o tBh)@sdZddlZddlZddlmZddlZddlZddlZddlZ ddl m Z ddl m Z ddlmZddlmZdd lmZdd lmZdd lmZdd lmZdd lmZddlmZddlmZddlmZddlmZddddZdefddZGdddZ GdddZ!GdddZ"GdddZ#Gd d!d!Z$Gd"d#d#Z%Gd$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-d4d5Z.d6d7Z/dS)8z Base classes for all estimators.N) defaultdict) __version__) get_config) _IS_32BIT _DEFAULT_TAGS) check_X_y check_array)_check_y) _num_features_check_feature_names_in)_generate_get_feature_names_out)check_is_fittedestimator_html_repr)_get_feature_namesTsafec st|}|ttttfvr|fdd|DSt|dr!t|tr=s(t|St|tr1t dt dt |t|f|j }|j dd}| D] \}}t|dd||<qJ|d i|}|j dd}|D]}||} ||} | | ur|td ||fqf|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).0erc/var/www/html/riverr-enterprise-integrations-main/venv/lib/python3.10/site-packages/sklearn/base.py Aszclone.. 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 %sNr)typelisttupleset frozensethasattr isinstancecopydeepcopy TypeErrorrepr __class__ritemsr RuntimeError) estimatorrestimator_typeklassnew_object_paramsnameparam new_object params_setparam1param2rrrr s@    rc Cs>t}tjddddt}|}dd|dd}tt|D]_\}\}} t| tur8d|t | f} nd||| f} t | d krT| d d d | d d } |dkrw|t | dksdd| vrn| |t |}n | d|d7}| | |t | 7}q#tjdi|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 @) precision threshold edgeitemsz, r z%s=%siNi,...irK z, css|]}|dVqdS)r>N)rstrip)rlrrr sz_pprint..r)npget_printoptionsset_printoptionsr! enumeratesortedr,r floatstrlenappendjoinsplit) paramsoffsetprinteroptions params_listthis_line_lengthline_sepikv this_reprlinesrrr_pprintgs.       r]cseZdZdZeddZd"ddZddZd#d d Zfd d Z fddZ ddZ ddZ ddZ ddZ    d$ddZeddZddZd d!ZZS)% BaseEstimatorzBase class for all estimators in scikit-learn. Notes ----- All estimators should specify all the parameters that can be set at the class level in their ``__init__`` as explicit keyword arguments (no ``*args`` or ``**kwargs``). cCstt|jd|j}|tjurgSt|}dd|jD}|D]}|j|jkr0t d||fq t dd|DS)z%Get parameter names for the estimatordeprecated_originalcSs&g|]}|jdkr|j|jkr|qSself)r2kind VAR_KEYWORDrprrrrs z2BaseEstimator._get_param_names..zscikit-learn estimators should always specify their parameters in the signature of their __init__ (no varargs). %s with constructor %s doesn't follow this convention.cSsg|]}|jqSr)r2rdrrrrs) getattr__init__objectinspect signature parametersvaluesrbVAR_POSITIONALr-rJ)clsinitinit_signaturerkrerrr_get_param_namess     zBaseEstimator._get_param_namesTcs\t}|D]$t|}|r't|dr'|}|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)rrYvalkeyrrrEs"z+BaseEstimator.get_params..)dictrqrfr%rr,update)raroutvalue deep_itemsrrtrrs    zBaseEstimator.get_paramsc Ks|s|S|jdd}tt}|D]5\}}|d\}}}||vr4|}td|d|d|d|r=||||<qt||||||<q|D]\}} ||jd i| qL|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. TrrrzInvalid parameter z for estimator z. Valid parameters are: .Nr) rrrvr, partitionrq ValueErrorsetattr set_params) rarQ valid_params nested_paramsrurydelimsub_keylocal_valid_params sub_paramsrrrrs(   zBaseEstimator.set_paramsc Csddlm}d}|ddd|d}||}td|}||krv|d}d|}t||} t||ddd } d || | vrY|d 7}t||ddd } d } | t| t|| krv|d| d || d}|S) Nr)_EstimatorPrettyPrinterT)compactindentindent_at_namen_max_elements_to_showrBr:z ^(\s*\S){%d}rAz[^\n]*\nr?) utils._pprintrpformatrMrOrPrematchend) ra N_CHAR_MAXrN_MAX_ELEMENTS_TO_SHOWpprepr_ n_nonblanklimregexleft_lim right_limellipsisrrr__repr__s,   zBaseEstimator.__repr__csPzt}Wnty|j}Ynwt|jdr&t| t dS|S)Nsklearn.)_sklearn_version) super __getstate__AttributeError__dict__r'r __module__ startswithrvr,r)rastater+rrr:s zBaseEstimator.__getstate__csrt|jdr|dd}|tkrtd|jj |tt z t |WdSt y8|j|YdSw)Nrrzpre-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 rrpoprwarningswarnformatr+__name__ UserWarningr __setstate__rrrw)rarpickle_versionrrrrEs    zBaseEstimator.__setstate__cCstSNrr`rrr _more_tagsYszBaseEstimator._more_tagscCs<i}tt|jD]}t|dr||}||q |S)Nr)reversedrigetmror+r%rrw)racollected_tags base_class more_tagsrrr _get_tags\s   zBaseEstimator._get_tagsc Cszt|}Wn)ty/}z|s$t|dr$td|jjd|jd|WYd}~dSd}~ww|r7||_dSt|ds>dS||jkrTtd|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.)r r)r%r}r+rr)raXreset n_featuresrrrr_check_n_featuresgs8    zBaseEstimator._check_n_featuresc CsX|rt|}|dur||_dSt|drt|ddSt|dd}t|}|dur/|dur/dS|durD|durDtd|jjddS|durY|durYtd|jjddSt |t |ksht ||krd}t |}t |}t ||} t ||} dd } | r|d 7}|| | 7}| r|d 7}|| | 7}| s| s|d 7}t|tdSdS) 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 nameszqThe feature names should match those that were passed during fit. Starting version 1.2, an error will be raised. cSsDd}d}t|D]\}}||kr|d7}|S|d|d7}q|S)NrBr8z- ... z- rA)rI)namesoutput max_n_namesrXr2rrr 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%delattrrfrrr+rrMrFanyr#rJ FutureWarning) rarrfeature_names_infitted_feature_namesX_feature_namesmessagefitted_feature_names_setX_feature_names_setunexpected_names missing_namesrrrr_check_feature_namess\       z"BaseEstimator._check_feature_names no_validationFc Ksd|j||d|dur|drtd|jjdt|to#|dk}|dup0t|to0|dk}d|i}i||}|rC|rCtd|sT|rTt|fd d i|}|} nM|rc|sct|fi|}|} n>|r|\} } d| vrsi|| } t|fd d i| }d| vri|| } t|fd d i| }n t ||fi|\}}||f} |s| d d r|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.rr.z*Validation should be done on X, y or both. input_namery ensure_2dT) rrr}r+rr&rLr r r getr) rarrrvalidate_separately check_paramsno_val_Xno_val_ydefault_check_paramsrxcheck_X_paramscheck_y_paramsrrr_validate_datas<A   zBaseEstimator._validate_datacCstddkr td|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')rr_repr_html_innerr`rrr _repr_html_\s 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"]`. rr`rrrrlszBaseEstimator._repr_html_innercKs*dt|i}tddkrt||d<|S)z8Mime bundle used by jupyter kernels to display estimatorz text/plainrrz text/html)r*rr)rakwargsrrrr_repr_mimebundle_ss  zBaseEstimator._repr_mimebundle_)T)r)rrTF)rr __qualname____doc__ classmethodrqrrrrrrrrrrpropertyrrr __classcell__rrrrr^s,   , 4  .\ m r^c@&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)rarrrrrrrscores zClassifierMixin.scorecCddiSNrTrr`rrrrzClassifierMixin._more_tagsrrrrr_estimator_typerrrrrrr{s   rc@r) 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)rarrrry_predrrrrs ) zRegressorMixin.scorecCrrrr`rrrrrzRegressorMixin._more_tagsrrrrrrrs   .rc@r) ClusterMixinz7Mixin class for all cluster estimators in scikit-learn. 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. )fitlabels_rarrrrr fit_predicts zClusterMixin.fit_predictcCsdgiS)Npreserves_dtyperr`rrrrrzClusterMixin._more_tagsr)rrrrrrrrrrrrs   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_r`rrr biclusters_s zBiclusterMixin.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)rrrFnonzero)rarXrowscolumnsrrr 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)rM)rrXrrrrE'sz+BiclusterMixin.get_shape..)rr")rarXindicesrrr 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 csr) accept_sparseN)utils.validationr rrFnewaxis)rarXdatar row_indcol_indrrr get_submatrix)s  zBiclusterMixin.get_submatrixN) rrrrrrrr rrrrrrs  rc@eZdZdZdddZdS)TransformerMixinz1Mixin class for all transformers in scikit-learn.NcKs:|dur|j|fi||S|j||fi||S)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)r transform)rarr fit_paramsrrr fit_transformGszTransformerMixin.fit_transformr)rrrrrrrrrrDsrc@r)_OneToOneFeatureMixinzProvides `get_feature_names_out` for simple transformers. Assumes there's a 1-to-1 correspondence between input features and output features. 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. rrainput_featuresrrrget_feature_names_outps z+_OneToOneFeatureMixin.get_feature_names_outrrrrrrrrrrrisrc@r) _ClassNamePrefixFeaturesOutMixinzMixin class for transformers that generate their own names by prefixing. Assumes that `_n_features_out` is defined for the estimator. NcCst|dt||j|dS)alGet output feature names for transformation. 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 z6_ClassNamePrefixFeaturesOutMixin.get_feature_names_outrrrrrrrsrc@eZdZdZdZdddZdS) DensityMixinz7Mixin class for all density estimators in scikit-learn.DensityEstimatorNcCsdS)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.scorer)rrrrrrrrrrrrc@r) 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_predictr)rrrrrrrrrrr"r!r"c@seZdZdgZdS)MetaEstimatorMixinr.N)rrr_required_parametersrrrrr$sr$c@eZdZdZddZdS)MultiOutputMixinz2Mixin to mark estimators that support multioutput.cCr)N multioutputTrr`rrrrrzMultiOutputMixin._more_tagsNrrrrrrrrrr' r'c@r&)_UnstableArchMixinz=Mark estimators that are non-determinstic on 32bit or PowerPCcCsdtp tdiS)Nnon_deterministic)ppcpowerpc)rplatformmachinerr`rrrrsz_UnstableArchMixin._more_tagsNr)rrrrr+r*r+cCt|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. rNrrfr.rrr is_classifier r4cCr1)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. rNrr2r3rrr is_regressorr5r6cCr1)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. rNr#r2r3rrris_outlier_detector r5r7)0rr'r collectionsrr/rirnumpyrFrBr_configrutilsr utils._tagsrr r r r r rrrutils._estimator_html_reprrrrr*r]r^rrrrrrrrr"r$r'r+r4r6r7rrrrsT              G2e%7N%