B \1K@sHdZddlZddlZddlmZddlZddlZddlm Z ddl m Z ddl m Z ddlmZdd lmZd d Zd+d dZdefddZGdddeZGdddeZGdddeZGdddeZGdddeZGdddeZGdddeZGdd d eZGd!d"d"eZGd#d$d$eZ d%d&Z!d'd(Z"d)d*Z#dS),z Base classes for all estimators.N) defaultdict)sparse)six) signature) _IS_32BIT) __version__cCsRt|tjst|dr>t|r&|jn|}|jd|jdfS|d|dfSdS)z?Returns first and last element of numpy array or sparse matrix.datar)rr)r r N) isinstancenpZndarrayhasattrrZissparser Zflat)Zarrr r+lib/python3.7/site-packages/sklearn/base.py_first_and_last_elementsrTc st|}|ttttfkr.|fdd|DSt|ds^sFt|Stdt |t|f|j }|j dd}x&t |D]\}}t|dd||<q|W|f|}|j dd}x4|D],}||} ||} | | k rtd||fqW|S) aConstructs a new 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 fit on any data. Parameters ---------- estimator : estimator object, or list, tuple or set of objects The estimator or group of estimators to be cloned safe : boolean, optional If safe is false, clone will fall back to a deep copy on objects that are not estimators. csg|]}t|dqS))safe)clone).0e)rrr 4szclone.. get_paramszCannot clone object '%s' (type %s): it does not seem to be a scikit-learn estimator as it does not implement a 'get_params' methods.F)deep)rzWCannot clone object %s, as the constructor either does not set or modifies parameter %s)typelisttupleset frozensetr copydeepcopy TypeErrorrepr __class__rr iteritemsr RuntimeError) estimatorrZestimator_typeklassZnew_object_paramsnameZparamZ new_objectZ params_setZparam1Zparam2r)rrr s*      rc Cs@t}tjddddt}|}dd|dd}xttt|D]\}\}} t| t krtd|t | f} nd||| f} t | d kr| d d d | d d } |dkr|t | dksd| kr| |t |}n| d|d7}| | |t | 7}qJWtjf|d |} d dd| dD} | S)aMPretty print the dictionary 'params' Parameters ---------- params : dict The dictionary to pretty print offset : int The offset in characters to add at the begin of each line. printer : callable The function to convert entries to strings, typically the builtin str or repr @)Z precisionZ thresholdZ edgeitemsz, r z%s=%siNi,z...irK z, css|]}|dVqdS)r*N)rstrip)rlrrr ~sz_pprint..)r Zget_printoptionsZset_printoptionsr enumeratesortedrr"rfloatstrlenappendjoinsplit) paramsoffsetZprinterZoptionsZ params_listZthis_line_lengthZline_sepikvZ this_reprlinesrrr_pprintPs.         r?csReZdZdZeddZdddZddZd d Zfd d Z fd dZ Z S) 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``). cCsvt|jd|j}|tjkrgSt|}dd|jD}x(|D] }|j|jkr@td||fq@Wt dd|DS)z%Get parameter names for the estimatorZdeprecated_originalcSs&g|]}|jdkr|j|jkr|qS)self)r&kindZ 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&)rrCrrrrs) getattr__init__objectr parametersvaluesrBZVAR_POSITIONALr#r2)clsZinitZinit_signaturerGrCrrr_get_param_namess   zBaseEstimator._get_param_namesTcsbt}xV|D]Jt|d}|rRt|drR|}|fdd|D||<qW|S)aoGet parameters for this estimator. Parameters ---------- deep : boolean, optional If True, will return the parameters for this estimator and contained subobjects that are estimators. Returns ------- params : mapping of string to any Parameter names mapped to their values. Nrc3s"|]\}}d||fVqdS)__Nr)rr<val)keyrrr0sz+BaseEstimator.get_params..)dictrJrDr ritemsupdate)rAroutvalueZ deep_itemsr)rMrrs   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 pipelines). The latter have parameters of the form ``__`` so that it's possible to update each component of a nested object. Returns ------- self T)rrKzsInvalid parameter %s for estimator %s. Check the list of available parameters with `estimator.get_params().keys()`.)rrrNrO partition ValueErrorsetattr set_params) rAr9Z valid_paramsZ nested_paramsrMrRZdelimZsub_keyZ sub_paramsrrrrVs     zBaseEstimator.set_paramscCs(|jj}d|t|jddt|dfS)Nz%s(%s)F)r)r:)r!__name__r?rr5)rA class_namerrr__repr__szBaseEstimator.__repr__csZytt|}Wntk r0|j}YnXt|jdrRt | t dS|SdS)Nzsklearn.)_sklearn_version) superr@ __getstate__AttributeError__dict__rr __module__ startswithrNrOr)rAstate)r!rrr\szBaseEstimator.__getstate__csxt|jdr>|dd}|tkr>td|jj |tt yt t | |Wn tk rr|j|YnXdS)Nzsklearn.rZzpre-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.)rr_r`poprwarningswarnformatr!rW UserWarningr[r@ __setstate__r]r^rP)rAraZpickle_version)r!rrrgs  zBaseEstimator.__setstate__)T) rWr_ __qualname____doc__ classmethodrJrrVrYr\rg __classcell__rr)r!rr@s  % r@c@seZdZdZdZdddZdS)ClassifierMixinz0Mixin class for all classifiers in scikit-learn. classifierNcCs ddlm}|||||dS)aReturns 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, shape = (n_samples, n_features) Test samples. y : array-like, shape = (n_samples) or (n_samples, n_outputs) True labels for X. sample_weight : array-like, shape = [n_samples], optional Sample weights. Returns ------- score : float Mean accuracy of self.predict(X) wrt. y. r)accuracy_score) sample_weight)metricsrnpredict)rAXyrornrrrscore s zClassifierMixin.score)N)rWr_rhri_estimator_typertrrrrrlsrlc@seZdZdZdZdddZdS)RegressorMixinz:Mixin class for all regression estimators in scikit-learn. regressorNcCs"ddlm}|||||ddS)aReturns the coefficient of determination R^2 of the prediction. The coefficient R^2 is defined as (1 - u/v), where u is the residual sum of squares ((y_true - y_pred) ** 2).sum() and 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 R^2 score of 0.0. Parameters ---------- X : array-like, shape = (n_samples, n_features) Test samples. For some estimators this may be a precomputed kernel matrix instead, 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, shape = (n_samples) or (n_samples, n_outputs) True values for X. sample_weight : array-like, shape = [n_samples], optional Sample weights. Returns ------- score : float R^2 of self.predict(X) wrt. y. r)r2_scoreZvariance_weighted)roZ multioutput)rprxrq)rArrrsrorxrrrrt*s zRegressorMixin.score)N)rWr_rhrirurtrrrrrv&srvc@seZdZdZdZdddZdS) ClusterMixinz7Mixin class for all cluster estimators in scikit-learn.Z clustererNcCs|||jS)anPerforms clustering on X and returns cluster labels. Parameters ---------- X : ndarray, shape (n_samples, n_features) Input data. y : Ignored not used, present for API consistency by convention. Returns ------- labels : ndarray, shape (n_samples,) cluster labels )fitZlabels_)rArrrsrrr fit_predictSs zClusterMixin.fit_predict)N)rWr_rhrirur{rrrrryOsryc@s4eZdZdZeddZddZddZdd Zd S) BiclusterMixinz8Mixin class for all bicluster estimators in scikit-learncCs |j|jfS)z{Convenient way to get row and column indicators together. Returns the ``rows_`` and ``columns_`` members. )rows_columns_)rArrr biclusters_lszBiclusterMixin.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 : np.array, dtype=np.intp Indices of rows in the dataset that belong to the bicluster. col_ind : np.array, dtype=np.intp Indices of columns in the dataset that belong to the bicluster. r)r}r~r Znonzero)rAr;Zrowscolumnsrrr get_indicests  zBiclusterMixin.get_indicescCs||}tdd|DS)zShape of the i'th bicluster. Parameters ---------- i : int The index of the cluster. Returns ------- shape : (int, int) Number of rows and columns (resp.) in the bicluster. css|]}t|VqdS)N)r5)rr;rrrr0sz+BiclusterMixin.get_shape..)rr)rAr;indicesrrr get_shapes zBiclusterMixin.get_shapecCs@ddlm}||dd}||\}}||ddtjf|fS)aReturns the submatrix corresponding to bicluster `i`. Parameters ---------- i : int The index of the cluster. data : array The data. Returns ------- submatrix : array The submatrix corresponding to bicluster i. Notes ----- Works with sparse matrices. Only works if ``rows_`` and ``columns_`` attributes exist. r) check_arrayZcsr)Z accept_sparseN)Zutils.validationrrr Znewaxis)rAr;r rZrow_indZcol_indrrr get_submatrixs  zBiclusterMixin.get_submatrixN) rWr_rhripropertyrrrrrrrrr|is  r|c@seZdZdZdddZdS)TransformerMixinz1Mixin class for all transformers in scikit-learn.NcKs6|dkr|j|f||S|j||f||SdS)aFit 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 : numpy array of shape [n_samples, n_features] Training set. y : numpy array of shape [n_samples] Target values. Returns ------- X_new : numpy array of shape [n_samples, n_features_new] Transformed array. N)rzZ transform)rArrrsZ fit_paramsrrr fit_transformszTransformerMixin.fit_transform)N)rWr_rhrirrrrrrsrc@seZdZdZdZdddZdS) DensityMixinz7Mixin class for all density estimators in scikit-learn.ZDensityEstimatorNcCsdS)zReturns the score of the model on the data X Parameters ---------- X : array-like, shape = (n_samples, n_features) Returns ------- score : float Nr)rArrrsrrrrts zDensityMixin.score)N)rWr_rhrirurtrrrrrsrc@seZdZdZdZdddZdS) OutlierMixinzAMixin class for all outlier detection estimators in scikit-learn.outlier_detectorNcCs|||S)aPerforms fit on X and returns labels for X. Returns -1 for outliers and 1 for inliers. Parameters ---------- X : ndarray, shape (n_samples, n_features) Input data. y : Ignored not used, present for API consistency by convention. Returns ------- y : ndarray, shape (n_samples,) 1 for inliers, -1 for outliers. )rzrq)rArrrsrrrr{szOutlierMixin.fit_predict)N)rWr_rhrirur{rrrrrsrc@seZdZdZdS)MetaEstimatorMixinz4Mixin class for all meta estimators in scikit-learn.N)rWr_rhrirrrrrsrc@seZdZdZddZdS)_UnstableArchMixinz=Mark estimators that are non-determinstic on 32bit or PowerPCcCsdtptdiS)NZnon_deterministic)ZppcZpowerpc)rplatformmachiner`)rArrr _more_tags sz_UnstableArchMixin._more_tagsN)rWr_rhrirrrrrrsrcCst|dddkS)aReturns 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. ruNrm)rD)r$rrr is_classifiers rcCst|dddkS)aReturns True if the given estimator is (probably) a regressor. Parameters ---------- estimator : object Estimator object to test. Returns ------- out : bool True if estimator is a regressor and False otherwise. ruNrw)rD)r$rrr is_regressors rcCst|dddkS)aReturns True if the given estimator is (probably) an outlier detector. Parameters ---------- estimator : object Estimator object to test. Returns ------- out : bool True if estimator is an outlier detector and False otherwise. ruNr)rD)r$rrris_outlier_detector/s r)T)$rirrc collectionsrrZnumpyr ZscipyrZ externalsrZ utils.fixesrZutilsrr-rrrr r?rFr@rlrvryr|rrrrrrrrrrrrs6       03!)L!