Skip to content

gcages.index_manipulation#

Manipulation of the index of pd.DataFrame's

Functions:

Name Description
combine_sectors

Combine the input pd.DataFrame's levels
combine_species

Combine the input pd.DataFrame's levels
split_sectors

Split the input pd.DataFrame's level to split into sectors
split_species

Split the input pd.DataFrame's level to split into species

combine_sectors #

combine_sectors(
    indf: DataFrame,
    drop: bool = True,
    combined_level: str = "variable",
    top_level: str = "table",
    middle_level: str = "species",
    bottom_level: str = "sectors",
    level_separator: str = "|",
) -> DataFrame

Combine the input pd.DataFrame's levels

This assumes that you want to combine three levels.

This is the inverse of split_sectors.

Parameters:

Name Type Description Default
indf DataFrame

Input data

 required
drop bool

Should the combined levels be dropped?

 True
combined_level str

The name of the combined level

 'variable'
top_level str

Name of the top level in the combined output

 'table'
middle_level str

Name of the middle level in the combined output

 'species'
bottom_level str

Name of the bottom level in the combined output

 'sectors'
level_separator str

Separator between levels in combined_level

 '|'

Returns:

Type Description
DataFrame

indf with the given levels combined into combined_level

Examples:

>>> indf = pd.DataFrame(
...     [
...         [1.0, 2.0],
...         [3.0, 2.0],
...         [1.3, 2.2],
...         [3.4, 2.1],
...     ],
...     columns=[2015, 2100],
...     index=pd.MultiIndex.from_tuples(
...         [
...             ("sa", "Emissions", "CO2", "sector", "t / yr"),
...             ("sa", "Emissions", "CO2", "sector|sub sector", "t / yr"),
...             (
...                 "sb",
...                 "Emissions",
...                 "CH4",
...                 "sector|sub|sub-sub|sub-sub-sub",
...                 "kg / yr",
...             ),
...             ("sb", "Emissions", "CO2", "sector", "t / yr"),
...         ],
...         names=["scenario", "table", "species", "sectors", "unit"],
...     ),
... )
>>> combine_sectors(indf)
                                                               2015  2100
scenario unit    variable
sa       t / yr  Emissions|CO2|sector                           1.0   2.0
                 Emissions|CO2|sector|sub sector                3.0   2.0
sb       kg / yr Emissions|CH4|sector|sub|sub-sub|sub-sub-sub   1.3   2.2
         t / yr  Emissions|CO2|sector                           3.4   2.1
>>> indf_funky = pd.DataFrame(
...     [
...         [1.0, 2.0],
...         [3.0, 2.0],
...         [1.3, 2.2],
...         [3.4, 2.1],
...     ],
...     columns=[2015, 2100],
...     index=pd.MultiIndex.from_tuples(
...         [
...             ("sa", "Emissions", "CO2", "sector", "t / yr"),
...             ("sa", "Emissions", "CO2", "sector-sub sector", "t / yr"),
...             ("sb", "Emissions", "CH4", "sector-sub-sub", "kg / yr"),
...             ("sb", "Emissions", "CO2", "sector", "t / yr"),
...         ],
...         names=["scenario", "prefix", "gas", "sector", "unit"],
...     ),
... )
>>> combine_sectors(
...     indf_funky,
...     combined_level="vv",
...     top_level="prefix",
...     middle_level="gas",
...     bottom_level="sector",
...     level_separator="-",
... )
                                                  2015  2100
scenario unit    vv
sa       t / yr  Emissions-CO2-sector              1.0   2.0
                 Emissions-CO2-sector-sub sector   3.0   2.0
sb       kg / yr Emissions-CH4-sector-sub-sub      1.3   2.2
         t / yr  Emissions-CO2-sector              3.4   2.1
Source code in src/gcages/index_manipulation.py 
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
def combine_sectors(  # noqa: PLR0913
    indf: pd.DataFrame,  # Could open this out as can also work on Series and MultiIndex
    drop: bool = True,
    combined_level: str = "variable",
    top_level: str = "table",
    middle_level: str = "species",
    bottom_level: str = "sectors",
    level_separator: str = "|",
) -> pd.DataFrame:
    """
    Combine the input [pd.DataFrame][pandas.DataFrame]'s levels

    This assumes that you want to combine three levels.

    This is the inverse of [split_sectors][(m).].

    Parameters
    ----------
    indf
        Input data

    drop
        Should the combined levels be dropped?

    combined_level
        The name of the combined level

    top_level
        Name of the top level in the combined output

    middle_level
        Name of the middle level in the combined output

    bottom_level
        Name of the bottom level in the combined output

    level_separator
        Separator between levels in `combined_level`

    Returns
    -------
    :
        `indf` with the given levels combined into `combined_level`

    Examples
    --------
    >>> indf = pd.DataFrame(
    ...     [
    ...         [1.0, 2.0],
    ...         [3.0, 2.0],
    ...         [1.3, 2.2],
    ...         [3.4, 2.1],
    ...     ],
    ...     columns=[2015, 2100],
    ...     index=pd.MultiIndex.from_tuples(
    ...         [
    ...             ("sa", "Emissions", "CO2", "sector", "t / yr"),
    ...             ("sa", "Emissions", "CO2", "sector|sub sector", "t / yr"),
    ...             (
    ...                 "sb",
    ...                 "Emissions",
    ...                 "CH4",
    ...                 "sector|sub|sub-sub|sub-sub-sub",
    ...                 "kg / yr",
    ...             ),
    ...             ("sb", "Emissions", "CO2", "sector", "t / yr"),
    ...         ],
    ...         names=["scenario", "table", "species", "sectors", "unit"],
    ...     ),
    ... )
    >>> combine_sectors(indf)  # doctest: +NORMALIZE_WHITESPACE
                                                                   2015  2100
    scenario unit    variable
    sa       t / yr  Emissions|CO2|sector                           1.0   2.0
                     Emissions|CO2|sector|sub sector                3.0   2.0
    sb       kg / yr Emissions|CH4|sector|sub|sub-sub|sub-sub-sub   1.3   2.2
             t / yr  Emissions|CO2|sector                           3.4   2.1
    >>> indf_funky = pd.DataFrame(
    ...     [
    ...         [1.0, 2.0],
    ...         [3.0, 2.0],
    ...         [1.3, 2.2],
    ...         [3.4, 2.1],
    ...     ],
    ...     columns=[2015, 2100],
    ...     index=pd.MultiIndex.from_tuples(
    ...         [
    ...             ("sa", "Emissions", "CO2", "sector", "t / yr"),
    ...             ("sa", "Emissions", "CO2", "sector-sub sector", "t / yr"),
    ...             ("sb", "Emissions", "CH4", "sector-sub-sub", "kg / yr"),
    ...             ("sb", "Emissions", "CO2", "sector", "t / yr"),
    ...         ],
    ...         names=["scenario", "prefix", "gas", "sector", "unit"],
    ...     ),
    ... )
    >>> combine_sectors(
    ...     indf_funky,
    ...     combined_level="vv",
    ...     top_level="prefix",
    ...     middle_level="gas",
    ...     bottom_level="sector",
    ...     level_separator="-",
    ... )  # doctest: +NORMALIZE_WHITESPACE
                                                      2015  2100
    scenario unit    vv
    sa       t / yr  Emissions-CO2-sector              1.0   2.0
                     Emissions-CO2-sector-sub sector   3.0   2.0
    sb       kg / yr Emissions-CH4-sector-sub-sub      1.3   2.2
             t / yr  Emissions-CO2-sector              3.4   2.1
    """
    try:
        from pandas_indexing.core import formatlevel  # noqa: PLC0415
    except ImportError as exc:
        raise MissingOptionalDependencyError(
            "combine_sectors", requirement="pandas_indexing"
        ) from exc

    kwargs = {
        combined_level: level_separator.join(
            [
                "{" + f"{level}" + "}"
                for level in [top_level, middle_level, bottom_level]
            ]
        )
    }

    return formatlevel(indf, drop=drop, **kwargs)  # type: ignore

combine_species #

combine_species(
    indf: DataFrame,
    drop: bool = True,
    combined_level: str = "variable",
    top_level: str = "table",
    bottom_level: str = "species",
    level_separator: str = "|",
) -> DataFrame

Combine the input pd.DataFrame's levels

This assumes that you want to combine two levels.

This is the inverse of split_species.

Parameters:

Name Type Description Default
indf DataFrame

Input data

 required
drop bool

Should the combined levels be dropped?

 True
combined_level str

The name of the combined level

 'variable'
top_level str

Name of the top level in the combined output

 'table'
bottom_level str

Name of the bottom level in the combined output

 'species'
level_separator str

Separator between levels in combined_level

 '|'

Returns:

Type Description
DataFrame

indf with the given levels combined into combined_level

Examples:

>>> indf = pd.DataFrame(
...     [
...         [1.0, 2.0],
...         [3.0, 2.0],
...         [1.3, 2.2],
...         [3.4, 2.1],
...     ],
...     columns=[2015, 2100],
...     index=pd.MultiIndex.from_tuples(
...         [
...             ("sa", "Emissions", "CO2", "t / yr"),
...             ("sa", "Emissions", "CO2", "t / yr"),
...             ("sb", "Emissions", "CH4", "kg / yr"),
...             ("sb", "Emissions", "CO2", "t / yr"),
...         ],
...         names=["scenario", "table", "species", "unit"],
...     ),
... )
>>> combine_species(indf)
                                2015  2100
scenario unit    variable
sa       t / yr  Emissions|CO2   1.0   2.0
                 Emissions|CO2   3.0   2.0
sb       kg / yr Emissions|CH4   1.3   2.2
         t / yr  Emissions|CO2   3.4   2.1
>>> indf_funky = pd.DataFrame(
...     [
...         [1.0, 2.0],
...         [3.0, 2.0],
...         [1.3, 2.2],
...         [3.4, 2.1],
...     ],
...     columns=[2015, 2100],
...     index=pd.MultiIndex.from_tuples(
...         [
...             ("sa", "Emissions", "CO2", "t / yr"),
...             ("sa", "Emissions", "CO2-sector-sub sector", "t / yr"),
...             ("sb", "Emissions", "CH4-sector-sub-sub", "kg / yr"),
...             ("sb", "Emissions", "CO2", "t / yr"),
...         ],
...         names=["scenario", "prefix", "gas", "unit"],
...     ),
... )
>>> combine_species(
...     indf_funky,
...     combined_level="vv",
...     top_level="prefix",
...     bottom_level="gas",
...     level_separator="-",
... )
                                                  2015  2100
scenario unit    vv
sa       t / yr  Emissions-CO2                     1.0   2.0
                 Emissions-CO2-sector-sub sector   3.0   2.0
sb       kg / yr Emissions-CH4-sector-sub-sub      1.3   2.2
         t / yr  Emissions-CO2                     3.4   2.1
Source code in src/gcages/index_manipulation.py 
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
def combine_species(  # noqa: PLR0913
    indf: pd.DataFrame,
    drop: bool = True,
    combined_level: str = "variable",
    top_level: str = "table",
    bottom_level: str = "species",
    level_separator: str = "|",
) -> pd.DataFrame:
    """
    Combine the input [pd.DataFrame][pandas.DataFrame]'s levels

    This assumes that you want to combine two levels.

    This is the inverse of [split_species][(m).].

    Parameters
    ----------
    indf
        Input data

    drop
        Should the combined levels be dropped?

    combined_level
        The name of the combined level

    top_level
        Name of the top level in the combined output

    bottom_level
        Name of the bottom level in the combined output

    level_separator
        Separator between levels in `combined_level`

    Returns
    -------
    :
        `indf` with the given levels combined into `combined_level`

    Examples
    --------
    >>> indf = pd.DataFrame(
    ...     [
    ...         [1.0, 2.0],
    ...         [3.0, 2.0],
    ...         [1.3, 2.2],
    ...         [3.4, 2.1],
    ...     ],
    ...     columns=[2015, 2100],
    ...     index=pd.MultiIndex.from_tuples(
    ...         [
    ...             ("sa", "Emissions", "CO2", "t / yr"),
    ...             ("sa", "Emissions", "CO2", "t / yr"),
    ...             ("sb", "Emissions", "CH4", "kg / yr"),
    ...             ("sb", "Emissions", "CO2", "t / yr"),
    ...         ],
    ...         names=["scenario", "table", "species", "unit"],
    ...     ),
    ... )
    >>> combine_species(indf)  # doctest: +NORMALIZE_WHITESPACE
                                    2015  2100
    scenario unit    variable
    sa       t / yr  Emissions|CO2   1.0   2.0
                     Emissions|CO2   3.0   2.0
    sb       kg / yr Emissions|CH4   1.3   2.2
             t / yr  Emissions|CO2   3.4   2.1
    >>> indf_funky = pd.DataFrame(
    ...     [
    ...         [1.0, 2.0],
    ...         [3.0, 2.0],
    ...         [1.3, 2.2],
    ...         [3.4, 2.1],
    ...     ],
    ...     columns=[2015, 2100],
    ...     index=pd.MultiIndex.from_tuples(
    ...         [
    ...             ("sa", "Emissions", "CO2", "t / yr"),
    ...             ("sa", "Emissions", "CO2-sector-sub sector", "t / yr"),
    ...             ("sb", "Emissions", "CH4-sector-sub-sub", "kg / yr"),
    ...             ("sb", "Emissions", "CO2", "t / yr"),
    ...         ],
    ...         names=["scenario", "prefix", "gas", "unit"],
    ...     ),
    ... )
    >>> combine_species(
    ...     indf_funky,
    ...     combined_level="vv",
    ...     top_level="prefix",
    ...     bottom_level="gas",
    ...     level_separator="-",
    ... )  # doctest: +NORMALIZE_WHITESPACE
                                                      2015  2100
    scenario unit    vv
    sa       t / yr  Emissions-CO2                     1.0   2.0
                     Emissions-CO2-sector-sub sector   3.0   2.0
    sb       kg / yr Emissions-CH4-sector-sub-sub      1.3   2.2
             t / yr  Emissions-CO2                     3.4   2.1
    """
    try:
        from pandas_indexing.core import formatlevel  # noqa: PLC0415
    except ImportError as exc:
        raise MissingOptionalDependencyError(
            "combine_species", requirement="pandas_indexing"
        ) from exc

    kwargs = {
        combined_level: level_separator.join(
            ["{" + f"{level}" + "}" for level in [top_level, bottom_level]]
        )
    }

    return formatlevel(indf, drop=drop, **kwargs)  # type: ignore

split_sectors #

split_sectors(
    indf: DataFrame,
    dropna: bool = True,
    level_to_split: str = "variable",
    top_level: str = "table",
    middle_level: str = "species",
    bottom_level: str = "sectors",
    level_separator: str = "|",
) -> DataFrame

Split the input pd.DataFrame's level to split into sectors

Any levels beyond three are all left in bottom_level in the output.

This is the inverse of combine_sectors.

Parameters:

Name Type Description Default
indf DataFrame

Input data

 required
dropna bool

Should levels which have NaNs after splitting be dropped?

 True
level_to_split str

The level to split

 'variable'
top_level str

Name of the top level after the split

 'table'
middle_level str

Name of the middle level after the split

 'species'
bottom_level str

Name of the bottom level after the split

 'sectors'
level_separator str

Separator between levels in level_to_split

 '|'

Returns:

Type Description
DataFrame

indf with level_to_split split into three levels with the given names

Examples:

>>> indf = pd.DataFrame(
...     [
...         [1.0, 2.0],
...         [3.0, 2.0],
...         [1.3, 2.2],
...         [3.4, 2.1],
...     ],
...     columns=[2015, 2100],
...     index=pd.MultiIndex.from_tuples(
...         [
...             ("sa", "Emissions|CO2|sector", "t / yr"),
...             ("sa", "Emissions|CO2|sector|sub sector", "t / yr"),
...             ("sb", "Emissions|CH4|sector|sub|sub-sub|sub-sub-sub", "kg / yr"),
...             ("sb", "Emissions|CO2|sector", "t / yr"),
...         ],
...         names=["scenario", "variable", "unit"],
...     ),
... )
>>> split_sectors(indf)
                                                                   2015  2100
scenario unit    table     species sectors
sa       t / yr  Emissions CO2     sector                           1.0   2.0
                                   sector|sub sector                3.0   2.0
sb       kg / yr Emissions CH4     sector|sub|sub-sub|sub-sub-sub   1.3   2.2
         t / yr  Emissions CO2     sector                           3.4   2.1

>>> indf_funky = pd.DataFrame(
...     [
...         [1.0, 2.0],
...         [3.0, 2.0],
...         [1.3, 2.2],
...         [3.4, 2.1],
...     ],
...     columns=[2015, 2100],
...     index=pd.MultiIndex.from_tuples(
...         [
...             ("sa", "Emissions-CO2-sector", "t / yr"),
...             ("sa", "Emissions-CO2-sector-sub sector", "t / yr"),
...             ("sb", "Emissions-CH4-sector-sub-sector-transport", "kg / yr"),
...             ("sb", "Emissions-CO2-sector", "t / yr"),
...         ],
...         names=["scenario", "vv", "unit"],
...     ),
... )
>>> split_sectors(
...     indf_funky,
...     level_to_split="vv",
...     top_level="t",
...     middle_level="m",
...     bottom_level="b",
...     level_separator="-",
... )
                                                            2015  2100
scenario unit    t         m   b
sa       t / yr  Emissions CO2 sector                        1.0   2.0
                               sector-sub sector             3.0   2.0
sb       kg / yr Emissions CH4 sector-sub-sector-transport   1.3   2.2
         t / yr  Emissions CO2 sector                        3.4   2.1
Source code in src/gcages/index_manipulation.py 
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
def split_sectors(  # noqa: PLR0913
    indf: pd.DataFrame,
    dropna: bool = True,
    level_to_split: str = "variable",
    top_level: str = "table",
    middle_level: str = "species",
    bottom_level: str = "sectors",
    level_separator: str = "|",
) -> pd.DataFrame:
    """
    Split the input [pd.DataFrame][pandas.DataFrame]'s level to split into sectors

    Any levels beyond three are all left in `bottom_level`
    in the output.

    This is the inverse of [combine_sectors][(m).].

    Parameters
    ----------
    indf
        Input data

    dropna
        Should levels which have NaNs after splitting be dropped?

    level_to_split
        The level to split

    top_level
        Name of the top level after the split

    middle_level
        Name of the middle level after the split

    bottom_level
        Name of the bottom level after the split

    level_separator
        Separator between levels in `level_to_split`

    Returns
    -------
    :
        `indf` with `level_to_split` split into three levels
        with the given names

    Examples
    --------
    >>> indf = pd.DataFrame(
    ...     [
    ...         [1.0, 2.0],
    ...         [3.0, 2.0],
    ...         [1.3, 2.2],
    ...         [3.4, 2.1],
    ...     ],
    ...     columns=[2015, 2100],
    ...     index=pd.MultiIndex.from_tuples(
    ...         [
    ...             ("sa", "Emissions|CO2|sector", "t / yr"),
    ...             ("sa", "Emissions|CO2|sector|sub sector", "t / yr"),
    ...             ("sb", "Emissions|CH4|sector|sub|sub-sub|sub-sub-sub", "kg / yr"),
    ...             ("sb", "Emissions|CO2|sector", "t / yr"),
    ...         ],
    ...         names=["scenario", "variable", "unit"],
    ...     ),
    ... )
    >>> split_sectors(indf)  # doctest: +NORMALIZE_WHITESPACE
                                                                       2015  2100
    scenario unit    table     species sectors
    sa       t / yr  Emissions CO2     sector                           1.0   2.0
                                       sector|sub sector                3.0   2.0
    sb       kg / yr Emissions CH4     sector|sub|sub-sub|sub-sub-sub   1.3   2.2
             t / yr  Emissions CO2     sector                           3.4   2.1

    >>> indf_funky = pd.DataFrame(
    ...     [
    ...         [1.0, 2.0],
    ...         [3.0, 2.0],
    ...         [1.3, 2.2],
    ...         [3.4, 2.1],
    ...     ],
    ...     columns=[2015, 2100],
    ...     index=pd.MultiIndex.from_tuples(
    ...         [
    ...             ("sa", "Emissions-CO2-sector", "t / yr"),
    ...             ("sa", "Emissions-CO2-sector-sub sector", "t / yr"),
    ...             ("sb", "Emissions-CH4-sector-sub-sector-transport", "kg / yr"),
    ...             ("sb", "Emissions-CO2-sector", "t / yr"),
    ...         ],
    ...         names=["scenario", "vv", "unit"],
    ...     ),
    ... )
    >>> split_sectors(
    ...     indf_funky,
    ...     level_to_split="vv",
    ...     top_level="t",
    ...     middle_level="m",
    ...     bottom_level="b",
    ...     level_separator="-",
    ... )  # doctest: +NORMALIZE_WHITESPACE
                                                                2015  2100
    scenario unit    t         m   b
    sa       t / yr  Emissions CO2 sector                        1.0   2.0
                                   sector-sub sector             3.0   2.0
    sb       kg / yr Emissions CH4 sector-sub-sector-transport   1.3   2.2
             t / yr  Emissions CO2 sector                        3.4   2.1
    """
    try:
        from pandas_indexing.core import extractlevel  # noqa: PLC0415
    except ImportError as exc:
        raise MissingOptionalDependencyError(
            "split_sectors", requirement="pandas_indexing"
        ) from exc

    kwargs = {
        level_to_split: level_separator.join(
            [
                "{" + f"{level}" + "}"
                for level in [top_level, middle_level, bottom_level]
            ]
        )
    }

    return extractlevel(indf, dropna=dropna, **kwargs)  # type: ignore

split_species #

split_species(
    indf: DataFrame,
    dropna: bool = True,
    level_to_split: str = "variable",
    top_level: str = "table",
    bottom_level: str = "species",
    level_separator: str = "|",
) -> DataFrame

Split the input pd.DataFrame's level to split into species

Any levels beyond two are all left in bottom_level in the output.

This is the inverse of combine_species.

Parameters:

Name Type Description Default
indf DataFrame

Input data

 required
dropna bool

Should levels which have NaNs after splitting be dropped?

 True
level_to_split str

The level to split

 'variable'
top_level str

Name of the top level after the split

 'table'
bottom_level str

Name of the bottom level after the split

 'species'
level_separator str

Separator between levels in level_to_split

 '|'

Returns:

Type Description
DataFrame

indf with level_to_split split into two levels with the given names

Examples:

>>> indf = pd.DataFrame(
...     [
...         [1.0, 2.0],
...         [3.0, 2.0],
...         [1.3, 2.2],
...         [3.4, 2.1],
...     ],
...     columns=[2015, 2100],
...     index=pd.MultiIndex.from_tuples(
...         [
...             ("sa", "Emissions|CO2", "t / yr"),
...             ("sa", "Emissions|CH4", "t / yr"),
...             ("sb", "Emissions|CH4|sector|sub", "kg / yr"),
...             ("sb", "Emissions|N2O", "t / yr"),
...         ],
...         names=["scenario", "variable", "unit"],
...     ),
... )
>>> split_species(indf)
                                           2015  2100
scenario unit    table     species
sa       t / yr  Emissions CO2              1.0   2.0
                           CH4              3.0   2.0
sb       kg / yr Emissions CH4|sector|sub   1.3   2.2
         t / yr  Emissions N2O              3.4   2.1
>>> indf_funky = pd.DataFrame(
...     [
...         [1.0, 2.0],
...         [3.0, 2.0],
...         [1.3, 2.2],
...         [3.4, 2.1],
...     ],
...     columns=[2015, 2100],
...     index=pd.MultiIndex.from_tuples(
...         [
...             ("sa", "Emissions-CO2", "t / yr"),
...             ("sa", "Emissions-CO2-sector-sub sector", "t / yr"),
...             ("sb", "Emissions-CH4", "kg / yr"),
...             ("sb", "Emissions-N2O", "t / yr"),
...         ],
...         names=["scenario", "vv", "unit"],
...     ),
... )
>>> split_species(
...     indf_funky,
...     level_to_split="vv",
...     top_level="t",
...     bottom_level="b",
...     level_separator="-",
... )
                                                  2015  2100
scenario unit    t         b
sa       t / yr  Emissions CO2                     1.0   2.0
                           CO2-sector-sub sector   3.0   2.0
sb       kg / yr Emissions CH4                     1.3   2.2
         t / yr  Emissions N2O                     3.4   2.1
Source code in src/gcages/index_manipulation.py 
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
def split_species(  # noqa: PLR0913
    indf: pd.DataFrame,
    dropna: bool = True,
    level_to_split: str = "variable",
    top_level: str = "table",
    bottom_level: str = "species",
    level_separator: str = "|",
) -> pd.DataFrame:
    """
    Split the input [pd.DataFrame][pandas.DataFrame]'s level to split into species

    Any levels beyond two are all left in `bottom_level` in the output.

    This is the inverse of [combine_species][(m).].

    Parameters
    ----------
    indf
        Input data

    dropna
        Should levels which have NaNs after splitting be dropped?

    level_to_split
        The level to split

    top_level
        Name of the top level after the split

    bottom_level
        Name of the bottom level after the split

    level_separator
        Separator between levels in `level_to_split`

    Returns
    -------
    :
        `indf` with `level_to_split` split into two levels
        with the given names

    Examples
    --------
    >>> indf = pd.DataFrame(
    ...     [
    ...         [1.0, 2.0],
    ...         [3.0, 2.0],
    ...         [1.3, 2.2],
    ...         [3.4, 2.1],
    ...     ],
    ...     columns=[2015, 2100],
    ...     index=pd.MultiIndex.from_tuples(
    ...         [
    ...             ("sa", "Emissions|CO2", "t / yr"),
    ...             ("sa", "Emissions|CH4", "t / yr"),
    ...             ("sb", "Emissions|CH4|sector|sub", "kg / yr"),
    ...             ("sb", "Emissions|N2O", "t / yr"),
    ...         ],
    ...         names=["scenario", "variable", "unit"],
    ...     ),
    ... )
    >>> split_species(indf)  # doctest: +NORMALIZE_WHITESPACE
                                               2015  2100
    scenario unit    table     species
    sa       t / yr  Emissions CO2              1.0   2.0
                               CH4              3.0   2.0
    sb       kg / yr Emissions CH4|sector|sub   1.3   2.2
             t / yr  Emissions N2O              3.4   2.1
    >>> indf_funky = pd.DataFrame(
    ...     [
    ...         [1.0, 2.0],
    ...         [3.0, 2.0],
    ...         [1.3, 2.2],
    ...         [3.4, 2.1],
    ...     ],
    ...     columns=[2015, 2100],
    ...     index=pd.MultiIndex.from_tuples(
    ...         [
    ...             ("sa", "Emissions-CO2", "t / yr"),
    ...             ("sa", "Emissions-CO2-sector-sub sector", "t / yr"),
    ...             ("sb", "Emissions-CH4", "kg / yr"),
    ...             ("sb", "Emissions-N2O", "t / yr"),
    ...         ],
    ...         names=["scenario", "vv", "unit"],
    ...     ),
    ... )
    >>> split_species(
    ...     indf_funky,
    ...     level_to_split="vv",
    ...     top_level="t",
    ...     bottom_level="b",
    ...     level_separator="-",
    ... )  # doctest: +NORMALIZE_WHITESPACE
                                                      2015  2100
    scenario unit    t         b
    sa       t / yr  Emissions CO2                     1.0   2.0
                               CO2-sector-sub sector   3.0   2.0
    sb       kg / yr Emissions CH4                     1.3   2.2
             t / yr  Emissions N2O                     3.4   2.1
    """
    try:
        from pandas_indexing.core import extractlevel  # noqa: PLC0415
    except ImportError as exc:
        raise MissingOptionalDependencyError(
            "split_species", requirement="pandas_indexing"
        ) from exc

    kwargs = {
        level_to_split: level_separator.join(
            ["{" + f"{level}" + "}" for level in [top_level, bottom_level]]
        )
    }

    return extractlevel(indf, dropna=dropna, **kwargs)  # type: ignore