0Ph*BddlZddlmZddlZddlmZmZmZddl m Z ddl m Z m Z mZddlmZddlmZdd lmZmZmZmZmZd d lmZGd d eeZdS)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 validate_data) OneHotEncoderc 4eZdZUdZeeddddgehdgehdgeee j e j hdgeed dddgd gd Z e ed < ddddddddZedddZdZdZddddZddZdS)KBinsDiscretizera 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> onehot-denseonehotordinal>kmeansuniformquantiler random_staten_binsencodestrategydtype subsampler _parameter_constraintsrri@ )r#r$r%r&r cZ||_||_||_||_||_||_dSNr!)selfr"r#r$r%r&r s e/var/www/html/test/jupyter/venv/lib/python3.11/site-packages/sklearn/preprocessing/_discretization.py__init__zKBinsDiscretizer.__init__s5     "(T)prefer_skip_nested_validationct||d}|jtjtjfvr|j}n|j}|j\}}#|jdkrtd|jd|j(||jkrt|d|j|j }|jd }| |}t||jtj |t}t|D]} |dd| f} } | | krKt%jd | zd || <tjtj tjg|| <|jdkr$tj| | || d z|| <nl|jd kr~tjd d || d z} ,tjtj| || <ntjfd| Dtj|| <n|jdkrddlm} tj| | || d z}|d d|ddzdddfdz}| || |d }|dddfjddd f}||d d|ddzdz|| <tj| || | f|| <|jdvrtj|| tjdk}|| ||| <tA|| d z || kr2t%jd| ztA|| d z || <||_!||_"d|j#vrotId|j"D|j#dk||_%|j%tj d tA|j"f|S)as Fit the estimator. Parameters ---------- X : array-like of shape (n_samples, n_features) Data to be discretized. y : None Ignored. This parameter exists only for compatibility with :class:`~sklearn.pipeline.Pipeline`. sample_weight : ndarray of shape (n_samples,) Contains weight values to be associated with each sample. Cannot be used when `strategy` is set to `"uniform"`. .. versionadded:: 1.3 Returns ------- self : object Returns the instance itself. numericr%NrzY`sample_weight` was provided but it cannot be used with strategy='uniform'. Got strategy=z instead.F)replace n_samplesr rz3Feature %d is constant and will be replaced with 0.rrdc2g|]}t|Sr ).0qcolumn sample_weights r, z(KBinsDiscretizer.fit..s5 !1JJr.rr)KMeans?) n_clustersinitn_init)r;)rr)to_beging:0yE>zqBins whose width are too small (i.e., <= 1e-8) in feature %d are removed. Consider decreasing the number of bins.rc6g|]}tj|Sr7)nparanger8is r,r<z(KBinsDiscretizer.fit..>s ???QBIaLL???r.) categories sparse_outputr%)&rr%rEfloat64float32shaper$ ValueErrorr&rr _validate_n_binsrzerosobjectrangeminmaxwarningswarnarrayinflinspaceasarray percentileclusterr=fitcluster_centers_sortr_ediff1dlen bin_edges_n_bins_r#r_encoder)r+Xyr; output_dtyper4 n_featuresr" bin_edgesjjcol_mincol_max quantilesr= uniform_edgesrAkmcentersmaskr:s ` @r,r]zKBinsDiscretizer.fits2 $ 3 3 3 :"*bj1 1 1:LL7L ! :  $))C)C.=...  > %)dn*D*D.!. AWQZ &&z22  $0QQQMHZv666  ##6 86 8Bqqq"uXF%zz||VZZ\\WG'!! IBNr "26'26): ; ; " } )) " GWfRj1n M M " *,,K3r Q??  ($&Jr}VY/O/O$P$PIbMM$&J%.!j %%%IbMM(**,,,,,,!# GWfRj1n M M %abb)M#2#,>>4H3NVvbzQGGG&&111d7O=!"111a4) !(wss|!;s B " "gy}g&E F " } 666z)B-"&AAADH )" d 3 " y}%%)VBZ77M9;=> "%Yr]!3!3a!7F2J# t{ " ")??$,???"kX5"DM M  bh3t|+<+<'=>> ? ? ? r.c|j}t|trtj||t St |t dd}|jdks|jd|krtd|dk||kz}tj |d}|jddkrLd d |D}td tj||S) z0Returns n_bins_, the number of bins per feature.r2TF)r%copy ensure_2drrz8n_bins must be a scalar or array of shape (n_features,).rz, c34K|]}t|VdSr*)strrGs r, z4KBinsDiscretizer._validate_n_bins..Ws(BB1ABBBBBBr.zk{} received an invalid number of bins at indices {}. Number of bins must be at least 2, and must be an int.)r" isinstancerrEfullintrndimrMrNwherejoinformatr__name__)r+ri orig_binsr"bad_nbins_valueviolating_indicesindicess r,rOz!KBinsDiscretizer._validate_n_binsHsK i * * =7:y<<< <YcNNN ;??fl1o;;WXX X!A:&I*=>H_55a8  "1 % ) )iiBB0ABBBBBG::@&$-w;;  r.c(t||jtjtjfn|j}t ||d|d}|j}t|jdD]8}tj ||dd|dd|fd|dd|f<9|j d kr|Sd}d |j vr|j j}|j|j _ |j |}||j _n#||j _wxYw|S) a 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)rtr%resetrr>right)siderr) rr%rErKrLrrcrRrM searchsortedr#re transform)r+rfr%Xtrjrk dtype_initXt_encs r,rzKBinsDiscretizer.transformas) -1J,>RZ((DJ 4U% H H HO  $$ V VB " ad(;R2YWUUUBqqq"uII ;) # #I t{ " ",J"$(DM  -],,R00F#-DM  *DM  , , , , s DD)rcVt||}t|d|jvr|j|}t |dt jt jf}|j j d}|j d|kr.td ||j dt|D]]}|j|}|dd|ddzd z}||dd|ft j|dd|f<^|S) a Transform discretized data back to original feature space. Note that this function does not regenerate the original data due to discretization rounding. Parameters ---------- X : array-like of shape (n_samples, n_features) Transformed data in the binned space. Xt : array-like of shape (n_samples, n_features) Transformed data in the binned space. .. deprecated:: 1.5 `Xt` was deprecated in 1.5 and will be removed in 1.7. Use `X` instead. Returns ------- Xinv : ndarray, dtype={np.float32, np.float64} Data in the original feature space. rT)rtr%rrz8Incorrect number of features. Expecting {}, received {}.Nr>r?)r rr#reinverse_transformrrErKrLrdrMrNrrRrcastypeint64)r+rfrXinvrirkrj bin_centerss r,rz"KBinsDiscretizer.inverse_transforms/. /q" 5 5 t{ " " //22A14 BJ/GHHH\'* :a=J & &JQQ 1    ## F FB+I$QRR=9SbS>9S@K%tAAArE{&:&:28&D&DEDBKK r.ct|dt||}t|dr|j|S|S)aGet output feature names. Parameters ---------- input_features : array-like of str or None, default=None Input features. - If `input_features` is `None`, then `feature_names_in_` is used as feature names in. If `feature_names_in_` is not defined, then the following input feature names are generated: `["x0", "x1", ..., "x(n_features_in_ - 1)"]`. - If `input_features` is an array-like, then `input_features` must match `feature_names_in_` if `feature_names_in_` is defined. Returns ------- feature_names_out : ndarray of str objects Transformed feature names. n_features_in_re)rrhasattrreget_feature_names_out)r+input_featuress r,rz&KBinsDiscretizer.get_feature_names_outsU( .///0~FF 4 $ $ G=66~FF Fr.)r()NNr*)r __module__ __qualname____doc__r rr r typerErKrLr'dict__annotations__r-rr]rOrrrr7r.r,rrsRRj8Haf===|L:CCCDDEZ A A ABBC'$RZ 8994@hxD@@@$G'( $$D))))))"\555}}}65}~2%%%N,d,,,,,\r.r)rUnumbersrnumpyrEbaserrrutilsrutils._param_validationr r r utils.deprecationr utils.statsrutils.validationrrrrr _encodersrrr7r.r,rs; @@@@@@@@@@CCCCCCCCCCBBBBBB......%$$$$$wwwww'wwwwwr.