U !`gv@sdZddlZddlZddlmZddlZddlZddlZddlZ ddl m Z ddl m Z ddlmZddlmZmZdd lmZdd lmZdd lmZdd lmZed dddZdefddZGdddZGdddZGdddZGdddZGdddZ GdddZ!Gdd d Z"Gd!d"d"Z#Gd#d$d$Z$Gd%d&d&Z%Gd'd(d(Z&d)d*Z'd+d,Z(d-d.Z)d/d0Z*dS)1z Base classes for all estimators.N) defaultdict) __version__) get_config) _IS_32BIT) _DEFAULT_TAGS _safe_tags) check_X_y check_arrayestimator_html_repr)_deprecate_positional_argsTsafec 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 ||fq|S) aConstructs 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 yields a new estimator with the same parameters that has not been fitted on any data. 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 yield different results from the original estimator. More details can be found in :ref:`randomness`. 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. csg|]}t|dqS)r)clone).0er+lib/python3.8/site-packages/sklearn/base.py 9szclone.. 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)typelisttupleset frozensethasattr isinstancecopydeepcopy TypeErrorrepr __class__ritemsr RuntimeError) estimatorrZestimator_typeklassZnew_object_paramsnameZparamZ new_objectZ params_setZparam1Zparam2rrrrs2      rc Cs:t}tjddddt}|}dd|dd}tt|D]\}\}} t| tkrpd|t | f} nd||| f} t | d kr| d d d | d d } |dkr|t | dksd| kr| |t |}n| d|d7}| | |t | 7}qFtjf|d |} d dd| dD} | S)afPretty print the dictionary 'params' Parameters ---------- params : dict The dictionary to pretty print offset : int, default=0 The offset in characters to add at the begin of each line. printer : callable, default=repr The function to convert entries to strings, typically the builtin str or repr @)Z precisionZ thresholdZ edgeitemsz, r z%s=%siNi,...irK z, css|]}|dVqdS)r.N)rstrip)rlrrr sz_pprint..)npZget_printoptionsZset_printoptionsr enumeratesortedr&rfloatstrlenappendjoinsplit) paramsoffsetZprinterZoptionsZ params_listZthis_line_lengthZline_sepikvZ this_reprlinesrrr_pprint[s.        rEcseZdZdZeddZd ddZddZd!d d Zfd d Z fddZ ddZ ddZ ddZ d"ddZeddZddZddZZS)# 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)r*kindZ 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)r*rJrrrrs) getattr__init__objectinspectZ signature parametersvaluesrIZVAR_POSITIONALr'r8)clsZinitZinit_signaturerPrKrrr_get_param_namess   zBaseEstimator._get_param_namesTcs\t}|D]Ht|}|rNt|drN|}|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)rrBvalkeyrrr5sz+BaseEstimator.get_params..)dictrSrLrrr&update)rHroutvalueZ deep_itemsrrVrrs    zBaseEstimator.get_paramsc Ks|s|S|jdd}tt}|D]V\}}|d\}}}||krTtd||f|rf||||<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. TrrTzsInvalid parameter %s for estimator %s. Check the list of available parameters with `estimator.get_params().keys()`.)rrrXr& partition ValueErrorsetattr set_params) rHr?Z valid_paramsZ nested_paramsrWr[ZdelimZsub_keyZ sub_paramsrrrr_s"   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)ZcompactindentZindent_at_nameZn_max_elements_to_showr2r-z ^(\s*\S){%d}r1z[^\n]*\nr/) Z utils._pprintraZpformatr;r=r>rematchend) rHZ N_CHAR_MAXraZN_MAX_ELEMENTS_TO_SHOWZpprepr_Z n_nonblankZlimZregexZleft_limZ right_limZellipsisrrr__repr__s,   zBaseEstimator.__repr__csVzt}Wntk r,|j}YnXt|jdrNt| t dS|SdS)Nsklearn.)_sklearn_version) super __getstate__AttributeError__dict__r!r __module__ startswithrXr&r)rHstater%rrrm'szBaseEstimator.__getstate__cstt|jdr>|dd}|tkr>td|jj |tt zt |Wn t k rn|j|YnXdS)Nrjrkzpre-0.18zTrying 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.)rrprqpoprwarningswarnformatr%__name__ UserWarningrl __setstate__rnrorY)rHrrZpickle_versionrsrrrz2s zBaseEstimator.__setstate__cCstSN)rrGrrr _more_tagsAszBaseEstimator._more_tagscCs<i}tt|jD]"}t|dr||}||q|S)Nr|)reversedrOZgetmror%rr|rY)rHZcollected_tagsZ base_classZ more_tagsrrr _get_tagsDs    zBaseEstimator._get_tagscCsV|jd}|r||_dSt|ds&dS||jkrRtd|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`. rNn_features_in_zX has z features, but z is expecting z features as input.)shaperrr]r%rx)rHXresetZ n_featuresrrr_check_n_featuresOs   zBaseEstimator._check_n_features no_validationFc Ks|dkr:|dr(td|jjdt|f|}|}ndt|tr^|dkr^t|f|}|}n@|r|\}}t|f|}t|f|}nt||f|\}}||f}|ddr|j ||d|S) arValidate input data and set or check the `n_features_in_` attribute. Parameters ---------- X : {array-like, sparse matrix, dataframe} of shape (n_samples, n_features) The input samples. 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. - Otherwise, 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. **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. Returns ------- out : {ndarray, sparse matrix} or tuple of these The validated input. A tuple is returned if `y` is not None. N requires_yzThis z= estimator requires y to be passed, but the target y is None.rZ ensure_2dT)r) r~r]r%rxr r r:r getr) rHryrZvalidate_separatelyZ check_paramsrZZcheck_X_paramsZcheck_y_paramsrrr_validate_dataqs&+     zBaseEstimator._validate_datacCstddkrtd|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')rrn_repr_html_innerrGrrr _repr_html_szBaseEstimator._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"]`. r rGrrrrszBaseEstimator._repr_html_innercKs*dt|i}tddkr&t||d<|S)z8Mime bundle used by jupyter kernels to display estimatorz text/plainrrz text/html)r$rr )rHkwargsoutputrrr_repr_mimebundle_s  zBaseEstimator._repr_mimebundle_)T)r`)rTF)rxrp __qualname____doc__ classmethodrSrr_rirmrzr|r~rrpropertyrrr __classcell__rrrsrrFs$   , 1  " H rFc@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)rHrrrrrrrscores zClassifierMixin.scorecCsddiSNrTrrGrrrr|szClassifierMixin._more_tags)Nrxrprr_estimator_typerr|rrrrrs rc@s&eZdZdZdZdddZddZdS) RegressorMixinz:Mixin class for all regression estimators in scikit-learn. regressorNcCs$ddlm}||}||||dS)aReturn the coefficient of determination :math:`R^2` of the prediction. The coefficient :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)rHrrrrZy_predrrrrs*  zRegressorMixin.scorecCsddiSrrrGrrrr|,szRegressorMixin._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_rHrrrrr fit_predict4s zClusterMixin.fit_predictcCsdgiS)NZpreserves_dtyperrGrrrr|JszClusterMixin._more_tags)N)rxrprrrrr|rrrrr0s 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_rGrrr biclusters_QszBiclusterMixin.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)rrr6Znonzero)rHrAZrowscolumnsrrr get_indicesYs  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{)r;)rrArrrr5sz+BiclusterMixin.get_shape..)rr)rHrAindicesrrr get_shapeos 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 rr6Znewaxis)rHrAdatar Zrow_indZcol_indrrr get_submatrixs  zBiclusterMixin.get_submatrixN) rxrprrrrrrrrrrrrNs  rc@seZdZdZdddZdS)TransformerMixinz1Mixin class for all transformers in scikit-learn.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)rHrrZ fit_paramsrrr fit_transformszTransformerMixin.fit_transform)N)rxrprrrrrrrrsrc@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)rxrprrrrrrrrrsrc@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, dataframe} of shape (n_samples, n_features) 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)rxrprrrrrrrrrsrc@seZdZdgZdS)MetaEstimatorMixinr(N)rxrprZ_required_parametersrrrrrsrc@seZdZdZddZdS)MultiOutputMixinz2Mixin to mark estimators that support multioutput.cCsddiS)NZ multioutputTrrGrrrr|szMultiOutputMixin._more_tagsNrxrprrr|rrrrrsrc@seZdZdZddZdS)_UnstableArchMixinz=Mark estimators that are non-determinstic on 32bit or PowerPCcCsdtptdiS)NZnon_deterministic)ZppcZpowerpc)rplatformmachinerqrGrrrr|sz_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. rNrrLr(rrr 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 rc Csdt*tjdtdt|d}t|dd}W5QRXt|dd}|r`||kr\tdt|S|S)aReturns True if estimator is pairwise. - If the `_pairwise` attribute and the tag are present and consistent, then use the value and not issue a warning. - If the `_pairwise` attribute and the tag are present and not consistent, use the `_pairwise` value and issue a deprecation warning. - If only the `_pairwise` attribute is present and it is not False, issue a deprecation warning and use the `_pairwise` value. Parameters ---------- estimator : object Estimator object to test. Returns ------- out : bool True if the estimator is pairwise and False otherwise. ignore)categoryZ _pairwiseFZpairwiserVz_pairwise was deprecated in 0.24 and will be removed in 1.1 (renaming of 0.26). Set the estimator tags of your estimator instead)rucatch_warningsfilterwarnings FutureWarningrrLrrv)r(Zhas_pairwise_attributeZpairwise_attributeZ pairwise_tagrrr _is_pairwise3s   r)+rr!ru collectionsrrrOreZnumpyr6r2rZ_configrZutilsrZ utils._tagsrrrr r Zutils._estimator_html_reprr rrr$rErFrrrrrrrrrrrrrrrrrrsF        >2K$6N%