 'dog',
...                    'mouse', 'mouse', 'mouse', 'mouse'])
>>> df.groupby(level=0).var()
              a          b
dog         4.0  12.333333
mouse  4.916667       2.25
<BLANKLINE>
[2 rows x 2 columns]
Parameter
Name Description
numeric_only bool, default False

Include only float, int or boolean data.