Q(hPddlmZmZddlZddlmZmZddlm Z m Z ddl m Z ddl mZmZmZmZdd lmZdd lmZmZGd d eeZy) )IntegralRealN)OneToOneFeatureMixin _fit_context)Interval StrOptions)type_of_target)_check_feature_names_in_check_ycheck_consistent_lengthcheck_is_fitted) _BaseEncoder)_fit_encoding_fast_fit_encoding_fast_auto_smoothc eZdZUdZedhegehdgedheedddgeedddgd gd gd Z e e d < ddZ e d dZe d dZdZdZdZdZdZddZfdZxZS) TargetEncoderuTarget Encoder for regression and classification targets. Each category is encoded based on a shrunk estimate of the average target values for observations belonging to the category. The encoding scheme mixes the global target mean with the target mean conditioned on the value of the category (see [MIC]_). When the target type is "multiclass", encodings are based on the conditional probability estimate for each class. The target is first binarized using the "one-vs-all" scheme via :class:`~sklearn.preprocessing.LabelBinarizer`, then the average target value for each class and each category is used for encoding, resulting in `n_features` * `n_classes` encoded output features. :class:`TargetEncoder` considers missing values, such as `np.nan` or `None`, as another category and encodes them like any other category. Categories that are not seen during :meth:`fit` are encoded with the target mean, i.e. `target_mean_`. For a demo on the importance of the `TargetEncoder` internal cross-fitting, see :ref:`sphx_glr_auto_examples_preprocessing_plot_target_encoder_cross_val.py`. For a comparison of different encoders, refer to :ref:`sphx_glr_auto_examples_preprocessing_plot_target_encoder.py`. Read more in the :ref:`User Guide `. .. note:: `fit(X, y).transform(X)` does not equal `fit_transform(X, y)` because a :term:`cross fitting` scheme is used in `fit_transform` for encoding. See the :ref:`User Guide ` for details. .. versionadded:: 1.3 Parameters ---------- categories : "auto" or list of shape (n_features,) of array-like, default="auto" Categories (unique values) per feature: - `"auto"` : Determine categories automatically from the training data. - list : `categories[i]` holds the categories expected in the i-th column. The passed categories should not mix strings and numeric values within a single feature, and should be sorted in case of numeric values. The used categories are stored in the `categories_` fitted attribute. target_type : {"auto", "continuous", "binary", "multiclass"}, default="auto" Type of target. - `"auto"` : Type of target is inferred with :func:`~sklearn.utils.multiclass.type_of_target`. - `"continuous"` : Continuous target - `"binary"` : Binary target - `"multiclass"` : Multiclass target .. note:: The type of target inferred with `"auto"` may not be the desired target type used for modeling. For example, if the target consisted of integers between 0 and 100, then :func:`~sklearn.utils.multiclass.type_of_target` will infer the target as `"multiclass"`. In this case, setting `target_type="continuous"` will specify the target as a regression problem. The `target_type_` attribute gives the target type used by the encoder. .. versionchanged:: 1.4 Added the option 'multiclass'. smooth : "auto" or float, default="auto" The amount of mixing of the target mean conditioned on the value of the category with the global target mean. A larger `smooth` value will put more weight on the global target mean. If `"auto"`, then `smooth` is set to an empirical Bayes estimate. cv : int, default=5 Determines the number of folds in the :term:`cross fitting` strategy used in :meth:`fit_transform`. For classification targets, `StratifiedKFold` is used and for continuous targets, `KFold` is used. shuffle : bool, default=True Whether to shuffle the data in :meth:`fit_transform` before splitting into folds. Note that the samples within each split will not be shuffled. random_state : int, RandomState instance or None, default=None When `shuffle` is True, `random_state` affects the ordering of the indices, which controls the randomness of each fold. Otherwise, this parameter has no effect. Pass an int for reproducible output across multiple function calls. See :term:`Glossary `. Attributes ---------- encodings_ : list of shape (n_features,) or (n_features * n_classes) of ndarray Encodings learnt on all of `X`. For feature `i`, `encodings_[i]` are the encodings matching the categories listed in `categories_[i]`. When `target_type_` is "multiclass", the encoding for feature `i` and class `j` is stored in `encodings_[j + (i * len(classes_))]`. E.g., for 2 features (f) and 3 classes (c), encodings are ordered: f0_c0, f0_c1, f0_c2, f1_c0, f1_c1, f1_c2, categories_ : list of shape (n_features,) of ndarray The categories of each input feature determined during fitting or specified in `categories` (in order of the features in `X` and corresponding with the output of :meth:`transform`). target_type_ : str Type of target. target_mean_ : float The overall mean of the target. This value is only used in :meth:`transform` to encode categories. n_features_in_ : int Number of features seen during :term:`fit`. 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. classes_ : ndarray or None If `target_type_` is 'binary' or 'multiclass', holds the label for each class, otherwise `None`. See Also -------- OrdinalEncoder : Performs an ordinal (integer) encoding of the categorical features. Contrary to TargetEncoder, this encoding is not supervised. Treating the resulting encoding as a numerical features therefore lead arbitrarily ordered values and therefore typically lead to lower predictive performance when used as preprocessing for a classifier or regressor. OneHotEncoder : Performs a one-hot encoding of categorical features. This unsupervised encoding is better suited for low cardinality categorical variables as it generate one new feature per unique category. References ---------- .. [MIC] :doi:`Micci-Barreca, Daniele. "A preprocessing scheme for high-cardinality categorical attributes in classification and prediction problems" SIGKDD Explor. Newsl. 3, 1 (July 2001), 27–32. <10.1145/507533.507538>` Examples -------- With `smooth="auto"`, the smoothing parameter is set to an empirical Bayes estimate: >>> import numpy as np >>> from sklearn.preprocessing import TargetEncoder >>> X = np.array([["dog"] * 20 + ["cat"] * 30 + ["snake"] * 38], dtype=object).T >>> y = [90.3] * 5 + [80.1] * 15 + [20.4] * 5 + [20.1] * 25 + [21.2] * 8 + [49] * 30 >>> enc_auto = TargetEncoder(smooth="auto") >>> X_trans = enc_auto.fit_transform(X, y) >>> # A high `smooth` parameter puts more weight on global mean on the categorical >>> # encodings: >>> enc_high_smooth = TargetEncoder(smooth=5000.0).fit(X, y) >>> enc_high_smooth.target_mean_ np.float64(44...) >>> enc_high_smooth.encodings_ [array([44..., 44..., 44...])] >>> # On the other hand, a low `smooth` parameter puts more weight on target >>> # conditioned on the value of the categorical: >>> enc_low_smooth = TargetEncoder(smooth=1.0).fit(X, y) >>> enc_low_smooth.encodings_ [array([20..., 80..., 43...])] auto>rbinary continuous multiclassrNleft)closedrboolean random_state) categories target_typesmoothcvshuffler_parameter_constraintsTcX||_||_||_||_||_||_yN)rrrr r!r)selfrrrr r!rs c/var/www/skyplay_api_hub/venv/lib/python3.12/site-packages/sklearn/preprocessing/_target_encoder.py__init__zTargetEncoder.__init__s0% & ()prefer_skip_nested_validationc*|j|||S)aFit the :class:`TargetEncoder` to X and y. Parameters ---------- X : array-like of shape (n_samples, n_features) The data to determine the categories of each feature. y : array-like of shape (n_samples,) The target data used to encode the categories. Returns ------- self : object Fitted encoder. )_fit_encodings_all)r%Xys r&fitzTargetEncoder.fits" 1% r(c <ddlm}m}|j||\}}}}|jdk(r*||j |j |j} n)||j |j |j} |jdk(rXtj|jd|jdt|jzftj} n%tj|tj} | j||D]y\} } || d d f|| }} tj |d }|jdk(r|j#| |||}n|j%| |||}|j'| ||| ||{| S) a Fit :class:`TargetEncoder` and transform X with the target encoding. .. note:: `fit(X, y).transform(X)` does not equal `fit_transform(X, y)` because a :term:`cross fitting` scheme is used in `fit_transform` for encoding. See the :ref:`User Guide `. for details. Parameters ---------- X : array-like of shape (n_samples, n_features) The data to determine the categories of each feature. y : array-like of shape (n_samples,) The target data used to encode the categories. Returns ------- X_trans : ndarray of shape (n_samples, n_features) or (n_samples, (n_features * n_classes)) Transformed input. r)KFoldStratifiedKFoldr)r!rrrrdtypeNaxis)model_selectionr0r1r+ target_type_r r!rnpemptyshapelenclasses_float64 empty_likesplitmean_fit_encoding_multiclass"_fit_encoding_binary_or_continuous_transform_X_ordinal)r%r,r-r0r1 X_ordinal X_known_mask y_encoded n_categoriesr X_out train_idxtest_idxX_trainy_train y_train_mean encodingss r& fit_transformzTargetEncoder.fit_transforms. =;?;R;RSTVW;X8 <L    ,tww 4CTCTUB DE#%88Aq>  Ix(A6 )8LWG7773L  L0 99   !CC    % %   % 4 r(c|j|dd\}}|jdk(rXtj|jd|jdt |j zftj}n%tj|tj}|j|||td|j|j|S) aTransform X with the target encoding. .. note:: `fit(X, y).transform(X)` does not equal `fit_transform(X, y)` because a :term:`cross fitting` scheme is used in `fit_transform` for encoding. See the :ref:`User Guide `. for details. Parameters ---------- X : array-like of shape (n_samples, n_features) The data to determine the categories of each feature. Returns ------- X_trans : ndarray of shape (n_samples, n_features) or (n_samples, (n_features * n_classes)) Transformed input. ignore allow-nanhandle_unknownensure_all_finiterrrr2N) _transformr7r8r9r:r;r<r=r>rCslice encodings_ target_mean_)r%r,rDrErHs r& transformzTargetEncoder.transform4s&#'// h+#2#  <    ,HH#Y__Q%7#dmm:L%LMjjE MM)2::>E !!   M $K OO      r(cddlm}m}t|||j |dd|j dk(r-d}t |d }||vrtd |d |d ||_n|j |_d |_ |jdk(r*|}|j|}|j|_ nG|jdk(r*|}|j|}|j|_ nt|d|}tj|d|_|j|dd\} } tj d|j"Dtj$t'|j"} |jdk(r|j)| || |j} n|j+| || |j} | |_| | || fS)z(Fit a target encoding with all the data.r)LabelBinarizer LabelEncoderrQrRrSr)rrrr-) input_namez3Unknown label type: Target type was inferred to be z. Only z are supported.NrrT) y_numeric estimatorrr4c32K|]}t|ywr$)r;).0category_for_features r& z3TargetEncoder._fit_encodings_all..s T+?S% & Ts)r3count) preprocessingr\r]r _fitrr ValueErrorr7r<rOr r8r@rYrVfromiter categories_int64r;rArBrX) r%r,r-r\r]accepted_target_typesinferred_type_of_target label_encoderlabel_binarizerrDrErGrNs r&r+z TargetEncoder._fit_encodings_all^s 1% !H L   v %$J !&4Q3&G #&.CC I.19N8OP!! !8D  $ 0 0D     ((NM++A.A)22DM   , .,.O--a0A+44DMdd;AGGAA."&// h+#2#  <{{ T4CSCS T((d&&'    ,55!! I??!! I $,<77r(c|jdk(r&tj|}t|||||}|St ||||j|}|S)zLearn target encodings.r)rr8varrr)r%rDr-rG target_mean y_variancerNs r&rBz0TargetEncoder._fit_encoding_binary_or_continuousse ;;& J6 I+  Ir(c( |j t|j g}t D]3}|dd|f}|j |||||}|j |5 fdt D} | D cgc]} ||  c} Scc} w)aDLearn multiclass encodings. Learn encodings for each class (c) then reorder encodings such that the same features (f) are grouped together. `reorder_index` enables converting from: f0_c0, f1_c0, f0_c1, f1_c1, f0_c2, f1_c2 to: f0_c0, f0_c1, f0_c2, f1_c0, f1_c1, f1_c2 Nc3LK|]}t|zD]}|ywr$)range)rbstartidx n_classes n_featuress r&rdz9TargetEncoder._fit_encoding_multiclass..s< UY%;jI    s!$)n_features_in_r;r<rvrBextend) r%rDr-rGrrrNiy_classencoding reorder_indexrxryrzs @@r&rAz&TargetEncoder._fit_encoding_multiclasss((  &  y! 'A1gG>>A H   X & ' z* +883 #888s Bc(|jdk(rSt|j}t|D]/\}} ||z} ||z} | ||| f|||f<|| ||dd| f|f<1yt|D]"\}} | |||f|||f<|||dd|f|f<$y)aTransform X_ordinal using encodings. In the multiclass case, `X_ordinal` and `X_unknown_mask` have column (axis=1) size `n_features`, while `encodings` has length of size `n_features * n_classes`. `feat_idx` deals with this by repeating feature indices by `n_classes` E.g., for 3 features, 2 classes: 0,0,1,1,2,2 Additionally, `target_mean` is of shape (`n_classes`,) so `mean_idx` cycles through 0 to `n_classes` - 1, `n_features` times. rN)r7r;r< enumerate) r%rHrDX_unknown_mask row_indicesrNrrrye_idxrfeat_idxmean_idxs r&rCz"TargetEncoder._transform_X_ordinals(    ,DMM*I#,Y#7 Rx I- 9,,4Y{H?T5U,Vk5()_'. r{r_r2)rr r7r<r8asarrayobject)r%input_features feature_names feature_name class_names r&get_feature_names_outz#TargetEncoder.get_feature_names_outs" .//nE    ,%2 "&-- .*..M ::m6: : sA,cFt|}d|j_|S)NT)super__sklearn_tags__ target_tagsrequired)r%tags __class__s r&rzTargetEncoder.__sklearn_tags__s#w')$(! r()rrrTNr$)__name__ __module__ __qualname____doc__r listrrrr"dict__annotations__r'rr.rOrZr+rBrArCrr __classcell__)rs@r&rrseP"6(+T2"#QRSvh'$4)OP!T&9:;'( $D ) 56&5G6GR(T>8@.9> ED!:r(r)numbersrrnumpyr8baserrutils._param_validationrr utils.multiclassr utils.validationr r r r _encodersr_target_encoder_fastrrrr(r&rs9#5:- $TA(,Ar(