rtjOddlZddlmZddlZddlmZmZmZddl m Z ddl m Z ddl mZmZmZddlmZddlmZmZmZmZmZGd d eeZdS) N)Integral) BaseEstimatorTransformerMixin _fit_context) OneHotEncoder)resample)IntervalOptions StrOptions)_weighted_percentile)_check_feature_names_in_check_sample_weight check_arraycheck_is_fitted validate_datac HeZdZUdZeeddddgehdgehdgehd geee j e j hdgeed dddgd gd Z e ed < dddddddddZedddZdZdZdZddZdS)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`. quantile_method : {"inverted_cdf", "averaged_inverted_cdf", "closest_observation", "interpolated_inverted_cdf", "hazen", "weibull", "linear", "median_unbiased", "normal_unbiased"}, default="averaged_inverted_cdf" Method to pass on to np.percentile calculation when using strategy="quantile". Only `averaged_inverted_cdf` and `inverted_cdf` support the use of `sample_weight != None` when subsampling is not active. .. versionadded:: 1.7 .. versionchanged:: 1.9 The default value changed from `"linear"` to `"averaged_inverted_cdf"`. 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]]) While this preprocessing step can be an optimization, it is important to note the array returned by ``inverse_transform`` will have an internal type of ``np.float64`` or ``np.float32``, denoted by the ``dtype`` input argument. This can drastically increase the memory usage of the array. See the :ref:`sphx_glr_auto_examples_cluster_plot_face_compress.py` where `KBinsDescretizer` is used to cluster the image into bins and increases the size of the image by 8x. Nleft)closedz array-like> onehot-denseonehotordinal>kmeansuniformquantile> hazenlinearweibull inverted_cdfmedian_unbiasednormal_unbiasedclosest_observationaveraged_inverted_cdfinterpolated_inverted_cdf random_staten_binsencodestrategyquantile_methoddtype subsampler'_parameter_constraintsrrr$i@ )r*r+r,r-r.r'ch||_||_||_||_||_||_||_dSNr()selfr)r*r+r,r-r.r's c/var/www/html/CA-Chatbot/venv/lib/python3.11/site-packages/sklearn/preprocessing/_discretization.py__init__zKBinsDiscretizer.__init__s=    . "(T)prefer_skip_nested_validationc t||d}|jtjtjfvr|j}n|j}|j\}}|t |||j}|j+||jkr t|d|j|j |}d}|jd}| |}tj |t}|j } |jdkr| dvr|td | d |jdkr ||d k} nt!d} t#|D]} |dd| f} | | } | | }| |krKt)jd | zd|| <tjtj tjg|| <|jd kr$tj| ||| dz|| <nu|jdkrtjd d|| dz}i}| dkr|| |d<|6tjtj| |fi|tj|| <n| dkrdnd}t7| ||||| <n|jdkrd dlm}tj| ||| dz}|dd|ddzdddfdz}||| |d}|| dddf|jddd f}| |dd|ddzdz|| <tj!| || |f|| <|jdvrtj"|| tjdk}|| ||| <tG|| dz || kr2t)jd| ztG|| dz || <||_$||_%d|j&vrotOd|j%D|j&dk| |_(|j(tj dtG|j%f|S)!a Fit the estimator. Parameters ---------- X : array-like of shape (n_samples, n_features) Data to be discretized. y : None Ignored. This parameter exists only for compatibility with :class:`~sklearn.pipeline.Pipeline`. sample_weight : ndarray of shape (n_samples,) Contains weight values to be associated with each sample. .. versionadded:: 1.3 .. versionchanged:: 1.7 Added support for strategy="uniform". Returns ------- self : object Returns the instance itself. numericr-NT)replace n_samplesr' sample_weightr&r)r r$zWhen fitting with strategy='quantile' and sample weights, quantile_method should either be set to 'averaged_inverted_cdf' or 'inverted_cdf', got quantile_method='z ' instead.rz3Feature %d is constant and will be replaced with 0.rdrmethodr$F)averager)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|S)nparange.0is r4 z(KBinsDiscretizer.fit..s ???QBIaLL???r6) categories sparse_outputr-))rr-rJfloat64float32shaperr.rr'_validate_n_binszerosobjectr,r+ ValueErrorslicerangeminmaxwarningswarnarrayinflinspaceasarray percentiler sklearn.clusterrAfitcluster_centers_sortr_ediff1dlen bin_edges_n_bins_r*r_encoder)r3Xyr= output_dtyper< n_featuresr) bin_edgesr,nnz_weight_maskjjcolumncol_mincol_maxpercentile_levelspercentile_kwargsr@rA uniform_edgesrEkmcentersmasks r4rezKBinsDiscretizer.fits;6 $ 3 3 3 :"*bj1 1 1:LL7L ! :  $0QQQM > %)dn*D*D.!.+ A!MWQZ &&z22HZv666 . MZ ' ''PPP)T8GTTT  =J & &=+D,q0OO$DkkO ##A 8A 8Bqqq"uXF_-1133G_-1133G'!! IBNr "26'26): ; ; " } )) " GWfRj1n M M " *,,$&K3r Q$G$G! %'!"h..=3H2A%h/ ($&J f.?UUCTUU j%%%IbMM !03J J JPU%9 /@'%%%IbMM(**222222!# 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{ " ")??$,???"kX5"DM M  bh3t|+<+<'=>> ? ? ? r6c|j}t|trtj||t St |t dd}|jdks|jd|krtd|dk||kz}tj |d}|jddkrLd d |D}td tj||S) z0Returns n_bins_, the number of bins per feature.r:TF)r-copy ensure_2dr&rz8n_bins must be a scalar or array of shape (n_features,).rz, c34K|]}t|VdSr2)strrLs r4 z4KBinsDiscretizer._validate_n_bins..s(BB1ABBBBBBr6zk{} received an invalid number of bins at indices {}. Number of bins must be at least 2, and must be an int.)r) isinstancerrJfullintrndimrTrXwherejoinformatr__name__)r3rq orig_binsr)bad_nbins_valueviolating_indicesindicess r4rUz!KBinsDiscretizer._validate_n_binssK i * * =7:y<<< <YcNNN ;??fl1o;;WXX X!A:&I*=>H_55a8  "1 % ) )iiBB0ABBBBBG::@&$-w;;  r6c(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)rr-resetr&rBright)siderr) rr-rJrRrSrrkrZrT searchsortedr*rm transform)r3rnr-Xtrrrt dtype_initXt_encs r4rzKBinsDiscretizer.transforms) -1J,>RZ((DJ 4U% H H HO  $$ V VB " ad(;R2YWUUUBqqq"uII ;) # #I t{ " ",J"$(DM  -],,R00F#-DM  *DM  , , , , s DDc6t|d|jvr|j|}t |dt jt jf}|jj d}|j d|kr.td ||j dt|D]]}|j |}|dd|ddzd z}||dd|ft j|dd|f<^|S) a Transform discretized data back to original feature space. Note that this function does not regenerate the original data due to discretization rounding. Parameters ---------- X : array-like of shape (n_samples, n_features) Transformed data in the binned space. Returns ------- X_original : ndarray, dtype={np.float32, np.float64} Data in the original feature space. rT)rr-rr&z8Incorrect number of features. Expecting {}, received {}.NrBrC)rr*rminverse_transformrrJrRrSrlrTrXrrZrkastypeint64)r3rnXinvrqrtrr bin_centerss r4rz"KBinsDiscretizer.inverse_transforms $  t{ " " //22A14 BJ/GHHH\'* :a=J & &JQQ 1    ## F FB+I$QRR=9SbS>9S@K%tAAArE{&:&:28&D&DEDBKK r6ct|dt||}t|dr|j|S|S)aGet output feature names. Parameters ---------- input_features : array-like of str or None, default=None Input features. - If `input_features` is `None`, then `feature_names_in_` is used as feature names in. If `feature_names_in_` is not defined, then the following input feature names are generated: `["x0", "x1", ..., "x(n_features_in_ - 1)"]`. - If `input_features` is an array-like, then `input_features` must match `feature_names_in_` if `feature_names_in_` is defined. Returns ------- feature_names_out : ndarray of str objects Transformed feature names. n_features_in_rm)rr hasattrrmget_feature_names_out)r3input_featuress r4rz&KBinsDiscretizer.get_feature_names_outsU( .///0~FF 4 $ $ G=66~FF Fr6)r0)NNr2)r __module__ __qualname____doc__r rr r typerJrRrSr/dict__annotations__r5rrerUrrrrIr6r4rrshhV8Haf===|L:CCCDDEZ A A ABBC J      '$RZ 8994@hxD@@@$G'(+$$D4)/)))))&\555fff65fP2%%%N%%%Nr6r)r]numbersrnumpyrJ sklearn.baserrrsklearn.preprocessing._encodersr sklearn.utilsrsklearn.utils._param_validationr r r sklearn.utils.statsr sklearn.utils.validationr rrrrrrIr6r4rs' FFFFFFFFFF999999""""""IIIIIIIIII444444@@@@@'@@@@@r6