U
|
¬ý°dG ã @ sö d dl mZ d dlmZ d dlZd dlmZmZ d dlZ d dl
|
m Z d dl m Z d dlmZmZmZmZ d dlmZ d d lmZ d d
|
lmZ d d lmZmZ d d l m Z d dddddddddZ d dddddddddZ d ddddddd Z dS ) é )Ú annotations)Ú defaultdictN)ÚHashableÚIterable)ÚIntIndex)ÚNpDtype)Úis_integer_dtypeÚ is_list_likeÚis_object_dtypeÚ pandas_dtype)Ú SparseArray)Úfactorize_from_iterable)Ú DataFrame)ÚIndexÚ default_index)ÚSeriesÚ_Fz$str | Iterable[str] | dict[str, str]ÚboolzNpDtype | Noner )Ú
|
prefix_sepÚdummy_naÚsparseÚ
|
drop_firstÚdtypeÚreturnc
|
s ddl m} dddg} t| trv|dkr8| j| d nt|sJtdn| | fd d
|
}
|
|
|
d |
|
d ttrt g¡tt
|
r¦fd d j D dkr´ j ttrÌt g¡n tt
|
rêfdd j D j | j krüg } n*|dk r| j |ddg} n| j| dg} t ¡ D ]0\} } }t| d | |||||d}| |¡ q6|| dd}nt| ||||d}|S )a£
|
Convert categorical variable into dummy/indicator variables.
|
|
Each variable is converted in as many 0/1 variables as there are different
|
values. Columns in the output are each named after a value; if the input is
|
a DataFrame, the name of the original variable is prepended to the value.
|
|
Parameters
|
----------
|
data : array-like, Series, or DataFrame
|
Data of which to get dummy indicators.
|
prefix : str, list of str, or dict of str, default None
|
String to append DataFrame column names.
|
Pass a list with length equal to the number of columns
|
when calling get_dummies on a DataFrame. Alternatively, `prefix`
|
can be a dictionary mapping column names to prefixes.
|
prefix_sep : str, default '_'
|
If appending prefix, separator/delimiter to use. Or pass a
|
list or dictionary as with `prefix`.
|
dummy_na : bool, default False
|
Add a column to indicate NaNs, if False NaNs are ignored.
|
columns : list-like, default None
|
Column names in the DataFrame to be encoded.
|
If `columns` is None then all the columns with
|
`object`, `string`, or `category` dtype will be converted.
|
sparse : bool, default False
|
Whether the dummy-encoded columns should be backed by
|
a :class:`SparseArray` (True) or a regular NumPy array (False).
|
drop_first : bool, default False
|
Whether to get k-1 dummies out of k categorical levels by removing the
|
first level.
|
dtype : dtype, default bool
|
Data type for new columns. Only a single dtype is allowed.
|
|
Returns
|
-------
|
DataFrame
|
Dummy-coded data. If `data` contains other columns than the
|
dummy-coded one(s), these will be prepended, unaltered, to the result.
|
|
See Also
|
--------
|
Series.str.get_dummies : Convert Series of strings to dummy codes.
|
:func:`~pandas.from_dummies` : Convert dummy codes to categorical ``DataFrame``.
|
|
Notes
|
-----
|
Reference :ref:`the user guide <reshaping.dummies>` for more examples.
|
|
Examples
|
--------
|
>>> s = pd.Series(list('abca'))
|
|
>>> pd.get_dummies(s)
|
a b c
|
0 True False False
|
1 False True False
|
2 False False True
|
3 True False False
|
|
>>> s1 = ['a', 'b', np.nan]
|
|
>>> pd.get_dummies(s1)
|
a b
|
0 True False
|
1 False True
|
2 False False
|
|
>>> pd.get_dummies(s1, dummy_na=True)
|
a b NaN
|
0 True False False
|
1 False True False
|
2 False False True
|
|
>>> df = pd.DataFrame({'A': ['a', 'b', 'a'], 'B': ['b', 'a', 'c'],
|
... 'C': [1, 2, 3]})
|
|
>>> pd.get_dummies(df, prefix=['col1', 'col2'])
|
C col1_a col1_b col2_a col2_b col2_c
|
0 1 True False False True False
|
1 2 False True True False False
|
2 3 True False False False True
|
|
>>> pd.get_dummies(pd.Series(list('abcaa')))
|
a b c
|
0 True False False
|
1 False True False
|
2 False False True
|
3 True False False
|
4 True False False
|
|
>>> pd.get_dummies(pd.Series(list('abcaa')), drop_first=True)
|
b c
|
0 False False
|
1 True False
|
2 False True
|
3 False False
|
4 False False
|
|
>>> pd.get_dummies(pd.Series(list('abc')), dtype=float)
|
a b c
|
0 1.0 0.0 0.0
|
1 0.0 1.0 0.0
|
2 0.0 0.0 1.0
|
r ©ÚconcatÚobjectÚstringÚcategoryN)Úincludez1Input must be a list-like for parameter `columns`c sH t | rDt| jd ksDd| dt| d jd d}t|d S )Né z Length of 'z' (ú9) did not match the length of the columns being encoded (z).)r ÚlenÚshapeÚ
|
ValueError)ÚitemÚnameÚlen_msg)Údata_to_encode© úSd:\z\workplace\vscode\pyvenv\venv\Lib\site-packages\pandas/core/reshape/encoding.pyÚ check_len¡ s
|
ÿz get_dummies.<locals>.check_lenÚprefixr c s g | ] } | qS r) r) ©Ú.0Úcol)r, r) r* Ú
|
<listcomp>± s z get_dummies.<locals>.<listcomp>c s g | ] } | qS r) r) r- )r r) r* r0 º s r ©Úaxis)Úexclude)r, r r r r r )r r r )Úpandas.core.reshape.concatr Ú
|
isinstancer Z select_dtypesr Ú TypeErrorÚstrÚ itertoolsÚcycleÚdictÚcolumnsr# ZdropÚzipÚitemsÚ_get_dummies_1dÚappend)Údatar, r r r; r r r r Zdtypes_to_encoder+ Z with_dummiesr/ ÚpreÚsepÚdummyÚresultr) )r( r, r r* Ú get_dummies s` s
|
|
|
|
|
|
|
|
|
|
ù ù rE c s ddl m} tt| dd\}} |d kr2t t¡}t|}
|
t|
|
rJt ddddd } |spt
|
| dkrp| | S | ¡ }|rt
|
| ||d
|
k< | t
|
| tj ¡} |r¶t
|
| d kr¶| | S t
|
| } d krÌ| } nt fd d | D } t| trö| j}nd }|r
|
t|rd}n|t t¡kr&d}nd}g }t
|
| }dd tt
|
| D }|d
|
k}|| }t |¡| }t||D ]\}}|| |¡ qt|r¬|d d
}| d d
} t| |D ]D\}}ttjt
|
||dt||||d}| t|||dd¡ q¶||d ddS t|
|
tjr |
|
}ntj}tj| |dj|d dj }|sPd||d
|
k< |rv|d d
d d
f }| d d
} t ||| |
|
dS d S )Nr r F©Úcopyz1dtype=object is not a valid dtype for get_dummiesr )r c S s( t | tr| j}n tt| }t|dS )N)Úindex)r5 r rH r r" r )r@ rH r) r) r* Úget_empty_frameø s
|
z(_get_dummies_1d.<locals>.get_empty_frameéÿÿÿÿr c s g | ]} | qS r) r) )r. Úlevel©r, r r) r* r0 s z#_get_dummies_1d.<locals>.<listcomp>g c S s g | ]}g qS r) r) )r. r r) r) r* r0 % s ©r )Z sparse_indexÚ
|
fill_valuer )r@ rH r& rG )r2 rG r1 )rH r; r ) r4 r r r Únpr r r r
|
r$ r" rG ÚinsertÚnanr r5 rH r ÚrangeZaranger< r? r Zonesr Zbool_ZeyeZtakeÚTr ) r@ r, r r r r r r ÚcodesÚlevelsZ_dtyperI Znumber_of_colsZ
|
dummy_colsrH rN Z sparse_seriesÚNZ
|
sp_indicesÚmaskZn_idxZndxÚcoder/ ZixsZsarrZ eye_dtypeZ dummy_matr) rL r* r> ã sv
|
|
|
ü r> z
|
None | strz%None | Hashable | dict[str, Hashable])r@ rB Údefault_categoryr c s® ddl m} t| ts*tdt| j | ¡ ¡ ¡ rVt d| ¡ ¡
|
¡ dz| j ddd}W n tk
|
r td Y nX t t }d
|
kr¦t | j|d < nfttrø|jD ]>}| ¡d t t|kræt d | | |¡ q¶ntd tj |d
|
k rt|trXt|t|ksdt| dt| d}t |n:t|tr~tt||gt| }ntdt|j i }| ¡ D ]\ } d
|
kr¼| ¡ }
|
n fdd| D }
|
|jd
|
d
|
| f jdd} t| dkr
|
t d|
|
¡ t| dkrjt|tr4|
|
| ¡ nt d| ¡ ||jd
|
d
|
| f | dkfdd} n|jd
|
d
|
| f } tj |
|
dd} | | ¡ ¡ d | < qt|S )a>
|
Create a categorical ``DataFrame`` from a ``DataFrame`` of dummy variables.
|
|
Inverts the operation performed by :func:`~pandas.get_dummies`.
|
|
.. versionadded:: 1.5.0
|
|
Parameters
|
----------
|
data : DataFrame
|
Data which contains dummy-coded variables in form of integer columns of
|
1's and 0's.
|
sep : str, default None
|
Separator used in the column names of the dummy categories they are
|
character indicating the separation of the categorical names from the prefixes.
|
For example, if your column names are 'prefix_A' and 'prefix_B',
|
you can strip the underscore by specifying sep='_'.
|
default_category : None, Hashable or dict of Hashables, default None
|
The default category is the implied category when a value has none of the
|
listed categories specified with a one, i.e. if all dummies in a row are
|
zero. Can be a single value for all variables or a dict directly mapping
|
the default categories to a prefix of a variable.
|
|
Returns
|
-------
|
DataFrame
|
Categorical data decoded from the dummy input-data.
|
|
Raises
|
------
|
ValueError
|
* When the input ``DataFrame`` ``data`` contains NA values.
|
* When the input ``DataFrame`` ``data`` contains column names with separators
|
that do not match the separator specified with ``sep``.
|
* When a ``dict`` passed to ``default_category`` does not include an implied
|
category for each prefix.
|
* When a value in ``data`` has more than one category assigned to it.
|
* When ``default_category=None`` and a value in ``data`` has no category
|
assigned to it.
|
TypeError
|
* When the input ``data`` is not of type ``DataFrame``.
|
* When the input ``DataFrame`` ``data`` contains non-dummy data.
|
* When the passed ``sep`` is of a wrong data type.
|
* When the passed ``default_category`` is of a wrong data type.
|
|
See Also
|
--------
|
:func:`~pandas.get_dummies` : Convert ``Series`` or ``DataFrame`` to dummy codes.
|
:class:`~pandas.Categorical` : Represent a categorical variable in classic.
|
|
Notes
|
-----
|
The columns of the passed dummy data should only include 1's and 0's,
|
or boolean values.
|
|
Examples
|
--------
|
>>> df = pd.DataFrame({"a": [1, 0, 0, 1], "b": [0, 1, 0, 0],
|
... "c": [0, 0, 1, 0]})
|
|
>>> df
|
a b c
|
0 1 0 0
|
1 0 1 0
|
2 0 0 1
|
3 1 0 0
|
|
>>> pd.from_dummies(df)
|
0 a
|
1 b
|
2 c
|
3 a
|
|
>>> df = pd.DataFrame({"col1_a": [1, 0, 1], "col1_b": [0, 1, 0],
|
... "col2_a": [0, 1, 0], "col2_b": [1, 0, 0],
|
... "col2_c": [0, 0, 1]})
|
|
>>> df
|
col1_a col1_b col2_a col2_b col2_c
|
0 1 0 0 1 0
|
1 0 1 1 0 0
|
2 1 0 0 0 1
|
|
>>> pd.from_dummies(df, sep="_")
|
col1 col2
|
0 a b
|
1 b a
|
2 a c
|
|
>>> df = pd.DataFrame({"col1_a": [1, 0, 0], "col1_b": [0, 1, 0],
|
... "col2_a": [0, 1, 0], "col2_b": [1, 0, 0],
|
... "col2_c": [0, 0, 0]})
|
|
>>> df
|
col1_a col1_b col2_a col2_b col2_c
|
0 1 0 0 1 0
|
1 0 1 1 0 0
|
2 0 0 0 0 0
|
|
>>> pd.from_dummies(df, sep="_", default_category={"col1": "d", "col2": "e"})
|
col1 col2
|
0 a b
|
1 b a
|
2 d e
|
r r z>Expected 'data' to be a 'DataFrame'; Received 'data' of type: z.Dummy DataFrame contains NA value in column: 'ú'ÚbooleanFrF z(Passed DataFrame contains non-dummy dataNÚ z$Separator not specified for column: zFExpected 'sep' to be of type 'str' or 'None'; Received 'sep' of type: z Length of 'default_category' (r! ú)znExpected 'default_category' to be of type 'None', 'Hashable', or 'dict'; Received 'default_category' of type: c s g | ]}|t d
qS )N)r" r- ©r, rB r) r* r0 ý s z from_dummies.<locals>.<listcomp>r r1 zEDummy DataFrame contains multi-assignment(s); First instance in row: zEDummy DataFrame contains unassigned value(s); First instance in row: r rM ) r4 r r5 r r6 ÚtypeÚ__name__ZisnaÚanyr$ ZidxmaxZastyper Úlistr; r7 Úsplitr" r? r: r r< r= rG ÚlocÚsumZidxminrO ÚarrayZto_numpyZnonzero)r@ rB rY r Zdata_to_decodeZvariables_slicer/ r' Zcat_dataZ prefix_sliceZcatsÚassignedZ
|
data_sliceZ
|
cats_arrayr) r^ r* Ú from_dummiesQ s| n
|
ÿÿ
|
|
ÿ
|
ÿ
|
ÿÿ
|
|
ÿ ÿ ÿ rh )Nr FNFFN)r FFFN)NN)!Ú
|
__future__r Ú collectionsr r8 Útypingr r ÚnumpyrO Zpandas._libs.sparser Zpandas._typingr Zpandas.core.dtypes.commonr r r
|
r Zpandas.core.arraysr Z pandas.core.arrays.categoricalr Zpandas.core.framer Zpandas.core.indexes.apir r Zpandas.core.seriesr rE r> rh r) r) r) r* Ú<module> s< ø G ùp ý
|
