B ud+@sdZddlZddlZddlmZddlZddlZddlZddlZ ddl m Z ddl m Z ddlmZddlmZmZdd lmZdd lmZdd lmZdd lmZdd lmZddlmZddlmZddddZdefddZGdddZGdddZ 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*d.d/Z+d0d1Z,d2d3Z-d4d5Z.dS)6z Base classes for all estimators.N) defaultdict) __version__) get_config) _IS_32BIT) _DEFAULT_TAGS _safe_tags) check_X_y) check_array)_check_y) _num_features)_check_feature_names_in)estimator_html_repr)_get_feature_namesT)safec st|}|ttttfkr.|fdd|DSt|drBt|tr|sPt|St|trdt dnt dt |t|f|j }|j dd}x$| D]\}}t|dd||<qW|f|}|j dd}x4|D],}||} ||} | | k rtd ||fqW|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).0e)rY/work/yifan.wang/ringdown/master-ringdown-env/lib/python3.7/site-packages/sklearn/base.py @szclone.. 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.F)deep)rzWCannot clone object %s, as the constructor either does not set or modifies parameter %s)typelisttupleset frozensethasattr isinstancecopydeepcopy TypeErrorrepr __class__ritemsr RuntimeError) estimatorrZestimator_typeklassZnew_object_paramsnameparamZ new_objectZ params_setZparam1Zparam2r)rrrs4      rc Cs>t}tjddddt}|}dd|dd}xtt|D]\}\}} t| tkrrd|t | f} nd||| f} t | d kr| d d d | d d } |dkr|t | dksd| kr| |t |}n| d|d7}| | |t | 7}qHWtjf|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 thresholdZ edgeitemsz, r z%s=%siNi,z...irK z, css|]}|dVqdS)r0N)rstrip)rlrrr sz_pprint..)npZget_printoptionsZset_printoptionsr enumeratesortedr%rfloatstrlenappendjoinsplit) paramsoffsetprinteroptionsZ params_listZthis_line_lengthZline_sepikvZ this_reprlinesrrr_pprintfs.        rHcseZdZdZeddZd"ddZddZd#d d Zfd d Z fddZ ddZ ddZ ddZ ddZd$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``). cCsxt|jd|j}|tjkrgSt|}dd|jD}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))rrMrrrrs) getattr__init__objectinspect signature parametersvaluesrKVAR_POSITIONALr&r9)clsinitZinit_signaturerSrMrrr_get_param_namess    zBaseEstimator._get_param_namesTcs`t}xT|D]Ht|}|rPt|drP|}|fdd|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)rrEval)keyrrr6sz+BaseEstimator.get_params..)dictrXrNrrr%update)rJroutvalueZ deep_itemsr)r[rrs   zBaseEstimator.get_paramsc Ks|s|S|jdd}tt}xb|D]V\}}|d\}}}||krVtd||f|rh||||<q&t||||||<q&Wx$|D]\}}||jf|qW|S)a Set the parameters of this estimator. The method works on simple estimators as well as on nested objects (such as :class:`~sklearn.pipeline.Pipeline`). The latter have parameters of the form ``__`` so that it's possible to update each component of a nested object. Parameters ---------- **params : dict Estimator parameters. Returns ------- self : estimator instance Estimator instance. T)rrYzsInvalid parameter %s for estimator %s. Check the list of available parameters with `estimator.get_params().keys()`.)rrr\r% partition ValueErrorsetattr set_params) rJr@Z valid_paramsZ nested_paramsr[r_delimZsub_keyZ sub_paramsrrrrcs"    zBaseEstimator.set_paramsc Csddlm}d}|ddd|d}||}td|}||kr|d}d|}t||} t||ddd } d || | kr|d 7}t||ddd } d } | t| t|| kr|d| d || d}|S) Nr)_EstimatorPrettyPrinterT)compactindentZindent_at_nameZn_max_elements_to_showr3r-z ^(\s*\S){%d}r2z[^\n]*\nz...) Z utils._pprintrfpformatr<r>r?rematchend) rJZ N_CHAR_MAXrfZN_MAX_ELEMENTS_TO_SHOWpprepr_Z n_nonblankZlimregexZleft_limZ right_limellipsisrrr__repr__s*   zBaseEstimator.__repr__csVyt}Wntk r,|j}YnXt|jdrNt| t dS|SdS)Nzsklearn.)_sklearn_version) super __getstate__AttributeError__dict__r r __module__ startswithr\r%r)rJstate)r$rrrv:szBaseEstimator.__getstate__cstt|jdr>|dd}|tkr>td|jj |tt yt |Wn t k rn|j|YnXdS)Nzsklearn.rtzpre-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/modules/model_persistence.html#security-maintainability-limitations)rryrzpoprwarningswarnformatr$__name__ UserWarningru __setstate__rwrxr])rJr{Zpickle_version)r$rrrEs  zBaseEstimator.__setstate__cCstS)N)r)rJrrr _more_tagsYszBaseEstimator._more_tagscCs@i}x6tt|jD]"}t|dr||}||qW|S)Nr)reversedrQgetmror$rrr])rJZcollected_tagsZ base_classZ more_tagsrrr _get_tags\s   zBaseEstimator._get_tagsc Csy t|}WnNtk rZ}z0|sJt|drJtd|jjd|jd|dSd}~XYnX|rj||_dSt|dsxdS||jkrtd|d|jjd|jddS) aSet the `n_features_in_` attribute, or check against it. Parameters ---------- X : {ndarray, sparse matrix} of shape (n_samples, n_features) The input samples. reset : bool If True, the `n_features_in_` attribute is set to `X.shape[1]`. If False and the attribute exists, then check that it is equal to `X.shape[1]`. If False and the attribute does *not* exist, then the check is skipped. .. note:: It is recommended to call reset=True in `fit` and in the first call to `partial_fit`. All other methods that validate `X` should set `reset=False`. n_features_in_z%X does not contain any features, but z is expecting z featuresNzX has z features, but z features as input.)r r"rrar$rr)rJXresetZ n_featuresrrrr_check_n_featuresgs    zBaseEstimator._check_n_featuresc Cs\|r4t|}|dk r||_nt|dr0t|ddSt|dd}t|}|dkr\|dkr\dS|dk r|dkrtd|jjddS|dkr|dk rtd|jjddSt |t |kst ||krXd}t |}t |}t ||} t ||} dd } | r|d 7}|| | 7}| r8|d 7}|| | 7}| sL| sL|d 7}t|tdS) 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}x6t|D]*\}}||kr,|d7}P|d|d7}qW|S)Nr3r+z- ... z- r2)r8)namesoutputZ max_n_namesrDr)rrr 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. )rrrdelattrrNr}r~r$rr<r7anyrr9 FutureWarning) rJrrZfeature_names_inZfitted_feature_namesZX_feature_namesmessageZfitted_feature_names_setZX_feature_names_setZunexpected_namesZ missing_namesrrrr_check_feature_namessJ          z"BaseEstimator._check_feature_names no_validationFc Ks|j||d|dkr6|dr6td|jjdt|toF|dk}|dkp`t|to`|dk}|rt|rttdnt|s|rt|f|}|}nZ|r|st|f|}|}n@|r|\} } t|f| }t|f| }nt ||f|\}}||f}|s | dd r |j ||d|S) aF 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. **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 both `X` and `y` are validated. )rN requires_yzThis z= estimator requires y to be passed, but the target y is None.rz*Validation should be done on X, y or both.Z ensure_2dT) rrrar$rrr;r r r getr) rJryrZvalidate_separatelyZ check_paramsZno_val_XZno_val_yr^Zcheck_X_paramsZcheck_y_paramsrrr_validate_datas.9    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')rrw_repr_html_inner)rJrrr _repr_html_MszBaseEstimator._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)rJrrrr]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)rJkwargsrrrr_repr_mimebundle_ds  zBaseEstimator._repr_mimebundle_)T)re)rrTF)rry __qualname____doc__ classmethodrXrrcrsrvrrrrrrpropertyrrr __classcell__rr)r$rrIs$  - 4  .\ Y rIc@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)rJrrrrrrrscoreqs zClassifierMixin.scorecCsddiS)NrTr)rJrrrrszClassifierMixin._more_tags)N)rryrr_estimator_typerrrrrrrls 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_score)r)rrr)rJrrrrZy_predrrrrs)  zRegressorMixin.scorecCsddiS)NrTr)rJrrrrszRegressorMixin._more_tags)N)rryrrrrrrrrrrs .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_)rJrrrrr fit_predicts zClusterMixin.fit_predictcCsdgiS)NZpreserves_dtyper)rJrrrrszClusterMixin._more_tags)N)rryrrrrrrrrrrs 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_)rJrrr 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)rrr7Znonzero)rJrDrowscolumnsrrr 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|VqdS)N)r<)rrDrrrr6sz+BiclusterMixin.get_shape..)rr)rJrDindicesrrr 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. r)r Zcsr)Z accept_sparseN)utils.validationr rr7Znewaxis)rJrDdatar Zrow_indZcol_indrrr get_submatrixs  zBiclusterMixin.get_submatrixN) rryrrrrrrrrrrrrs  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)rJrrZ fit_paramsrrr fit_transform8szTransformerMixin.fit_transform)N)rryrrrrrrrr5src@seZdZdZdddZdS)_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 names are generated: `[x0, x1, ..., x(n_features_in_)]`. - 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. )r )rJZinput_featuresrrrget_feature_names_outasz+_OneToOneFeatureMixin.get_feature_names_out)N)rryrrrrrrrrZsrc@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)rJrrrrrr|szDensityMixin.score)N)rryrrrrrrrrrwsrc@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. )rr)rJrrrrrrszOutlierMixin.fit_predict)N)rryrrrrrrrrrsrc@seZdZdgZdS)MetaEstimatorMixinr'N)rryrZ_required_parametersrrrrrsrc@seZdZdZddZdS)MultiOutputMixinz2Mixin to mark estimators that support multioutput.cCsddiS)NZ multioutputTr)rJrrrrszMultiOutputMixin._more_tagsN)rryrrrrrrrrsrc@seZdZdZddZdS)_UnstableArchMixinz=Mark estimators that are non-determinstic on 32bit or PowerPCcCsdtptdiS)NZnon_deterministic)ppcZpowerpc)rplatformmachinerz)rJrrrrsz_UnstableArchMixin._more_tagsN)rryrrrrrrrrsrcCst|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)rN)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)rN)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)rN)r'rrris_outlier_detectors rc Csdt*tjdtdt|d}t|dd}WdQRXt|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 _pairwiseFNpairwise)r[z_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)r}catch_warningsfilterwarningsrrrNrr~)r'Zhas_pairwise_attributeZpairwise_attributeZ pairwise_tagrrr _is_pairwises   r)/rr r} collectionsrrrQrlnumpyr7r3r_configrutilsrZ utils._tagsrrrr r r r r Zutils._estimator_html_reprrrrr#rHrIrrrrrrrrrrrrrrrrrrrsN           G2W%7N%