:i6Z v % S SK Jr S SKrS SKJrJrJrJr S SKJ r S SK
r S SK r
S SKrS SKr\( a S SKJr SrS\S' SSS jjrSSS jjrSS S
jjrSS S jjrSSS jjrSSS
jjr\S S S jj5 r \S S S jj5 r S!S"S jjr S!S#S jjr S!S#S jjr S$S%S jjr S$S%S jjr SS&S jjr!S'S jr"SS(S jjr#g)) ) annotationsN)
TYPE_CHECKINGFinalLiteraloverload) urlretrievez-https://github.com/shap/shap/raw/master/data/z
Final[str]github_data_urlc d [ S- n[ R " [ U U SU S35 5 R [ R
5 n[ R " [ U S35 5 nUb< [ R R X1SS9n[ R R XASS9nX44$ )aG Return a set of 50 images representative of ImageNet images.
Parameters
----------
resolution : int
The resolution of the images. At present, the only supported value is 224.
n_points : int, optional
Number of data points to sample. If None, the entire dataset is used.
Returns
-------
X : np.ndarray
Represents images from ImageNet of a certain resolution.
y : np.ndarray
The target variables, that is, the ImageNet classes.
Notes
-----
This dataset was collected by randomly finding a working ImageNet link and then pasting the
original ImageNet image into Google image search restricted to images licensed for reuse. A
similar image (now with rights to reuse) was downloaded as a rough replacement for the original
ImageNet image. The point is to have a random sample of ImageNet for use as a background
distribution for explaining models trained on ImageNet data.
Note that because the images are only rough replacements, the labels might no longer be correct.
Examples
--------
To get the processed images and labels::
images, labels = shap.datasets.imagenet50()
imagenet50_xz.npyz
labels.csvr random_state)
r nploadcacheastypefloat32loadtxtshaputilssample)
resolutionn_pointsprefixXys P/srv/projetos/modelo_ml_acdoc/venv/lib/python3.13/site-packages/shap/datasets.py
imagenet50r s D }
,FGGEVHZL* T"J KLSSTVT^T^_AJJuxz%: ;
eO&667' Ja{{}
K
T"AAfuIzz xa @ JJ a : 7N
K Js B
B$c f [ R " [ [ S- 5 SS9n[ R
" [ R " [ R " UR SS2S4 5 5 5 S nU b [ R R X SS9n[ R " UR US4 [ S9nUR US S
24 n[ R
" [ R " UR 5 R S5 S:H 5 S nUR SS2U4 nXC4$ ) aa Predict the total number of violent crimes per 100K population.
This dataset is from the classic UCI Machine Learning repository:
https://archive.ics.uci.edu/ml/datasets/Communities+and+Crime+Unnormalized
Used in predictive regression tasks.
Parameters
----------
n_points : int, optional
Number of data points to sample. If provided, randomly samples the specified number of points.
Returns
-------
X : pd.DataFrame
The feature data.
y : np.ndarray
The target variable.
Examples
--------
To get the processed data and target labels::
data, target = shap.datasets.communitiesandcrime()
z CommViolPredUnnormalizedData.txt?) na_valuesNr r
r5 i)r' read_csvr r r whereinvertisnanilocr r r arrayfloatvaluessum)r raw_data
valid_indsr r
valid_colss r communitiesandcrimerN s 6 {{5 3U!UVbefH "))BHHX]]1b5-A$BCDQGJZZ&&z!&L
z2~.e50K' is True and '<=50K' is False.
- Certain categorical columns are encoded for numerical representation.
Examples
--------
To get the processed data and target labels::
data, target = shap.datasets.adult()
To get the raw data for display::
raw_data, target = shap.datasets.adult(display=True)
))Ager ) Workclasscategory)fnlwgtr ) Educationr` )z
Education-Numr )zMarital Statusr` )
Occupationr` ) Relationshipr` )Racer` )Sexr` )z Capital Gainr )z Capital Lossr )zHours per weekr )Countryr` )Targetr` z
adult.datar r> )namesr? r6 r
rb )axisc U S S; $ )Nr )rh rb rT )r s r adult.. s !4K(Kr rh z >50K rA )z
Not-in-family UnmarriedzOther-relativez Own-childHusbandWifer` rd )rb rh ra ra )r' rB r r dictr r r droplistfilterr rG stripcatcodesrI ) rV r dtypesr, rK r" filt_dtypesrcodekr6 r\ s r adultr l sh nF" {{
o ,-F5KFqdF5KWZbfgmbnH ::$$Xa$H ==+ Q= /Dv KVTUK(^w.DN a1STablm nE J N" ((dg#Fg!'')$4g#FG '++++ }} >Q}Gh I^I^^^ 99h)9 2DN4I4I II' 6L $Gs E
E"
c [ R " [ [ S- 5 SS9n[ R " [ [ S- 5 SS9S nUb< [ R
R
X!SS9n[ R
R
X1SS9nU ( a( UR 5 nU[ R " U5 4$ U[ R " U5 4$ )a Return a nicely packaged version of NHANES I data with survival times as labels.
Used in survival analysis tasks.
Parameters
----------
display : bool, optional
If True, returns the features with a modified display. Default is False.
n_points : int, optional
Number of data points to sample. Default is None (returns the entire dataset).
Returns
-------
X : pd.DataFrame
The feature data matrix. If ``display`` is True, a modified version of the features for display
is returned as ``X`` instead.
y : np.ndarray
The target variables representing survival times.
Examples
--------
Usage example::
features, survival_times = shap.datasets.nhanesi(display=True, n_points=100)
z
NHANESI_X.csvr ) index_colz
NHANESI_y.csvr r
)
r' rB r r r r r copyr rG )rV r r r X_displays r nhanesir s 6 E/O;<JA
E/O;<J3OA JJ a : JJ a :FFH "((1+%% bhhqk>r c ^ ^ [ R R 5 n[ R R S5 U Sp2[ R " U5 mSTSSS2' [ R " U5 n[ SSS5 H? nS=XEUS- 4' XES- U4' S=XEUS- 4' XES- U4' S=XES- US- 4' XES- US- 4' MA U4S jn[ R R
X#5 nXwR S5 -
n[ R " UR U5 UR S - n [ R R [ R R U 5 5 R n
[ R " XR 5 n [ R R [ R " [ R " XR 5 R 5 [ R " U5 -
5 S : d e[ R " U [ R R U5 R 5 n U n
U" U
5 [ R R
U5 S
- - n[ R R U5 [ R" " U
5 U4$ ) a Correlated Groups (60 features)
A synthetic dataset consisting of 60 features with tight correlations among distinct groups of features.
Parameters
----------
n_points : int, optional
Number of data points to generate. Default is 1,000.
Returns
-------
X : pd.DataFrame
The feature data matrix
y : np.ndarray
The target variables
Notes
-----
- The dataset is generated with known correlations among distinct groups of features.
- Each feature is a unit variance Gaussian random variable centred around 0.
- The labels are generated based on a linear function of the features with added random noise.
Examples
--------
.. code-block:: python
data, target = shap.datasets.corrgroups60()
r < rj rp gGz?ro c 2 > [ R " U T5 $ rS r matmulr betas r r; corrgroups60..f$ yyD!!r gư>{Gz?)r randomseedzeroseyerangerandnmeanr Tshapelinalgcholeskyinvnormcorrcoefr' r( )r old_seedNMCir; X_start
X_centeredSigmaWX_whiteX_finalr r r s @r corrgroups60r s
> yy~~ HIINN1 Rq 88A;DD2aL q A
1b!_$((QU( aAqk$((QU( aAqk,00a%Q,!E1q5L/
" iiooa#G<<?*J IIjllJ /*2B2B12E EE
299==/022Aii
CC(G
r{{299Z#=#?#?@266!9LMPTTT ii!3!3A!6!8!89GA !ryyq!D((A IINN8
<<?A r c ^ [ R R 5 n[ R R S5 U Sp2[ R " U5 mSTSSS2' U4S jn[ R R X#5 nXUR S5 -
nU" U5 [ R R U5 S- - n[ R R U5 [ R " U5 U4$ )a@ Independent Linear (60 features)
A synthetic dataset consisting of 60 features.
Parameters
----------
n_points : int, optional
Number of data points to generate. Default is 1,000.
Returns
-------
X : pd.DataFrame
The feature data matrix
y : np.ndarray
The target variables
Notes
-----
- Each feature is a unit variance Gaussian random variable centred around 0.
- The labels are generated based on a linear function of the features with added random noise.
Examples
--------
.. code-block:: python
features, labels = shap.datasets.independentlinear60()
r r rj r rp c 2 > [ R " U T5 $ rS r r s r r; independentlinear60..fd r r r )r r r r r r r' r( ) r r r r r; r r r r s @r independentlinear60r < s < yy~~ HIINN1 Rq 88A;DD2aL" iiooa#G,,q/!A !ryyq!D((A IINN8
<<?A r c [ R R [ [ S- 5 5 u pU b< [
R R XSS9n[
R R X SS9nX4$ )a
Return a sparse dataset in scipy csr matrix format.
Data Source: :external+scikit-learn:func:`sklearn.datasets.load_svmlight_file`
Parameters
----------
n_points : int, optional
Number of data points to sample. If None, returns the entire dataset. Default is None.
Returns
-------
X : scipy.sparse.csr_matrix
Sparse feature matrix.
y : np.ndarray
Target labels.
Examples
--------
.. code-block:: python
data, target = shap.datasets.a1a()
z a1a.svmlightr r
)r$ r% load_svmlight_filer r r r r )r r" r* s r a1ar r sf 6 ##66u_~=]7^_LDzz a @""6!"D <r c L Sn [ R R [ U S- 5 5 u p[ R R [ U S- 5 5 u p4[ R
" [ U S- 5 5 n[ R
" [ U S- 5 5 nXX4XV4$ )a Return ranking datasets from the LightGBM repository.
Used in ranking tasks.
Returns
-------
x_train : scipy.sparse.csr_matrix
Training feature matrix.
y_train : numpy.ndarray
Training labels.
x_test : scipy.sparse.csr_matrix
Testing feature matrix.
y_test : numpy.ndarray
Testing labels.
q_train : numpy.ndarray
Training query information.
q_test : numpy.ndarray
Testing query information.
Notes
-----
Data Source: LightGBM repository https://github.com/microsoft/LightGBM/tree/master/examples/lambdarank
Examples
--------
.. code-block:: python
x_train, y_train, x_test, y_test, q_train, q_test = shap.datasets.rank()
zPhttps://raw.githubusercontent.com/Microsoft/LightGBM/master/examples/lambdarank/z
rank.trainz rank.testzrank.train.queryzrank.test.query)r$ r% r r r r )
rank_data_urlx_trainy_trainx_testy_testq_trainq_tests r rankr s > gM ''::5 Q]A];^_G %%88}{?Z9[\NFjj}/A ABCG
ZZm.? ?@
AF VW <>) $ $C# r ) N)r intr
int | Nonereturnz tuple[np.ndarray, np.ndarray]rS )r r r tuple[pd.DataFrame, np.ndarray])r r r z!tuple[pd.DataFrame, pd.DataFrame])r r r z tuple[list[str], np.ndarray])..)rV zLiteral[False]r r r r )rV z
Literal[True]r r r z tuple[pd.DataFrame, list[str]])FN)rV r: r r r z+tuple[pd.DataFrame, np.ndarray | list[str]])rV r: r r r r )i )r r r r )r r r z!tuple[ssp.csr_matrix, np.ndarray])r zUtuple[ssp.csr_matrix, np.ndarray, ssp.csr_matrix, np.ndarray, np.ndarray, np.ndarray])r r[ r z
str | Noner r[ )$
__future__r r typingr r r r urllib.requestr numpyr pandasr' sklearn.datasetsr$ r scipy.sparsesparsesspr __annotations__r r. r2 r< rN rQ rW r r r r r r r rT r r r s " : : & M M*Z3l+\(V*Z6r
k
k i
i.b\J~&RE P3 l!H%=P r