:iBSSKrSSKJr SSKrSSKJrJrJr SSK J r SSK J r J r Jr SSKJr SSKJr SS KJrJrJrJr S S KJr "S S \\5rg)N)Integral) BaseEstimatorTransformerMixin _fit_context)resample)IntervalOptions StrOptions)"_deprecate_Xt_in_inverse_transform)_weighted_percentile)_check_feature_names_in_check_sample_weight check_arraycheck_is_fitted) OneHotEncoderc \rSrSr%Sr\"\SSSS9S/\"1Sk5/\"1S k5/\"\ \ R\ R15S/\"\S SSS9S/S /S .r \\S 'SSSSSSS.Sjjr\"SS9SSj5rSrSrSSS.SjjrSSjrSrg)KBinsDiscretizeraN Bin continuous data into intervals. Read more in the :ref:`User Guide `. .. versionadded:: 0.20 Parameters ---------- n_bins : int or array-like of shape (n_features,), default=5 The number of bins to produce. Raises ValueError if ``n_bins < 2``. encode : {'onehot', 'onehot-dense', 'ordinal'}, default='onehot' Method used to encode the transformed result. - 'onehot': Encode the transformed result with one-hot encoding and return a sparse matrix. Ignored features are always stacked to the right. - 'onehot-dense': Encode the transformed result with one-hot encoding and return a dense array. Ignored features are always stacked to the right. - 'ordinal': Return the bin identifier encoded as an integer value. strategy : {'uniform', 'quantile', 'kmeans'}, default='quantile' Strategy used to define the widths of the bins. - 'uniform': All bins in each feature have identical widths. - 'quantile': All bins in each feature have the same number of points. - 'kmeans': Values in each bin have the same nearest center of a 1D k-means cluster. For an example of the different strategies see: :ref:`sphx_glr_auto_examples_preprocessing_plot_discretization_strategies.py`. dtype : {np.float32, np.float64}, default=None The desired data-type for the output. If None, output dtype is consistent with input dtype. Only np.float32 and np.float64 are supported. .. versionadded:: 0.24 subsample : int or None, default=200_000 Maximum number of samples, used to fit the model, for computational efficiency. `subsample=None` means that all the training samples are used when computing the quantiles that determine the binning thresholds. Since quantile computation relies on sorting each column of `X` and that sorting has an `n log(n)` time complexity, it is recommended to use subsampling on datasets with a very large number of samples. .. versionchanged:: 1.3 The default value of `subsample` changed from `None` to `200_000` when `strategy="quantile"`. .. versionchanged:: 1.5 The default value of `subsample` changed from `None` to `200_000` when `strategy="uniform"` or `strategy="kmeans"`. random_state : int, RandomState instance or None, default=None Determines random number generation for subsampling. Pass an int for reproducible results across multiple function calls. See the `subsample` parameter for more details. See :term:`Glossary `. .. versionadded:: 1.1 Attributes ---------- bin_edges_ : ndarray of ndarray of shape (n_features,) The edges of each bin. Contain arrays of varying shapes ``(n_bins_, )`` Ignored features will have empty arrays. n_bins_ : ndarray of shape (n_features,), dtype=np.int64 Number of bins per feature. Bins whose width are too small (i.e., <= 1e-8) are removed with a warning. n_features_in_ : int Number of features seen during :term:`fit`. .. versionadded:: 0.24 feature_names_in_ : ndarray of shape (`n_features_in_`,) Names of features seen during :term:`fit`. Defined only when `X` has feature names that are all strings. .. versionadded:: 1.0 See Also -------- Binarizer : Class used to bin values as ``0`` or ``1`` based on a parameter ``threshold``. Notes ----- For a visualization of discretization on different datasets refer to :ref:`sphx_glr_auto_examples_preprocessing_plot_discretization_classification.py`. On the effect of discretization on linear models see: :ref:`sphx_glr_auto_examples_preprocessing_plot_discretization.py`. In bin edges for feature ``i``, the first and last values are used only for ``inverse_transform``. During transform, bin edges are extended to:: np.concatenate([-np.inf, bin_edges_[i][1:-1], np.inf]) You can combine ``KBinsDiscretizer`` with :class:`~sklearn.compose.ColumnTransformer` if you only want to preprocess part of the features. ``KBinsDiscretizer`` might produce constant features (e.g., when ``encode = 'onehot'`` and certain bins do not contain any data). These features can be removed with feature selection algorithms (e.g., :class:`~sklearn.feature_selection.VarianceThreshold`). Examples -------- >>> from sklearn.preprocessing import KBinsDiscretizer >>> X = [[-2, 1, -4, -1], ... [-1, 2, -3, -0.5], ... [ 0, 3, -2, 0.5], ... [ 1, 4, -1, 2]] >>> est = KBinsDiscretizer( ... n_bins=3, encode='ordinal', strategy='uniform' ... ) >>> est.fit(X) KBinsDiscretizer(...) >>> Xt = est.transform(X) >>> Xt # doctest: +SKIP array([[ 0., 0., 0., 0.], [ 1., 1., 1., 0.], [ 2., 2., 2., 1.], [ 2., 2., 2., 2.]]) Sometimes it may be useful to convert the data back into the original feature space. The ``inverse_transform`` function converts the binned data into the original feature space. Each value will be equal to the mean of the two bin edges. >>> est.bin_edges_[0] array([-2., -1., 0., 1.]) >>> est.inverse_transform(Xt) array([[-1.5, 1.5, -3.5, -0.5], [-0.5, 2.5, -2.5, -0.5], [ 0.5, 3.5, -1.5, 0.5], [ 0.5, 3.5, -1.5, 1.5]]) rNleft)closedz array-like>onehotordinal onehot-dense>kmeansuniformquantiler random_staten_binsencodestrategydtype subsampler_parameter_constraintsrri@ )r"r#r$r%rcLXlX lX0lX@lXPlX`lgNr )selfr!r"r#r$r%rs h/srv/projetos/modelo_ml_acdoc/venv/lib/python3.13/site-packages/sklearn/preprocessing/_discretization.py__init__KBinsDiscretizer.__init__s#    "(T)prefer_skip_nested_validationc URUSS9nUR[R[R4;a URnO URnUR upVUb*UR S:Xa[SUR <S35eURb/XPR:a [USURURS9nUR S nURU5nUb[X1URS9n[R"U[S9n[U5GHn USS2U 4n U R!5U R#5pX:XaV[$R&"S U -5 S Xy'[R("[R**[R*/5X'MUR S:Xa [R,"XXyS -5X'GOQUR S :Xa[R,"S S XyS -5n Uc-[R."[R0"X55X'O[R."U Vs/sHn[3XU5PM sn[RS9X'OUR S:XaSSKJn [R,"XXyS -5nUS SUSS-SS2S4S-nU"XyUS S9nUR9U SS2S4US9R:SS2S 4nUR=5 US SUSS-S-X'[R>XU U 4X'UR S;dGM[R@"X[R*S9S:nXUX'[CX5S - Xy:wdGMe[$R&"SU -5 [CX5S - Xy'GM Xl"Xpl#SURH;a[KURFVs/sHn[RL"U5PM snURHS:HUS9Ul'URNR9[R"S [CURF5455 U$s snfs snf)a Fit the estimator. Parameters ---------- X : array-like of shape (n_samples, n_features) Data to be discretized. y : None Ignored. This parameter exists only for compatibility with :class:`~sklearn.pipeline.Pipeline`. sample_weight : ndarray of shape (n_samples,) Contains weight values to be associated with each sample. Cannot be used when `strategy` is set to `"uniform"`. .. versionadded:: 1.3 Returns ------- self : object Returns the instance itself. numericr$NrzY`sample_weight` was provided but it cannot be used with strategy='uniform'. Got strategy=z instead.F)replace n_samplesrrz3Feature %d is constant and will be replaced with 0.rrdrr)KMeans?) n_clustersinitn_init) sample_weight)rr)to_beging:0yE>zqBins whose width are too small (i.e., <= 1e-8) in feature %d are removed. Consider decreasing the number of bins.r) categories sparse_outputr$)(_validate_datar$npfloat64float32shaper# ValueErrorr%rr_validate_n_binsrzerosobjectrangeminmaxwarningswarnarrayinflinspaceasarray percentiler clusterr5fitcluster_centers_sortr_ediff1dlen bin_edges_n_bins_r"rarange_encoder)r)Xyr; output_dtyper3 n_featuresr! bin_edgesjjcolumncol_mincol_max quantilesqr5 uniform_edgesr9kmcentersmaskis r*rSKBinsDiscretizer.fits2     3 ::"**bjj1 1::L77L !  $))C>==#9.  >> %)nn*D..!.. AWWQZ &&z2  $0QMHHZv6  #Bq"uXF%zz|VZZ\W! IBN "266'266): ; }} ) " Gfj1n M *,KK3 Q?  ($&JJr}}V/O$PIM$&JJ&/%.1J%.!jj %IM(*,!# Gfj1n M %ab)M#2,>>4H3NvzQG&&1d7O=!""1a4) !(ws|!;s B "g}g&E F }} 66zz)-"&&ADH ) d 3 y}%)VZ7MM9;=> "%Y]!3a!7FJm$p$ t{{ ")26,,?,QBIIaL,?"kkX5"DM MM  bhh3t||+<'=> ? aP@s Q- . Q2cURn[U[5(a[R"X[ S9$[ U[ SSS9nURS:dURSU:wa [S5eUS:X2:g-n[R"U5SnURSS:aAS RS U55n[S R[RU55eU$) z0Returns n_bins_, the number of bins per feature.r1TF)r$copy ensure_2drrz8n_bins must be a scalar or array of shape (n_features,).rz, c38# UHn[U5v M g7fr()str).0rls r* 4KBinsDiscretizer._validate_n_bins..XsB0A1A0Aszk{} received an invalid number of bins at indices {}. Number of bins must be at least 2, and must be an int.)r! isinstancerr@fullintrndimrCrDwherejoinformatr__name__)r)r` orig_binsr!bad_nbins_valueviolating_indicesindicess r*rE!KBinsDiscretizer._validate_n_binsIsKK i * *77:< <YcN ;;?fll1o;WX X!A:&*=>HH_5a8  " "1 % )iiB0ABBG::@&$--w;  r-c[U5 URc [R[R4O URnUR USUSS9nUR n[URS5H,n[R"XESSUSS2U4SS9USS2U4'M. URS :XaU$SnS UR;a1URRnURURlURRU5nX`RlU$!X`Rlf=f) a3 Discretize the data. Parameters ---------- X : array-like of shape (n_samples, n_features) Data to be discretized. Returns ------- Xt : {ndarray, sparse matrix}, dtype={np.float32, np.float64} Data in the binned space. Will be a sparse matrix if `self.encode='onehot'` and ndarray otherwise. NTF)ror$resetrr6right)siderr) rr$r@rArBr?rYrHrC searchsortedr"r\ transform)r)r]r$Xtrarb dtype_initXt_encs r*rKBinsDiscretizer.transformbs -1JJ,>RZZ(DJJ  U% HOO  $B a(;R2YWUBq"uI% ;;) #I t{{ ",,J"$((DMM  -]],,R0F#-MM  #-MM s D..E)rc<[X5n[U5 SUR;aURR U5n[ US[ R[ R4S9nURRSnURSU:wa'[SRXCRS55e[U5HOnURUnUSSUSS-S -nXsSS2U4R[ R 5USS2U4'MQ U$) a9 Transform discretized data back to original feature space. Note that this function does not regenerate the original data due to discretization rounding. Parameters ---------- X : array-like of shape (n_samples, n_features) Transformed data in the binned space. Xt : array-like of shape (n_samples, n_features) Transformed data in the binned space. .. deprecated:: 1.5 `Xt` was deprecated in 1.5 and will be removed in 1.7. Use `X` instead. Returns ------- Xinv : ndarray, dtype={np.float32, np.float64} Data in the original feature space. rT)ror$rrz8Incorrect number of features. Expecting {}, received {}.Nr6r7)r rr"r\inverse_transformrr@rArBrZrCrDr|rHrYastypeint64)r)r]rXinvr`rbra bin_centerss r*r"KBinsDiscretizer.inverse_transforms. /q 5 t{{ " //2A14 BJJ/GH\\''* ::a=J &JQQ 1    #B+I$QR=9Sb>9S@K%ArE{&:&:288&DEDBK$  r-c[US5 [X5n[US5(aURR U5$U$)a\Get output feature names. Parameters ---------- input_features : array-like of str or None, default=None Input features. - If `input_features` is `None`, then `feature_names_in_` is used as feature names in. If `feature_names_in_` is not defined, then the following input feature names are generated: `["x0", "x1", ..., "x(n_features_in_ - 1)"]`. - If `input_features` is an array-like, then `input_features` must match `feature_names_in_` if `feature_names_in_` is defined. Returns ------- feature_names_out : ndarray of str objects Transformed feature names. n_features_in_r\)rrhasattrr\get_feature_names_out)r)input_featuress r*r&KBinsDiscretizer.get_feature_names_outsC( ./0F 4 $ $==66~F Fr-) r\rYr$r"r!rZrr#r%))NNr()r} __module__ __qualname____firstlineno____doc__r rr r typer@rArBr&dict__annotations__r+rrSrErrr__static_attributes__r-r*rrsRjHaf=|LCDE ABC$RZZ 894@xD@$G'( $D))"5}6}~2%N,d,\r-r)rKnumbersrnumpyr@baserrrutilsrutils._param_validationr r r utils.deprecationr utils.statsr utils.validationrrrr _encodersrrrr-r*rsE@@CCB. %w'wr-