!h%dZddlmZddlZddlmZddlZddlm Z ddl m Z ddl m Z ddlmZmZmZmZmZerdd lmZmZmZdd lmZmZdd lmZmZmZmZd Z d(dZ!dde dfd)d Z"de fd*d#Z#de dfd+d%Z$de dfd,d'Z%dS)-z" data hash pandas / numpy objects ) annotationsN) TYPE_CHECKING)hash_object_array) is_list_like)CategoricalDtype) ABCDataFrameABCExtensionArrayABCIndex ABCMultiIndex ABCSeries)HashableIterableIterator) ArrayLikenpt) DataFrameIndex MultiIndexSeries0123456789123456arraysIterator[np.ndarray] num_itemsintreturnnpt.NDArray[np.uint64]c  t|}n0#t$r#tjgtjcYSwxYwt j|g|}tjd}tj|tjdz}d}t|D]3\}}||z }||z}||z}|tjd|z|zz }|}4|dz|ks Jd|tjdz }|S) z Parameters ---------- arrays : Iterator[np.ndarray] num_items : int Returns ------- np.ndarray[uint64] Should be the same as CPython's tupleobject.c )dtypeiCBixV4riXBzFed in wrong num_itemsi|) next StopIterationnparrayuint64 itertoolschain zeros_like enumerate) rrfirstmultoutlast_iia inverse_is Rc:\xampp_lite_8_4\www\timesheet\venv\Lib\site-packages\pandas/core/util/hashing.pycombine_hash_arraysr1/s%-V  ---x"),,,,,,-_eWf - -F 9W  D -  8!4!4 4C F&!!1M  q t   %)+i7888 A: " " "$< " " "29U  C Js *??Tutf8objIndex | DataFrame | Seriesindexboolencodingstrhash_key str | None categorizercddlm}tttr|t ddStt r=tj dd}||dd}nWttrztj dd}|r7fd d D}tj |g|} t| d }||jdd}nttrfd D} t#j} |r7fd d D} | dz } tj | | } d| D} t| | }||jdd}nt'dt)|S)a> Return a data hash of the Index/Series/DataFrame. Parameters ---------- obj : Index, Series, or DataFrame index : bool, default True Include the index in the hash (if Series/DataFrame). encoding : str, default 'utf8' Encoding for data & key when strings. hash_key : str, default _default_hash_key Hash_key for string key to encode. categorize : bool, default True Whether to first categorize object arrays before hashing. This is more efficient when the array contains duplicate values. Returns ------- Series of uint64, same length as the object Examples -------- >>> pd.util.hash_pandas_object(pd.Series([1, 2, 3])) 0 14639053686158035780 1 3869563279212530728 2 393322362522515241 dtype: uint64 r)rNr$F)rcopyr=)r5rr=c3TK|]"}tjdjV#dSF)r5r7r9r;Nhash_pandas_objectr5_values.0_r;r7r9r3s r0 z%hash_pandas_object..s^  #I%%)        Nc3LK|]\}}t|jVdSrI) hash_arrayrC)rErFseriesr;r7r9s r0rGz%hash_pandas_object..sK  6 v~x: F F      rHc3TK|]"}tjdjV#dSr@rArDs r0rGz%hash_pandas_object..s^ $ $#I%%)   $ $ $ $ $ $rHrc3K|]}|VdSrI)rExs r0rGz%hash_pandas_object..s"))Aa))))))rHzUnexpected type for hashing )pandasr_default_hash_key isinstancer hash_tuplesr rLrCastyper r%r&r1r5ritemslencolumns TypeErrortype)r3r5r7r9r;rhser index_iterrhashesrindex_hash_generator_hashess` ``` r0rBrBSsF$#}%%7Dvk#x::(QVWWWW C " "4D s{Hh C C J J 5 K  fQc>>> C # #.D s{Hh C C J J 5 K    /           J_aS*55F#FA..AfQcixeDDD C & &D       YY[[    $$  * $ $ $ $ $ $ $  $ $ $  NI of.BCCG)))))F  2 2fQcixeDDDBtCyyBBCCC JrHvals+MultiIndex | Iterable[tuple[Hashable, ...]]cDt|stdddlmm}t |t s|j|n|fdtj D}fd|D}t|t|}|S)a Hash an MultiIndex / listlike-of-tuples efficiently. Parameters ---------- vals : MultiIndex or listlike-of-tuples encoding : str, default 'utf8' hash_key : str, default _default_hash_key Returns ------- ndarray[np.uint64] of hashed values z'must be convertible to a list-of-tuplesr) Categoricalrc g|]=}j|tj|d>S)F categoriesordered) _simple_newcodesrlevels)rElevelremis r0 zhash_tuples..s[   HUO  %(8% H H H  rHc3HK|]}|dVdS)Fr7r9r;N)_hash_pandas_object)rEcatr7r9s r0rGzhash_tuples..sM  HQVWWrH) rrZrRrerrTr from_tuplesrangenlevelsr1rX) rbr7r9rcat_valsr_r\rerns `` @@r0rUrUs$   CABBB dM * * #Z #D ) )  2:&& HF FCMM22A HrHrc<t|dstdt|tr||||St|t js%tdt|jdt||||S)a Given a 1d array, return an array of deterministic integers. Parameters ---------- vals : ndarray or ExtensionArray encoding : str, default 'utf8' Encoding for data & key when strings. hash_key : str, default _default_hash_key Hash_key for string key to encode. categorize : bool, default True Whether to first categorize object arrays before hashing. This is more efficient when the array contains duplicate values. Returns ------- ndarray[np.uint64, ndim=1] Hashed values, same length as the vals. Examples -------- >>> pd.util.hash_array(np.array([1, 2, 3])) array([ 6238072747940578789, 15839785061582574730, 2185194620014831856], dtype=uint64) rzmust pass a ndarray-likerqz6hash_array requires np.ndarray or ExtensionArray, not z!. Use hash_pandas_object instead.) hasattrrZrTr rrr"ndarrayr[__name__ _hash_ndarray)rbr7r9r;s r0rLrLs> 4 ! !42333$)** ''Z(    dBJ ' '  FDzz" F F F   x: > >>rH np.ndarrayc|j}tj|tjr6t |j|||}t |j|||}|d|zzS|tkr|d}nt|j tj tj fr,| ddd}n(t|j tjrA|jdkr6| d|jjd}n|rbdd lm}m}m} | |d \} } t)|| d }|| |} | ||d S t/|||}nQ#t0$rDt/|t2t4||}YnwxYw||d z z}|tjdz}||dz z}|tjdz}||dz z}|S)z! See hash_array.__doc__. u8i8Fr>ur)rer factorize)sortrgrqle9z lb&&& )rr" issubdtype complex128r|realimagr6rV issubclassr[ datetime64 timedelta64viewnumberitemsizerRrerrrrjrrrrZr8objectr$) rbr7r9r;r hash_real hash_imagrerrrkrhrss r0r|r|sz JE }UBM***!$)XxLL !$)XxLL 2 >)) }}{{4   EJ ? @ @yy%%d%77 EJ * *u~/B/Byy2TZ02233::4@@             !* $U ; ; ; E:$j0A0A5QQQE))%77C**!H+  $T8X>>DD   $ C  ''//8DDD  DBJDBI( ) ))DDBJDBI( ) ))DDBJD KsF--A G;:G;)rrrrrr) r3r4r5r6r7r8r9r:r;r6rr)rbrcr7r8r9r8rr) rbrr7r8r9r8r;r6rr) rbr}r7r8r9r8r;r6rr)&__doc__ __future__rr%typingrnumpyr"pandas._libs.hashingrpandas.core.dtypes.commonrpandas.core.dtypes.dtypesrpandas.core.dtypes.genericrr r r r collections.abcr rrpandas._typingrrrRrrrrrSr1rBrUrLr|rPrHr0rs(#""""" 222222222222666666  '!!!!L, aaaaaL%/ / / / / h% .?.?.?.?.?f% 9999999rH