ZPh]BdZddlZddlmZddlmZddlmZmZddl m Z m Z ddl Z ddlmZddlmZdd lmZdd lmZdd lmZdd lmZd dlmZmZdZdZGddZdZ d%dZ!dZ"d&dZ#dZ$dZ%dZ&dZ'dZ(dZ)dZ*dZ+d Z,d!Z-e(e%e'e&e$e)d"Z.d#Z/d$Z0dS)'zUtilities for input validationN) OrderedDict)wraps) Parameter signature)IntegralReal)issparse)clone)NearestNeighbors) column_or_1d)type_of_target) _num_samples) _is_pandas_df check_array) over-samplingunder-samplingclean-samplingensemblebypass)binary multiclassmultilabel-indicatorc*eZdZdZdZdZdZdZdS)ArraysTransformerzAA class to convert sampler output arrays to their original types.cn|||_|||_dSN) _gets_propsx_propsy_propsselfXys Z/var/www/html/test/jupyter/venv/lib/python3.11/site-packages/imblearn/utils/_validation.py__init__zArraysTransformer.__init__#s0''** ''** c|||j}|||j}|jddkr-|jddvr |j|_||fS)Ntype dataframe>seriesr*)_transfrom_onerr lowerindexr!s r% transformzArraysTransformer.transform's   4< 0 0   4< 0 0 <  % % ' '; 6 64< < %'',<-<- gAG!t r'ci}|jj|d<t|dd|d<t|dd|d<t|dd|d<|S)Nr)columnsnamedtypes) __class____name__getattr)r"arraypropss r%rzArraysTransformer._gets_props2sZ0f "5)T::ivt44f !%488h r'c 2|d}|dkr|}n`|dkr(ddl}t|r(|jj||d}n|||d} ||d}n#t$r|j D]}|| rR||j dkrA|d|d kr/| d gt||z||<||d}Yn5wxYw|d kr)ddl}|||d|d  }n|}|S)Nr)listr*rr1)r1r3zdatetime64[ns]ztimedelta64[ns]NaTr+r2)dtyper2)r-tolistpandasr DataFramesparse from_spmatrixastype TypeErrorr1isnullallr< to_timedeltalenSeries)r"r7r8type_retpdcols r%r,z ArraysTransformer._transfrom_one:sf ##%% F??,,..CC k ! !     Dl)77uYGW7XXll5% 2BlCC 2jjx11 2 2 2 ;LLCC))--//LHN.>>>!(OC04EEE#%??E7SS]]3J#K#KCjjx11 2h      ))ExuV})MMCCC sB33B-E#"E#N)r5 __module__ __qualname____doc__r&r/rr,r'r%rr sVKK+++   #####r'rcBddg}tfd|DS)aCheck that the estimator exposes a KNeighborsMixin-like API. A KNeighborsMixin-like API exposes the following methods: (i) `kneighbors`, (ii) `kneighbors_graph`. Parameters ---------- estimator : object A scikit-learn compatible estimator. Returns ------- is_neighbors_object : bool True if the estimator exposes a KNeighborsMixin-like API. kneighborskneighbors_graphc38K|]}t|VdSr)hasattr).0attr estimators r% z'_is_neighbors_object..qs-IIDwy$''IIIIIIr')rE)rXneighbors_attributess` r%_is_neighbors_objectr[`s5 )*<= IIII4HIII I IIr'cpt|trt||zSt|S)aCheck the objects is consistent to be a k nearest neighbors. Several methods in `imblearn` relies on k nearest neighbors. These objects can be passed at initialisation as an integer or as an object that has KNeighborsMixin-like attributes. This utility will create or clone said object, ensuring it is KNeighbors-like. Parameters ---------- nn_name : str The name associated to the object to raise an error if needed. nn_object : int or KNeighborsMixin The object to be checked. additional_neighbor : int, default=0 Sometimes, some algorithm need an additional neighbors. Returns ------- nn_object : KNeighborsMixin The k-NN object. ) n_neighbors) isinstancerr r )nn_name nn_objectadditional_neighbors r%check_neighbors_objectrbts<0)X&&MI8K,KLLLL   r'cntj|d\}}tt||S)NT) return_counts)npuniquedictzip)r$rfcountss r%_count_class_samplerjs2Yq555NFF FF## $ $$r'Fct|}|dkrRtj|ddkrt d|d}nt |}|r||dkfn|S)aCheck the target types to be conform to the current samplers. The current samplers should be compatible with ``'binary'``, ``'multilabel-indicator'`` and ``'multiclass'`` targets only. Parameters ---------- y : ndarray The array containing the target. indicate_one_vs_all : bool, default=False Either to indicate if the targets are encoded in a one-vs-all fashion. Returns ------- y : ndarray The returned target. is_one_vs_all : bool, optional Indicate if the target was originally encoded in a one-vs-all fashion. Only returned if ``indicate_multilabel=True``. r)axiszImbalanced-learn currently supports binary, multiclass and binarized encoded multiclasss targets. Multilabel and multioutput targets are not supported.)r reanysum ValueErrorargmaxr )r$indicate_one_vs_alltype_ys r%check_target_typerts.A  F ''' 6!%%Q%--!# $ $ 9  HH!H   OO4G NAv// 0 0QNr'cbt|}|dkrBt|fd|D}nU|dks|dkrBt |fd|D}nt |S)z1Returns sampling target by targeting all classes.rc"i|] \}}||z  SrPrP)rVkeyvaluen_sample_majoritys r% z*_sampling_strategy_all..s2   /;UC"U*   r'rrci|]}|SrPrP)rVrwn_sample_minoritys r%rzz*_sampling_strategy_all..sSSSS"3SSSr')rjmaxvaluesitemsminkeysNotImplementedError)r$ sampling_type target_statssampling_strategyryr|s @@r%_sampling_strategy_allrs&q))L'' 3 3 5 566    ?K?Q?Q?S?S    * * *m?O.O.O 3 3 5 566SSSS|?P?P?R?RSSS!! r'c*|dkrtd|dks|dkrht|}t||jt |fd|D}nt|S)z=Returns sampling target by targeting the majority class only.rz@'sampling_strategy'='majority' cannot be used with over-sampler.rrrwc"i|] }|k| SrPrPrVrwclass_majorityr|s r%rzz/_sampling_strategy_majority..1   n$$ "$$$r')rprjr}getrr~rr)r$rrrrr|s @@r%_sampling_strategy_majorityrs'' N    * * *m?O.O.O*1-- \|/?@@@ 3 3 5 566     #((**    "! r'ct|}|dkrYt|t||jfd|D}nl|dks|dkrYt |t||jfd|D}nt|S)zJReturns sampling target by targeting all classes but not the majority.rrc.i|]\}}|k ||z SrPrP)rVrwrxrrys r%rzz3_sampling_strategy_not_majority..:   en$$ "U*$$$r'rrc"i|] }|k| SrPrPrs r%rzz3_sampling_strategy_not_majority..rr')rjr}r~rrrrr)r$rrrrryr|s @@@r%_sampling_strategy_not_majorityr'q))L'' 3 3 5 566\|/?@@@     , 2 2 4 4    * * *m?O.O.O 3 3 5 566\|/?@@@     #((**    "! r'ct|}|dkrYt|t||jfd|D}nl|dks|dkrYt|t||jfd|D}nt|S)zJReturns sampling target by targeting all classes but not the minority.rrc.i|]\}}|k ||z SrPrPrVrwrxclass_minorityrys r%rzz3_sampling_strategy_not_minority..rr'rrc"i|] }|k| SrPrP)rVrwrr|s r%rzz3_sampling_strategy_not_minority.. rr')rjr}r~rrrrr)r$rrrrryr|s @@@r%_sampling_strategy_not_minorityrrr'c*t|}|dkrYt|t||jfd|D}n"|dks|dkrt dt|S)z=Returns sampling target by targeting the minority class only.rrc.i|]\}}|k ||z SrPrPrs r%rzz/_sampling_strategy_minority..rr'rrzS'sampling_strategy'='minority' cannot be used with under-sampler and clean-sampler.)rjr}r~rrrrpr)r$rrrrrys @@r%_sampling_strategy_minorityrs&q))L'' 3 3 5 566\|/?@@@     , 2 2 4 4    * * *m?O.O.O 0   "! r'cj|dkrt||S|dks|dkrt||SdS)zWReturns sampling target auto for over-sampling and not-minority for under-sampling.rrrN)rr)r$rs r%_sampling_strategy_autor-sO''.q-@@@ * * *m?O.O.O.q-@@@/P.Or'cdt|}t|t|z }t|dkrt d|dt d|Drt d|i}|dkrt|t||j| D];\}}|||krt d||d |d |||z ||<.Ds& E EY9q= E E E E E Er'zfThe number of samples in a class cannot be negative.'sampling_strategy' contains some negative value: rrzWith over-sampling methods, the number of samples in a class should be greater or equal to the original number of samples. Originally, there is z samples and z samples are asked.rzWith under-sampling methods, the number of samples in a class should be less or equal to the original number of samples. Originally, there is rz'sampling_strategy' as a dict for cleaning methods is not supported. Please give a list of the classes to be targeted by the sampling.) rjsetrrGrprnr~r}rrr)rr$rr!set_diff_sampling_strategy_targetsampling_strategy_ class_samplers r%_sampling_strategy_dictr6s'q))L(+,=,B,B,D,D(E(EII)% ,--11 #4 # # #    E E*;*B*B*D*D E E EEE  UAR U U   '' L   ! !""" Ll.////'8'>'>'@'@ V V #L)< 555 B.:,-GBB$- BBB09< ;U/U | , , V * * *'8'>'>'@'@ 9 9 #L)< 555 B.:,-GBB$- BBB09 | , , 9 * * * (   "! r'c|dkrtdt|t|tz }t |dkrtd|dfd|DS)z[With cleaning methods, sampling_strategy can be a list to target the class of interest.rzQ'sampling_strategy' cannot be a list for samplers which are not cleaning methods.rrrcTi|]$}|t%SrP)rr~)rVrrs r%rzz+_sampling_strategy_list..s<   5A c,--//00   r')rprjrrrG)rr$rrrs @r%_sampling_strategy_listrns((( .   'q))L(+,=(>(>BB)% ,--11 #4 # # #       EV   r'c t|}|dkrtdt| |dkrt t jfd D}td|Drtdn|dkrt t jfd  D}t fd |Drtd ntd |S) zrTake a proportion of the majority (over-sampling) or minority (under-sampling) class in binary classification.rzg"sampling_strategy" can be a float only when the type of target is binary. For multi-class, use a dict.rrcNi|]!\}}|k |tz|z "SrPint)rVrwrxrryrs r%rzz,_sampling_strategy_float..sH   en$$ &)::UBCC$$$r'cg|]}|dk SrrPrs r% z,_sampling_strategy_float..sLLL9 QLLLr'zThe specified ratio required to remove samples from the minority class while trying to generate new samples. Please increase the ratio.rcHi|]\}}|k |tz SrPr)rVrwrxrr|rs r%rzz,_sampling_strategy_float..sC   en$$ &)::;;$$$r'c.g|]\}}||kSrPrP)rVtargetrrs r%rz,_sampling_strategy_float..s7   %FIL00   r'zThe specified ratio required to generate new sample in the majority class while trying to remove samples. Please increase the ratio.zD'clean-sampling' methods do let the user specify the sampling ratio.) r rprjr}r~rrrnr) rr$rrsrrrryr|rs ` @@@@@r%_sampling_strategy_floatrs A  F  @   'q))L'' 3 3 5 566\|/?@@@      , 2 2 4 4    LL0B0I0I0K0KLLL M M    * * * 3 3 5 566\|/?@@@      , 2 2 4 4        );)A)A)C)C      =   R    r'c |tvrtdtd|dtj|jdkr*tdtj|jd|dvr|St |t rx|tvrtdtd|d ttt||| St |tr=ttt||| St |tr=ttt||| St |t r\|d ks|dkrtd |dttt#||| St%|rF||fi|}ttt||| Sd S) aJSampling target validation for samplers. Checks that ``sampling_strategy`` is of consistent type and return a dictionary containing each targeted class with its corresponding number of sample. It is used in :class:`~imblearn.base.BaseSampler`. Parameters ---------- sampling_strategy : float, str, dict, list or callable, Sampling information to sample the data set. - When ``float``: For **under-sampling methods**, it corresponds to the ratio :math:`\alpha_{us}` defined by :math:`N_{rM} = \alpha_{us} \times N_{m}` where :math:`N_{rM}` and :math:`N_{m}` are the number of samples in the majority class after resampling and the number of samples in the minority class, respectively; For **over-sampling methods**, it correspond to the ratio :math:`\alpha_{os}` defined by :math:`N_{rm} = \alpha_{os} \times N_{m}` where :math:`N_{rm}` and :math:`N_{M}` are the number of samples in the minority class after resampling and the number of samples in the majority class, respectively. .. warning:: ``float`` is only available for **binary** classification. An error is raised for multi-class classification and with cleaning samplers. - When ``str``, specify the class targeted by the resampling. For **under- and over-sampling methods**, the number of samples in the different classes will be equalized. For **cleaning methods**, the number of samples will not be equal. Possible choices are: ``'minority'``: resample only the minority class; ``'majority'``: resample only the majority class; ``'not minority'``: resample all classes but the minority class; ``'not majority'``: resample all classes but the majority class; ``'all'``: resample all classes; ``'auto'``: for under-sampling methods, equivalent to ``'not minority'`` and for over-sampling methods, equivalent to ``'not majority'``. - When ``dict``, the keys correspond to the targeted classes. The values correspond to the desired number of samples for each targeted class. .. warning:: ``dict`` is available for both **under- and over-sampling methods**. An error is raised with **cleaning methods**. Use a ``list`` instead. - When ``list``, the list contains the targeted classes. It used only for **cleaning methods**. .. warning:: ``list`` is available for **cleaning methods**. An error is raised with **under- and over-sampling methods**. - When callable, function taking ``y`` and returns a ``dict``. The keys correspond to the targeted classes. The values correspond to the desired number of samples for each class. y : ndarray of shape (n_samples,) The target array. sampling_type : {{'over-sampling', 'under-sampling', 'clean-sampling'}} The type of sampling. Can be either ``'over-sampling'``, ``'under-sampling'``, or ``'clean-sampling'``. **kwargs : dict Dictionary of additional keyword arguments to pass to ``sampling_strategy`` when this is a callable. Returns ------- sampling_strategy_converted : dict The converted and validated sampling target. Returns a dictionary with the key being the class target and the value being the desired number of samples. z!'sampling_type' should be one of z. Got 'z instead.rlz4The target 'y' needs to have more than 1 class. Got z class instead)rrzO   '(9:1mLLRRTT U U    %t , ,  *+.inner_f..ks6D##r'zPass z, z` as keyword args. From version 0.9 passing these as positional arguments will result in an errorci|]\}}|| SrPrP)rVkrs r%rzz?_deprecate_positional_args..inner_f..wsFFF&!Sq#FFFr'rP)rGrhwarningswarnjoin FutureWarningupdate parameters)argsr extra_argsargs_msgall_argsf kwonly_argssigs r%inner_fz+_deprecate_positional_args..inner_ffsYYX. >>!$[*%=tZKLL?Q!R!RH M)DIIh//)))      FFC,E,EFFFGGGq{{6{{r') rrrkindrPOSITIONAL_OR_KEYWORDappend KEYWORD_ONLYr)rr2paramrrrrs` @@@r%_deprecate_positional_argsrQs A,,CKH~++--%% e :8 8 8 OOD ! ! ! ! Z91 1 1   t $ $ $ 1XXX& Nr'ct|}|dkrtd|dt|r|St|dddgdS) z+Check X and do not check it if a dataframe.rlzFound array with z, sample(s) while a minimum of 1 is required.NcsrcscF)r< accept_sparseensure_all_finite)rrprr)r#rs r%_check_Xr}sqQI1}} W W W W   Q  eU^u   r'r)F)1rOr collectionsr functoolsrinspectrrnumbersrrnumpyre scipy.sparser sklearn.baser sklearn.neighborsr sklearn.utilsr sklearn.utils.multiclassr sklearn.utils.validationrutils._sklearn_compatrrr TARGET_KINDrr[rbrjrtrrrrrrrrrrrrrrPr'r%rsh$$ ######((((((((""""""""!!!!!!......&&&&&&333333111111>>>>>>>> ? ========@JJJ(<%%% #O#O#O#OL"*44,AAA555p2000fJ J J \,+33 ! # )))X     r'