U 2d(@sdZddlZddlZddlmZddlZddlZddlZddlZ ddl m Z ddl m Z ddlmZddlmZdd lmZdd lmZdd lmZdd lmZdd lmZddlmZddlmZddlmZddlmZddlmZddlm Z ddddZ!GdddZ"GdddZ#GdddZ$GdddZ%Gd d!d!Z&Gd"d#d#eZ'Gd$d%d%Z(Gd&d'd'Z)Gd(d)d)Z*Gd*d+d+Z+Gd,d-d-Z,Gd.d/d/Z-Gd0d1d1Z.d2d3Z/d4d5Z0d6d7Z1dS)8z Base classes for all estimators.N) defaultdict) __version__) get_config) _IS_32BIT)_SetOutputMixin _DEFAULT_TAGS) check_X_y check_array)_check_y) _num_features_check_feature_names_in)_generate_get_feature_names_out)check_is_fitted)_get_feature_namesestimator_html_repr)validate_parameter_constraintsTsafec st|}|ttttfkr.|fdd|DSt|drBt|tr|sPt|St|trdt dnt dt |t|f|j }|j dd}| D]\}}t|dd||<q|f|}|j dd}|D],}||} ||} | | k rtd ||fqt|d rt|j|_|S) arConstruct a new unfitted estimator with the same parameters. Clone does a deep copy of the model in an estimator without actually copying attached data. It returns a new estimator with the same parameters that has not been fitted on any data. Parameters ---------- estimator : {list, tuple, set} of estimator instance or a single estimator instance The estimator or group of estimators to be cloned. safe : bool, default=True If safe is False, clone will fall back to a deep copy on objects that are not estimators. Returns ------- estimator : object The deep copy of the input, an estimator if input is an estimator. Notes ----- If the estimator's `random_state` parameter is an integer (or if the estimator doesn't have a `random_state` parameter), an *exact clone* is returned: the clone and the original estimator will give the exact same results. Otherwise, *statistical clone* is returned: the clone might return different results from the original estimator. More details can be found in :ref:`randomness`. csg|]}t|dqS)r)clone).0er0/tmp/pip-unpacked-wheel-zrfo1fqw/sklearn/base.py Cszclone.. get_paramszaCannot clone object. You should provide an instance of scikit-learn estimator instead of a class.zCannot clone object '%s' (type %s): it does not seem to be a scikit-learn estimator as it does not implement a 'get_params' method.FdeeprzWCannot clone object %s, as the constructor either does not set or modifies parameter %s_sklearn_output_config)typelisttupleset frozensethasattr isinstancecopydeepcopy TypeErrorrepr __class__ritemsr RuntimeErrorr") estimatorrZestimator_typeklassZnew_object_paramsnameparamZ new_objectZ params_setZparam1Zparam2rrrr"sF      rcseZdZdZeddZd$ddZddZd%d d Zfd d Z fddZ ddZ ddZ ddZ ddZd&ddZddZeddZd d!Zd"d#ZZS)' BaseEstimatorzBase class for all estimators in scikit-learn. Notes ----- All estimators should specify all the parameters that can be set at the class level in their ``__init__`` as explicit keyword arguments (no ``*args`` or ``**kwargs``). cCstt|jd|j}|tjkrgSt|}dd|jD}|D] }|j|jkr@t d||fq@t dd|DS)z%Get parameter names for the estimatorZdeprecated_originalcSs&g|]}|jdkr|j|jkr|qSself)r3kind VAR_KEYWORDrprrrrs z2BaseEstimator._get_param_names..zscikit-learn estimators should always specify their parameters in the signature of their __init__ (no varargs). %s with constructor %s doesn't follow this convention.cSsg|] }|jqSr)r3r:rrrrs) getattr__init__objectinspect signature parametersvaluesr8VAR_POSITIONALr0sorted)clsinitZinit_signaturerAr;rrr_get_param_nameszs   zBaseEstimator._get_param_namesTcsft}|D]Rt|}|rXt|drXt|tsX|}|fdd|D||<q|S)ae Get parameters for this estimator. Parameters ---------- deep : bool, default=True If True, will return the parameters for this estimator and contained subobjects that are estimators. Returns ------- params : dict Parameter names mapped to their values. rc3s"|]\}}d||fVqdS)__Nr)rkvalkeyrr sz+BaseEstimator.get_params..) dictrGr<r(r)r#rr/update)r7r!outvalueZ deep_itemsrrKrrs    zBaseEstimator.get_paramsc Ks|s|S|jdd}tt}|D]j\}}|d\}}}||krh|}td|d|d|d|rz||||<q$t||||||<q$|D]\}} ||jf| q|S)a Set the parameters of this estimator. The method works on simple estimators as well as on nested objects (such as :class:`~sklearn.pipeline.Pipeline`). The latter have parameters of the form ``__`` so that it's possible to update each component of a nested object. Parameters ---------- **params : dict Estimator parameters. Returns ------- self : estimator instance Estimator instance. Tr rHzInvalid parameter z for estimator z. Valid parameters are: .) rrrNr/ partitionrG ValueErrorsetattr set_params) r7paramsZ valid_paramsZ nested_paramsrLrQdelimZsub_keyZlocal_valid_paramsZ sub_paramsrrrrVs$   zBaseEstimator.set_paramsc Csddlm}d}|ddd|d}||}td|}||kr|d}d|}t||} t||ddd } d || | kr|d 7}t||ddd } d } | t| t|| kr|d| d || d}|S) Nr)_EstimatorPrettyPrinterT)compactindentZindent_at_nameZn_max_elements_to_showz ^(\s*\S){%d} z[^\n]*\nz...) Z utils._pprintrZpformatlenjoinsplitrematchend) r7Z N_CHAR_MAXrZZN_MAX_ELEMENTS_TO_SHOWpprepr_Z n_nonblankZlimregexZleft_limZ right_limZellipsisrrr__repr__s,   zBaseEstimator.__repr__cs|t|ddrtdz t}|dkr2|j}Wntk rR|j}YnXt|j drtt | t dS|SdS)N __slots__zSYou cannot use `__slots__` in objects inheriting from `sklearn.base.BaseEstimator`.sklearn.)_sklearn_version) r<r,super __getstate____dict__r*AttributeErrorr# __module__ startswithrNr/r)r7stater.rrrqs  zBaseEstimator.__getstate__cstt|jdr>|dd}|tkr>td|jj |tt zt |Wn t k rn|j|YnXdS)Nrnrozpre-0.18aTrying to unpickle estimator {0} from version {1} when using version {2}. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to: https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations)r#rtrupoprwarningswarnformatr.__name__ UserWarningrp __setstate__rsrrrO)r7rvZpickle_versionrwrrr~'s  zBaseEstimator.__setstate__cCstSNrr6rrr _more_tags;szBaseEstimator._more_tagscCs<i}tt|jD]"}t|dr||}||q|S)Nr)reversedr?getmror.r(rrO)r7Zcollected_tagsZ base_classZ more_tagsrrr _get_tags>s    zBaseEstimator._get_tagsc Csz t|}WnTtk r`}z6|sJt|drJtd|jjd|jd|WYdSd}~XYnX|rp||_dSt|ds~dS||jkrtd|d|jjd|jddS) aSet the `n_features_in_` attribute, or check against it. Parameters ---------- X : {ndarray, sparse matrix} of shape (n_samples, n_features) The input samples. reset : bool If True, the `n_features_in_` attribute is set to `X.shape[1]`. If False and the attribute exists, then check that it is equal to `X.shape[1]`. If False and the attribute does *not* exist, then the check is skipped. .. note:: It is recommended to call reset=True in `fit` and in the first call to `partial_fit`. All other methods that validate `X` should set `reset=False`. n_features_in_z%X does not contain any features, but z is expecting z featuresNzX has z features, but z features as input.)rr,r(rTr.r|r)r7XresetZ n_featuresrrrr_check_n_featuresIs&   zBaseEstimator._check_n_featuresc CsX|r4t|}|dk r||_nt|dr0t|ddSt|dd}t|}|dkr\|dkr\dS|dk r|dkrtd|jjddS|dkr|dk rtd|jjddSt |t |kst ||krTd}t |}t |}t ||} t ||} dd } | r|d 7}|| | 7}| r8|d 7}|| | 7}| sL| sL|d 7}t|dS) aSet or check the `feature_names_in_` attribute. .. versionadded:: 1.0 Parameters ---------- X : {ndarray, dataframe} of shape (n_samples, n_features) The input samples. reset : bool Whether to reset the `feature_names_in_` attribute. If False, the input will be checked for consistency with feature names of data provided when reset was last True. .. note:: It is recommended to call `reset=True` in `fit` and in the first call to `partial_fit`. All other methods that validate `X` should set `reset=False`. Nfeature_names_in_zX has feature names, but z! was fitted without feature namesz)X does not have valid feature names, but z was fitted with feature nameszBThe feature names should match those that were passed during fit. cSsBd}d}t|D],\}}||kr,|d7}q>|d|d7}q|S)Nr^z- ... z- ra) enumerate)namesoutputZ max_n_namesir3rrr add_namessz5BaseEstimator._check_feature_names..add_namesz"Feature names unseen at fit time: z1Feature names seen at fit time, yet now missing: z=Feature names must be in the same order as they were in fit. )rrr(delattrr<ryrzr.r|rcnpanyr&rDrT) r7rrZfeature_names_inZfitted_feature_namesZX_feature_namesmessageZfitted_feature_names_setZX_feature_names_setZunexpected_namesZ missing_namesrrrr_check_feature_nameswsT         z"BaseEstimator._check_feature_names no_validationFc KsZ|j||d|dkr6|dr6td|jjdt|toF|dk}|dkp`t|to`|dk}d|i}||}|r|rtdn|s|rt|fd d i|}|} n|r|st|f|}|} nt|r|\} } d| kr|| } t|fd d i| }d| kr|| } t|fd d i| }nt ||f|\}}||f} |sV| d d rV|j ||d| S)a} Validate input data and set or check the `n_features_in_` attribute. Parameters ---------- X : {array-like, sparse matrix, dataframe} of shape (n_samples, n_features), default='no validation' The input samples. If `'no_validation'`, no validation is performed on `X`. This is useful for meta-estimator which can delegate input validation to their underlying estimator(s). In that case `y` must be passed and the only accepted `check_params` are `multi_output` and `y_numeric`. y : array-like of shape (n_samples,), default='no_validation' The targets. - If `None`, `check_array` is called on `X`. If the estimator's requires_y tag is True, then an error will be raised. - If `'no_validation'`, `check_array` is called on `X` and the estimator's requires_y tag is ignored. This is a default placeholder and is never meant to be explicitly set. In that case `X` must be passed. - Otherwise, only `y` with `_check_y` or both `X` and `y` are checked with either `check_array` or `check_X_y` depending on `validate_separately`. reset : bool, default=True Whether to reset the `n_features_in_` attribute. If False, the input will be checked for consistency with data provided when reset was last True. .. note:: It is recommended to call reset=True in `fit` and in the first call to `partial_fit`. All other methods that validate `X` should set `reset=False`. validate_separately : False or tuple of dicts, default=False Only used if y is not None. If False, call validate_X_y(). Else, it must be a tuple of kwargs to be used for calling check_array() on X and y respectively. `estimator=self` is automatically added to these dicts to generate more informative error message in case of invalid input data. **check_params : kwargs Parameters passed to :func:`sklearn.utils.check_array` or :func:`sklearn.utils.check_X_y`. Ignored if validate_separately is not False. `estimator=self` is automatically added to these params to generate more informative error message in case of invalid input data. Returns ------- out : {ndarray, sparse matrix} or tuple of these The validated input. A tuple is returned if both `X` and `y` are validated. )rN requires_yzThis z= estimator requires y to be passed, but the target y is None.rr1z*Validation should be done on X, y or both.Z input_nameryZ ensure_2dT) rrrTr.r|r)strr r r getr) r7rrrZvalidate_separatelyZ check_paramsZno_val_XZno_val_yZdefault_check_paramsrPZcheck_X_paramsZcheck_y_paramsrrr_validate_datas<A   zBaseEstimator._validate_datacCs t|j|jdd|jjddS)aYValidate types and values of constructor parameters The expected type and values must be defined in the `_parameter_constraints` class attribute, which is a dictionary `param_name: list of constraints`. See the docstring of `validate_parameter_constraints` for a description of the accepted constraints. Fr )Z caller_nameN)rZ_parameter_constraintsrr.r|r6rrr_validate_params=s  zBaseEstimator._validate_paramscCstddkrtd|jS)aHTML representation of estimator. This is redundant with the logic of `_repr_mimebundle_`. The latter should be favorted in the long term, `_repr_html_` is only implemented for consumers who do not interpret `_repr_mimbundle_`. displaydiagramzW_repr_html_ is only defined when the 'display' configuration option is set to 'diagram')rrs_repr_html_innerr6rrr _repr_html_Ks zBaseEstimator._repr_html_cCst|S)zThis function is returned by the @property `_repr_html_` to make `hasattr(estimator, "_repr_html_") return `True` or `False` depending on `get_config()["display"]`. rr6rrrr[szBaseEstimator._repr_html_innercKs*dt|i}tddkr&t||d<|S)z8Mime bundle used by jupyter kernels to display estimatorz text/plainrrz text/html)r-rr)r7kwargsrrrr_repr_mimebundle_bs  zBaseEstimator._repr_mimebundle_)T)rY)rrTF)r|rt __qualname____doc__ classmethodrGrrVrlrqr~rrrrrrpropertyrrr __classcell__rrrwrr5ps,   , 4   .[ m r5c@s&eZdZdZdZdddZddZdS) ClassifierMixinz0Mixin class for all classifiers in scikit-learn. classifierNcCs ddlm}|||||dS)a Return the mean accuracy on the given test data and labels. In multi-label classification, this is the subset accuracy which is a harsh metric since you require for each sample that each label set be correctly predicted. Parameters ---------- X : array-like of shape (n_samples, n_features) Test samples. y : array-like of shape (n_samples,) or (n_samples, n_outputs) True labels for `X`. sample_weight : array-like of shape (n_samples,), default=None Sample weights. Returns ------- score : float Mean accuracy of ``self.predict(X)`` wrt. `y`. r)accuracy_score sample_weight)metricsrpredict)r7rrrrrrrscoreos zClassifierMixin.scorecCsddiSNrTrr6rrrrszClassifierMixin._more_tags)Nr|rtrr_estimator_typerrrrrrrjs rc@s&eZdZdZdZdddZddZdS) RegressorMixinz:Mixin class for all regression estimators in scikit-learn. regressorNcCs$ddlm}||}||||dS)aReturn the coefficient of determination of the prediction. The coefficient of determination :math:`R^2` is defined as :math:`(1 - \frac{u}{v})`, where :math:`u` is the residual sum of squares ``((y_true - y_pred)** 2).sum()`` and :math:`v` is the total sum of squares ``((y_true - y_true.mean()) ** 2).sum()``. The best possible score is 1.0 and it can be negative (because the model can be arbitrarily worse). A constant model that always predicts the expected value of `y`, disregarding the input features, would get a :math:`R^2` score of 0.0. Parameters ---------- X : array-like of shape (n_samples, n_features) Test samples. For some estimators this may be a precomputed kernel matrix or a list of generic objects instead with shape ``(n_samples, n_samples_fitted)``, where ``n_samples_fitted`` is the number of samples used in the fitting for the estimator. y : array-like of shape (n_samples,) or (n_samples, n_outputs) True values for `X`. sample_weight : array-like of shape (n_samples,), default=None Sample weights. Returns ------- score : float :math:`R^2` of ``self.predict(X)`` wrt. `y`. Notes ----- The :math:`R^2` score used when calling ``score`` on a regressor uses ``multioutput='uniform_average'`` from version 0.23 to keep consistent with default value of :func:`~sklearn.metrics.r2_score`. This influences the ``score`` method of all the multioutput regressors (except for :class:`~sklearn.multioutput.MultiOutputRegressor`). r)r2_scorer)rrr)r7rrrrZy_predrrrrs)  zRegressorMixin.scorecCsddiSrrr6rrrrszRegressorMixin._more_tags)Nrrrrrrs .rc@s&eZdZdZdZdddZddZdS) ClusterMixinz7Mixin class for all cluster estimators in scikit-learn.Z clustererNcCs|||jS)a Perform clustering on `X` and returns cluster labels. Parameters ---------- X : array-like of shape (n_samples, n_features) Input data. y : Ignored Not used, present for API consistency by convention. Returns ------- labels : ndarray of shape (n_samples,), dtype=np.int64 Cluster labels. )fitZlabels_r7rrrrr fit_predicts zClusterMixin.fit_predictcCsdgiS)NZpreserves_dtyperr6rrrrszClusterMixin._more_tags)N)r|rtrrrrrrrrrrs rc@s4eZdZdZeddZddZddZdd Zd S) BiclusterMixinz9Mixin class for all bicluster estimators in scikit-learn.cCs |j|jfS)z{Convenient way to get row and column indicators together. Returns the ``rows_`` and ``columns_`` members. )rows_columns_r6rrr biclusters_szBiclusterMixin.biclusters_cCs0|j|}|j|}t|dt|dfS)aRow and column indices of the `i`'th bicluster. Only works if ``rows_`` and ``columns_`` attributes exist. Parameters ---------- i : int The index of the cluster. Returns ------- row_ind : ndarray, dtype=np.intp Indices of rows in the dataset that belong to the bicluster. col_ind : ndarray, dtype=np.intp Indices of columns in the dataset that belong to the bicluster. r)rrrZnonzero)r7rZrowscolumnsrrr get_indicess  zBiclusterMixin.get_indicescCs||}tdd|DS)a-Shape of the `i`'th bicluster. Parameters ---------- i : int The index of the cluster. Returns ------- n_rows : int Number of rows in the bicluster. n_cols : int Number of columns in the bicluster. css|]}t|VqdSr)rc)rrrrrrMsz+BiclusterMixin.get_shape..)rr%)r7rindicesrrr get_shapes zBiclusterMixin.get_shapecCs@ddlm}||dd}||\}}||ddtjf|fS)aReturn the submatrix corresponding to bicluster `i`. Parameters ---------- i : int The index of the cluster. data : array-like of shape (n_samples, n_features) The data. Returns ------- submatrix : ndarray of shape (n_rows, n_cols) The submatrix corresponding to bicluster `i`. Notes ----- Works with sparse matrices. Only works if ``rows_`` and ``columns_`` attributes exist. rr Zcsr)Z accept_sparseN)utils.validationr rrZnewaxis)r7rdatar Zrow_indZcol_indrrr get_submatrixs  zBiclusterMixin.get_submatrixN) r|rtrrrrrrrrrrrrs  rc@seZdZdZdddZdS)TransformerMixinaMixin class for all transformers in scikit-learn. If :term:`get_feature_names_out` is defined, then `BaseEstimator` will automatically wrap `transform` and `fit_transform` to follow the `set_output` API. See the :ref:`developer_api_set_output` for details. :class:`base.OneToOneFeatureMixin` and :class:`base.ClassNamePrefixFeaturesOutMixin` are helpful mixins for defining :term:`get_feature_names_out`. NcKs6|dkr|j|f||S|j||f||SdS)a Fit to data, then transform it. Fits transformer to `X` and `y` with optional parameters `fit_params` and returns a transformed version of `X`. Parameters ---------- X : array-like of shape (n_samples, n_features) Input samples. y : array-like of shape (n_samples,) or (n_samples, n_outputs), default=None Target values (None for unsupervised transformations). **fit_params : dict Additional fit parameters. Returns ------- X_new : ndarray array of shape (n_samples, n_features_new) Transformed array. N)rZ transform)r7rrZ fit_paramsrrr fit_transform?szTransformerMixin.fit_transform)N)r|rtrrrrrrrr3s rc@seZdZdZdddZdS)OneToOneFeatureMixinzProvides `get_feature_names_out` for simple transformers. This mixin assumes there's a 1-to-1 correspondence between input features and output features, such as :class:`~preprocessing.StandardScaler`. NcCs t||S)aGet output feature names for transformation. 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 Same as input features. rr7input_featuresrrrget_feature_names_outhsz*OneToOneFeatureMixin.get_feature_names_out)Nr|rtrrrrrrrrasrc@seZdZdZdddZdS)ClassNamePrefixFeaturesOutMixinaEMixin class for transformers that generate their own names by prefixing. This mixin is useful when the transformer needs to generate its own feature names out, such as :class:`~decomposition.PCA`. For example, if :class:`~decomposition.PCA` outputs 3 features, then the generated feature names out are: `["pca0", "pca1", "pca2"]`. This mixin assumes that a `_n_features_out` attribute is defined when the transformer is fitted. `_n_features_out` is the number of output features that the transformer will return in `transform` of `fit_transform`. NcCst|dt||j|dS)aLGet output feature names for transformation. The feature names out will prefixed by the lowercased class name. For example, if the transformer outputs 3 features, then the feature names out are: `["class_name0", "class_name1", "class_name2"]`. Parameters ---------- input_features : array-like of str or None, default=None Only used to validate feature names with the names seen in :meth:`fit`. Returns ------- feature_names_out : ndarray of str objects Transformed feature names. _n_features_out)r)rrrrrrrrs  z5ClassNamePrefixFeaturesOutMixin.get_feature_names_out)Nrrrrrrs rc@seZdZdZdZdddZdS) DensityMixinz7Mixin class for all density estimators in scikit-learn.ZDensityEstimatorNcCsdS)a=Return the score of the model on the data `X`. Parameters ---------- X : array-like of shape (n_samples, n_features) Test samples. y : Ignored Not used, present for API consistency by convention. Returns ------- score : float NrrrrrrszDensityMixin.score)N)r|rtrrrrrrrrrsrc@seZdZdZdZdddZdS) OutlierMixinzAMixin class for all outlier detection estimators in scikit-learn.outlier_detectorNcCs|||S)aPerform fit on X and returns labels for X. Returns -1 for outliers and 1 for inliers. Parameters ---------- X : {array-like, sparse matrix} of shape (n_samples, n_features) The input samples. y : Ignored Not used, present for API consistency by convention. Returns ------- y : ndarray of shape (n_samples,) 1 for inliers, -1 for outliers. )rrrrrrrszOutlierMixin.fit_predict)N)r|rtrrrrrrrrrsrc@seZdZdgZdS)MetaEstimatorMixinr1N)r|rtrZ_required_parametersrrrrrsrc@seZdZdZddZdS)MultiOutputMixinz2Mixin to mark estimators that support multioutput.cCsddiS)NZ multioutputTrr6rrrrszMultiOutputMixin._more_tagsNr|rtrrrrrrrrsrc@seZdZdZddZdS)_UnstableArchMixinz=Mark estimators that are non-determinstic on 32bit or PowerPCcCsdtptdiS)NZnon_deterministic)ppcZpowerpc)rplatformmachinerur6rrrrsz_UnstableArchMixin._more_tagsNrrrrrrsrcCst|dddkS)aReturn True if the given estimator is (probably) a classifier. Parameters ---------- estimator : object Estimator object to test. Returns ------- out : bool True if estimator is a classifier and False otherwise. rNrr<r1rrr is_classifiers rcCst|dddkS)a Return True if the given estimator is (probably) a regressor. Parameters ---------- estimator : estimator instance Estimator object to test. Returns ------- out : bool True if estimator is a regressor and False otherwise. rNrrrrrr is_regressors rcCst|dddkS)aReturn True if the given estimator is (probably) an outlier detector. Parameters ---------- estimator : estimator instance Estimator object to test. Returns ------- out : bool True if estimator is an outlier detector and False otherwise. rNrrrrrris_outlier_detector s r)2rr*ry collectionsrrr?rfZnumpyrr^r_configrutilsrZutils._set_outputrZ utils._tagsr rr r r rrrrrZutils._estimator_html_reprrZutils._param_validationrrr5rrrrrrrrrrrrrrrrrrrsT                N}%7N.$