a h*B@sddlZddlmZddlZddlmZmZmZddl m Z ddl m Z m Z mZddlmZddlmZdd lmZmZmZmZmZd d lmZGd d 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 @seZdZUdZeedddddgehdgehdgeee j e j hdgeed ddddgd gd Z e ed <d!ddddddddZeddd"ddZddZddZd#ddddZd$dd ZdS)%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>ordinalz onehot-denseonehot>uniformquantilekmeansr random_staten_binsencodestrategydtype subsampler_parameter_constraintsrri@ )r r!r"r#rcCs(||_||_||_||_||_||_dSNr)selfrr r!r"r#rr(a/var/www/html/assistant/venv/lib/python3.9/site-packages/sklearn/preprocessing/_discretization.py__init__s zKBinsDiscretizer.__init__T)Zprefer_skip_nested_validationcsTt||dd}|jtjtjfvr(|j}n|j}|j\}}dur\|jdkr\td|jd|jdur||jkrt |d|j|j d}|jd }| |}durt ||jdtj |td}t|D]0} |dd| f} } | | kr(td | d || <ttj tjg|| <q|jdkrRt| | || d || <n:|jd krtd d || d } durtt| || <n$tjfdd| Dtjd|| <n|jdkrddlm} t| | || d }|d d|dddddfd}| || |d d}|jdddfdjddd f}||d d|ddd|| <tj| || | f|| <|jdvrtj|| tjddk}|| ||| <t || d || krtd| t || d || <q||_!||_"d|j#vrPt$dd|j"D|j#dk|d|_%|j%t d t |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_samplesrrz3Feature %d is constant and will be replaced with 0.rrdcsg|]}t|qSr(r ).0qcolumn sample_weightr(r) sz(KBinsDiscretizer.fit..rr)KMeans?)Z n_clustersinitZn_init)r4)rr)Zto_beging:0yE>zqBins whose width are too small (i.e., <= 1e-8) in feature %d are removed. Consider decreasing the number of bins.rcSsg|]}t|qSr()npZaranger0ir(r(r)r5>) categoriesZ sparse_outputr")&rr"r:float64float32shaper! ValueErrorr#rr_validate_n_binsrZzerosobjectrangeminmaxwarningswarnarrayinfZlinspaceZasarrayZ percentileZclusterr6fitZcluster_centers_sortZr_Zediff1dlen bin_edges_n_bins_r r_encoder)r'Xyr4Z output_dtyper. n_featuresr bin_edgesjjZcol_minZcol_maxZ quantilesr6Z uniform_edgesr9kmZcentersmaskr(r2r)rLs           (    zKBinsDiscretizer.fitcCs|j}t|tr tj||tdSt|tddd}|jdksH|jd|krPt d|dk||kB}t |d}|jddkrd d d |D}t d t j||S) z0Returns n_bins_, the number of bins per feature.r,TF)r"copyZ ensure_2drrz8n_bins must be a scalar or array of shape (n_features,).rz, css|]}t|VqdSr&)strr;r(r(r) Wr=z4KBinsDiscretizer._validate_n_bins..zk{} received an invalid number of bins at indices {}. Number of bins must be at least 2, and must be an int.)r isinstancerr:fullintrndimrArBwherejoinformatr__name__)r'rTZ orig_binsrZbad_nbins_valueZviolating_indicesindicesr(r(r)rCHs  z!KBinsDiscretizer._validate_n_binscCst||jdurtjtjfn|j}t||d|dd}|j}t|jdD]8}tj ||dd|dd|fdd|dd|f<qJ|j d kr|Sd}d |j vr|j j}|j|j _z|j |}W||j _n ||j _0|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)rYr"resetrr7right)Zsiderr) rr"r:r?r@rrOrErAZ searchsortedr rQ transform)r'rRr"XtrUrVZ dtype_initZXt_encr(r(r)rgas 6   zKBinsDiscretizer.transform)rhcCst||}t|d|jvr(|j|}t|dtjtjfd}|j j d}|j d|krnt d ||j dt |D]R}|j|}|dd|ddd }||dd|ftj|dd|f<qv|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)rYr"rrz8Incorrect number of features. Expecting {}, received {}.Nr7r8)r rr rQinverse_transformrr:r?r@rPrArBrbrErOZastypeZint64)r'rRrhZXinvrTrVrUZ bin_centersr(r(r)ris"       *z"KBinsDiscretizer.inverse_transformcCs.t|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. Zn_features_in_rQ)rrhasattrrQget_feature_names_out)r'Zinput_featuresr(r(r)rks     z&KBinsDiscretizer.get_feature_names_out)r%)NN)N)N)rc __module__ __qualname____doc__rrr r typer:r?r@r$dict__annotations__r*rrLrCrgrirkr(r(r(r)rs.      '.r)rHnumbersrnumpyr:baserrrutilsrZutils._param_validationrr r Zutils.deprecationr Z utils.statsr Zutils.validationrrrrrZ _encodersrrr(r(r(r)s