o tBhg,@sddlmZddlmZddlmZddlZddlm Z dddd d Z d!d d Z Gd ddeZ ddZ GdddeZddZddZddddZd"ddZGdddeZdd ZdS)#)suppress)Counter) NamedTupleN is_scalar_nanFreturn_inverse return_countscCs&|jtkr t|||dSt|||dS)aHelper function to find unique values with support for python objects. Uses pure python method for object dtype, and numpy method for all other dtypes. Parameters ---------- values : ndarray Values to check for unknowns. return_inverse : bool, default=False If True, also return the indices of the unique values. return_counts : bool, default=False If True, also return the number of times each unique item appears in values. Returns ------- unique : ndarray The sorted unique values. unique_inverse : ndarray The indices to reconstruct the original array from the unique array. Only provided if `return_inverse` is True. unique_counts : ndarray The number of times each of the unique values comes up in the original array. Only provided if `return_counts` is True. r)dtypeobject_unique_python _unique_np)valuesr r rl/var/www/html/riverr-enterprise-integrations-main/venv/lib/python3.10/site-packages/sklearn/utils/_encode.py_unique s rcCstj|||d}d\}}|r|^}}|r|^}}|s|r"|d}|jrWt|drWt|tj}|d|d}|rB||||k<|rWt||d||<|d|d}|f}|ra||f7}|rh||f7}t|dkrr|dS|S)zHelper function to find unique values for numpy arrays that correctly accounts for nans. See `_unique` documentation for details.r)NNrNr)npuniquesizer searchsortednansumlen)rr r uniquesinversecountsnan_idxretrrrr2s0     rc@s*eZdZUdZeed<eed<ddZdS) MissingValuesz'Data class for missing data informationrnonecCs*g}|jr |d|jr|tj|S)z3Convert tuple to a list where None is always first.N)r!appendrr)selfoutputrrrto_listas   zMissingValues.to_listN)__name__ __module__ __qualname____doc__bool__annotations__r%rrrrr [s  r cCsndd|D}|s|tdddfSd|vr)t|dkr"tddd}n tddd}ntddd}||}||fS)a.Extract missing values from `values`. Parameters ---------- values: set Set of values to extract missing from. Returns ------- output: set Set with missing values extracted. missing_values: MissingValues Object with missing value information. cSs h|] }|dus t|r|qSNr.0valuerrr {sz#_extract_missing..F)rr!NrT)r r)rmissing_values_setoutput_missing_valuesr$rrr_extract_missingks  r3cs(eZdZdZfddZddZZS)_nandictz!Dictionary with support for nans.cs6t||D]\}}t|r||_dSq dSr,)super__init__itemsr nan_value)r#mappingkeyr/ __class__rrr6s z_nandict.__init__cC t|dr t|r |jSt|)Nr8)hasattrrr8KeyErrorr#r:rrr __missing__z_nandict.__missing__)r&r'r(r)r6rA __classcell__rrr;rr4s r4cs.tddt|Dtfdd|DS)z,Map values based on its position in uniques.cSsi|]\}}||qSrr)r.ivalrrr sz#_map_to_integer..csg|]}|qSrrr.vtablerr z#_map_to_integer..)r4 enumeraterarray)rrrrIr_map_to_integersrOcCszt|}t|\}}t|}||tj||jd}Wnty=tddtdd|DD}td|w|f}|rK|t ||f7}|rU|t ||f7}t |dkr_|dS|S)Nr css|]}|jVqdSr,)r()r.trrr sz!_unique_python..css|]}t|VqdSr,)typerGrrrrRszEEncoders require their input to be uniformly strings or numbers. Got rr) setr3sortedextendr%rrNr TypeErrorrO _get_countsr)rr r uniques_setmissing_valuesrtypesrrrrr s(   r T) check_unknownc Cst|jjdvr"zt||WSty!}z tdt|d}~ww|r4t||}|r4tdt|t||S)aHelper function to encode values into [0, n_uniques - 1]. Uses pure python method for object dtype, and numpy method for all other dtypes. The numpy method has the limitation that the `uniques` need to be sorted. Importantly, this is not checked but assumed to already be the case. The calling method needs to ensure this for all non-object values. Parameters ---------- values : ndarray Values to encode. uniques : ndarray The unique values in `values`. If the dtype is not object, then `uniques` needs to be sorted. check_unknown : bool, default=True If True, check for values in `values` that are not in `unique` and raise an error. This is ignored for object dtype, and treated as True in this case. This parameter is useful for _BaseEncoder._transform() to avoid calling _check_unknown() twice. Returns ------- encoded : ndarray Encoded values OUSz%y contains previously unseen labels: N) r kindrOr? ValueErrorstr_check_unknownrr)rrr\ediffrrr_encodes    rdc spd}|jjdvrgt|}t|\}}t|t\|}|jo&j }|jo-j }fdd|rS|s=|s=|rJtfdd|D}n tjt |t d}t |}|r^| d|rf| tjnIt |} tj| |dd }|r|jrt||}n tjt |t d}t|rt|} | r|jr|rt|} d || <|| }t |}|r||fS|S) a Helper function to check for unknowns in values to be encoded. Uses pure python method for object dtype, and numpy method for all other dtypes. Parameters ---------- values : array Values to check for unknowns. known_values : array Known values. Must be unique. return_mask : bool, default=False If True, return a mask of the same shape as `values` indicating the valid values. Returns ------- diff : list The unique values present in `values` and not in `know_values`. valid_mask : boolean array Additionally returned if ``return_mask=True``. Nr]cs$|vpjo |dupjot|Sr,)r!rr)r/)missing_in_uniquesrYrris_validsz _check_unknown..is_validcsg|]}|qSrrr-)rfrrrKrLz"_check_unknown..rPT assume_uniquer)r r^rTr3rr!rrNonesrr*listr"r setdiff1drin1disnanany) r known_values return_mask valid_mask values_setmissing_in_valuesrc nan_in_diff none_in_diff unique_values diff_is_nanis_nanr)rfrerYrrasJ           racs0eZdZdZfddZddZddZZS) _NaNCounterz$Counter with support for nan values.cst||dSr,)r5r6_generate_items)r#r7r;rrr6Csz_NaNCounter.__init__ccs>|D]}t|s |Vqt|dsd|_|jd7_qdS)z>Generate items without nans. Stores the nan counts separately. nan_countrrN)rr>r{)r#r7itemrrrrzFs z_NaNCounter._generate_itemscCr=)Nr{)r>rr{r?r@rrrrAPrBz_NaNCounter.__missing__)r&r'r(r)r6rzrArCrrr;rry@s   ryc Cs|jjdvr9t|}tjt|tjd}t|D]\}}tt ||||<Wdn1s1wYq|St |dd\}}tj ||dd}t |dr[t |dr[d|d<t |||} tj|tjd}|| ||<|S)zGet the count of each of the `uniques` in `values`. The counts will use the order passed in by `uniques`. For non-object dtypes, `uniques` is assumed to be sorted and `np.nan` is at the end. OUrPNT)r rgr)r r^ryrzerosrint64rMrr?risinrmr zeros_like) rrcounterr$rDr|rvruniques_in_valuesunique_valid_indicesrrrrXVs"   rX)FF)F) contextlibr collectionsrtypingrnumpyrrrrr r3dictr4rOr rdraryrXrrrrs    ))& *U