3 [hgv@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$Gd%d&d&Z%Gd'd(d(Z&d)d*Z'd+d,Z(d-d.Z)d/d0Z*dS)1z Base classes for all estimators.N) defaultdict) __version__) get_config) _IS_32BIT) _DEFAULT_TAGS _safe_tags) check_X_y) check_array)estimator_html_repr)_deprecate_positional_argsT)safec st|}|ttttfkr.|fdd|DSt|d sDt|tr~sRtj|St|trft d nt dt |t|f|j }|j dd }x$|j D]\}}t|dd ||<qW|f|}|j dd }x4|D],}||} ||} | | k rtd ||fqW|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).0e)r 4/tmp/pip-build-zwgx3nbq/scikit-learn/sklearn/base.py 9szclone.. get_paramszCannot clone object. z"You should provide an instance of z*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.F)deep)r zWCannot clone object %s, as the constructor either does not set or modifies parameter %sz7Cannot clone object. You should provide an instance of zaCannot clone object. You should provide an instance of scikit-learn estimator instead of a class.)typelisttupleset frozensethasattr isinstancecopydeepcopy TypeErrorrepr __class__ritemsr RuntimeError) estimatorr Zestimator_typeklassZnew_object_paramsnameparamZ new_objectZ params_setZparam1Zparam2r)r rrs2      rc Cs>tj}tjddddt}|}dd|dd}xtt|jD]\}\}} t| tkrrd|t | f} nd||| f} t | d kr| d d d | dd } |dkr|t | dksd| kr|j |t |}n|j d|d7}|j | |t | 7}qHWtjf|dj |} dj dd| j 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 precision thresholdZ edgeitemsz, r z%s=%siNi,z...drK z, css|]}|jdVqdS)r,N)rstrip)rlrrr sz_pprint..i)npZget_printoptionsZset_printoptionsr enumeratesortedr"rfloatstrlenappendjoinsplit) paramsoffsetprinteroptionsZ 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``). cCsxt|jd|j}|tjkrgStj|}dd|jjD}x(|D] }|j|jkrBt d||fqBWt dd|DS)z%Get parameter names for the estimatorZdeprecated_originalcSs&g|]}|jdkr|j|jkr|qS)self)r&kind VAR_KEYWORD)rprrrrsz2BaseEstimator._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&)rrJrrrrs) getattr__init__objectinspect signature parametersvaluesrHVAR_POSITIONALr#r6)clsinitZinit_signaturerPrJrrr_get_param_namess    zBaseEstimator._get_param_namesTcs`t}xT|jD]Ht|}|rPt|drP|jj}|jfdd|D||<qW|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)rrBval)keyrrr3sz+BaseEstimator.get_params..)dictrUrKrrr"update)rGroutvalueZ deep_itemsr)rXrrs   zBaseEstimator.get_paramsc Ks|s|S|jdd}tt}xb|jD]V\}}|jd\}}}||krVtd||f|rh||||<q&t||||||<q&Wx$|jD]\}}||jf|qW|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. T)rrVzsInvalid parameter %s for estimator %s. Check the list of available parameters with `estimator.get_params().keys()`.)rrrYr" partition ValueErrorsetattr set_params) rGr=Z valid_paramsZ nested_paramsrXr\delimZsub_keyZ sub_paramsrrrr`s     zBaseEstimator.set_paramsc Csddlm}d}|ddd|d}|j|}tdj|j}||kr|d}d|}tj||j} tj||ddd j} d || | kr|d 7}tj||ddd j} d } | t| t|| kr|d| d || d}|S)Nr)_EstimatorPrettyPrinterT)compactindentZindent_at_nameZn_max_elements_to_showr0r*z ^(\s*\S){%d}r/z[^\n]*\nz...rg) Z utils._pprintrcpformatr9r;r<rematchend) rGZ N_CHAR_MAXrcZN_MAX_ELEMENTS_TO_SHOWpprepr_Z n_nonblankZlimregexZleft_limZ right_limZellipsisrrr__repr__s&   zBaseEstimator.__repr__c sVytj}Wntk r,|jj}YnXt|jjdrNt|j t dS|SdS)Nzsklearn.)_sklearn_version) super __getstate__AttributeError__dict__rr __module__ startswithrYr"r)rGstate)r!rrrr'szBaseEstimator.__getstate__c stt|jjdr>|jdd}|tkr>tjdj|jj |tt yt j |Wn t k rn|jj|YnXdS)Nzsklearn.rpzpre-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.)rrurvpoprwarningswarnformatr!__name__ UserWarningrq __setstate__rsrtrZ)rGrwZpickle_version)r!rrr~2s  zBaseEstimator.__setstate__cCstS)N)r)rGrrr _more_tagsAszBaseEstimator._more_tagscCs@i}x6ttj|jD]"}t|dr|j|}|j|qW|S)Nr)reversedrNgetmror!rrrZ)rGZcollected_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!r|)rGXresetZ n_featuresrrr_check_n_featuresOs   zBaseEstimator._check_n_features no_validationFc Ks|dkr:|jdr(td|jjdt|f|}|}ndt|tr^|dkr^t|f|}|}n@|r|\}}t|f|}t|f|}nt||f|\}}||f}|jddr|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) rr^r!r|r rr8r getr) rGryrZvalidate_separatelyZ check_paramsr[Zcheck_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')rrs_repr_html_inner)rGrrr _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 )rGkwargsoutputrrr_repr_mimebundle_s  zBaseEstimator._repr_mimebundle_)T)rb)rTF)r|ru __qualname____doc__ classmethodrUrr`rorrr~rrrrpropertyrrr __classcell__rr)r!rrFs  , 1  " G rFc@s&eZdZdZdZdddZddZdS) ClassifierMixinz0Mixin class for all classifiers in scikit-learn. classifierNcCs ddlm}|||j||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)rGrrrrrrrscores zClassifierMixin.scorecCsddiS)NrTr)rGrrrrszClassifierMixin._more_tags)N)r|rurr_estimator_typerrrrrrrs rc@s&eZdZdZdZdddZddZdS) RegressorMixinz:Mixin class for all regression estimators in scikit-learn. regressorNcCs$ddlm}|j|}||||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_score)r)rrr)rGrrrrZy_predrrrrs*  zRegressorMixin.scorecCsddiS)NrTr)rGrrrr,szRegressorMixin._more_tags)N)r|rurrrrrrrrrrs .rc@s&eZdZdZdZdddZddZdS) ClusterMixinz7Mixin class for all cluster estimators in scikit-learn.Z clustererNcCs|j||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_)rGrrrrr fit_predict4s zClusterMixin.fit_predictcCsdgiS)NZpreserves_dtyper)rGrrrrJszClusterMixin._more_tags)N)r|rurrrrrrrrrr0s 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|}tj|dtj|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)rrr4Znonzero)rGrAZrowscolumnsrrr get_indicesYs  zBiclusterMixin.get_indicescCs|j|}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|VqdS)N)r9)rrArrrr3sz+BiclusterMixin.get_shape..)rr)rGrAindicesrrr get_shapeos zBiclusterMixin.get_shapecCs@ddlm}||dd}|j|\}}||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. r)r Zcsr)Z accept_sparseN)utils.validationr rr4Znewaxis)rGrAdatar Zrow_indZcol_indrrr get_submatrixs  zBiclusterMixin.get_submatrixN) r|rurrrrrrrrrrrrNs  rc@seZdZdZdddZdS)TransformerMixinz1Mixin class for all transformers in scikit-learn.NcKs6|dkr|j|f|j|S|j||f|j|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)rGrrZ fit_paramsrrr fit_transformszTransformerMixin.fit_transform)N)r|rurrrrrrrrsrc@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 Nr)rGrrrrrrszDensityMixin.score)N)r|rurrrrrrrrrsrc@seZdZdZdZdddZdS) OutlierMixinzAMixin class for all outlier detection estimators in scikit-learn.outlier_detectorNcCs|j|j|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. )rr)rGrrrrrrszOutlierMixin.fit_predict)N)r|rurrrrrrrrrsrc@seZdZdgZdS)MetaEstimatorMixinr$N)r|rurZ_required_parametersrrrrrsrc@seZdZdZddZdS)MultiOutputMixinz2Mixin to mark estimators that support multioutput.cCsddiS)NZ multioutputTr)rGrrrrszMultiOutputMixin._more_tagsN)r|rurrrrrrrrsrc@seZdZdZddZdS)_UnstableArchMixinz=Mark estimators that are non-determinstic on 32bit or PowerPCcCsdtptjjdiS)NZnon_deterministicppcpowerpc)rr)rplatformmachinerv)rGrrrrsz_UnstableArchMixin._more_tagsN)r|rurrrrrrrrsrcCst|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. rNr)rK)r$rrr is_classifiers rcCst|dddkS)a Return True if the given estimator is (probably) a regressor. Parameters ---------- estimator : estimator instance Estimator object to test. Returns ------- out : bool True if estimator is a regressor and False otherwise. rNr)rK)r$rrr 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. rNr)rK)r$rrris_outlier_detector#s rc Csdtj*tjdtdt|d}t|dd}WdQRXt|dd}|r`||kr\tjdt|S|S) aReturns True if estimator is pairwise. - If the `_pairwise` attribute and the tag are present and consistent, then use the value and not issue a warning. - If the `_pairwise` attribute and the tag are present and not consistent, use the `_pairwise` value and issue a deprecation warning. - If only the `_pairwise` attribute is present and it is not False, issue a deprecation warning and use the `_pairwise` value. Parameters ---------- estimator : object Estimator object to test. Returns ------- out : bool True if the estimator is pairwise and False otherwise. ignore)categoryZ _pairwiseFNZpairwise)rXz_pairwise was deprecated in 0.24 and will be removed in 1.1 (renaming of 0.26). Set the estimator tags of your estimator instead)rycatch_warningsfilterwarnings FutureWarningrrKrrz)r$Zhas_pairwise_attributeZpairwise_attributeZ pairwise_tagrrr _is_pairwise3s   r)+rrry collectionsrrrNriZnumpyr4r0rZ_configrutilsrZ utils._tagsrrrr r Zutils._estimator_html_reprr r rr rErFrrrrrrrrrrrrrrrrrrsF        >2K$6N%