o ŀg%@sdZddlmZddlZddlmZddlZddlm Z ddl m Z ddl m Z ddlmZmZmZmZmZerVdd lmZmZmZdd lmZmZdd lmZmZmZmZd Z d-ddZ!dde dfd.d!d"Z"de fd/d%d&Z#de dfd0d(d)Z$de dfd1d+d,Z%dS)2z" data hash pandas / numpy objects ) annotationsN) TYPE_CHECKING)hash_object_array) is_list_like)CategoricalDtype) ABCDataFrameABCExtensionArrayABCIndex ABCMultiIndex ABCSeries)HashableIterableIterator) ArrayLikenpt) DataFrameIndex MultiIndexSeries0123456789123456arraysIterator[np.ndarray] num_itemsintreturnnpt.NDArray[np.uint64]c Cszt|}WntytjgtjdYSwt|g|}td}t|td}d}t|D]\}}||}||N}||9}|td||7}|}q4|d|ks\Jd|td7}|S) z Parameters ---------- arrays : Iterator[np.ndarray] num_items : int Returns ------- np.ndarray[uint64] Should be the same as CPython's tupleobject.c )dtypeiCBixV4riXBzFed in wrong num_itemsi|) next StopIterationnparrayuint64 itertoolschain zeros_like enumerate) rrfirstmultoutlast_iia inverse_ir.L/var/www/html/myenv/lib/python3.10/site-packages/pandas/core/util/hashing.pycombine_hash_arrays/s$   r0Tutf8objIndex | DataFrame | Seriesindexboolencodingstrhash_key str | None categorizercs|ddlm}dur tttr|tdddSttr8tjj ddd}||ddd}|Stt rotjj ddd}|rdfd d d D}t |g|} t | d }||jddd}|Sttrfd d D} tj} |rfdd d D} | d7} t | | } dd | D} t | | }||jddd}|Stdt)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;)r4rr;c3&|]}tjddjVqdSF)r4r6r8r:Nhash_pandas_objectr4_values.0_r:r6r8r2r.r/  z%hash_pandas_object..Nc3s$|] \}}t|jVqdSrH) hash_arrayrA)rCrDseries)r:r6r8r.r/rFs  c3r=r>r?rBrEr.r/rFrGrcss|]}|VqdSrHr.)rCxr.r.r/rFszUnexpected type for hashing )pandasr_default_hash_key isinstancer hash_tuplesr rJrAastyper r#r$r0r4ritemslencolumns TypeErrortype)r2r4r6r8r:rhser index_iterrhashesrindex_hash_generator_hashesr.rEr/r@SsN #  2      r@vals+MultiIndex | Iterable[tuple[Hashable, ...]]cszt|stdddlmm}t|ts||n|fddtj D}fdd|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 s,g|]}j|tj|ddqS)F categoriesordered) _simple_newcodesrlevels)rClevel)r_mir.r/ szhash_tuples..c3s |] }|jddVqdS)Fr6r8r:N)_hash_pandas_object)rCcat)r6r8r.r/rFs  zhash_tuples..) rrUrMr_rrOr from_tuplesrangenlevelsr0rS)r]r6r8rcat_valsrZrWr.)r_r6r8rgr/rPs    rPrcCs\t|ds tdt|tr|j|||dSt|tjs'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-likeriz6hash_array requires np.ndarray or ExtensionArray, not z!. Use hash_pandas_object instead.) hasattrrUrOrrjr ndarrayrV__name__ _hash_ndarray)r]r6r8r:r.r.r/rJs   rJ np.ndarrayc Cs|j}t|tjr t|j|||}t|j|||}|d|S|tkr*|d}nwt |j tj tj fr?| djddd}nbt |j tjrY|jdkrY| d|jjd}nH|rdd lm}m}m} | |dd \} } t|| dd }|| |} | j||dd Szt|||}Wntyt|tt||}Ynw||d ?N}|td9}||d?N}|td9}||d?N}|S)z! See hash_array.__doc__. u8i8Fr<ur)r_r factorize)sortr`rile9z lb&&& )rr issubdtype complex128rsrealimagr5rQ issubclassrV datetime64 timedelta64viewnumberitemsizerMr_rrzrrcrjrrUr7objectr") r]r6r8r:r hash_real hash_imagr_rrzrdrarkr.r.r/rss@        rs)rrrrrr) r2r3r4r5r6r7r8r9r:r5rr)r]r^r6r7r8r7rr) r]rr6r7r8r7r:r5rr) r]rtr6r7r8r7r:r5rr)&__doc__ __future__rr#typingrnumpyr pandas._libs.hashingrpandas.core.dtypes.commonrpandas.core.dtypes.dtypesrpandas.core.dtypes.genericrrr r r collections.abcr r rpandas._typingrrrMrrrrrNr0r@rPrJrsr.r.r.r/s>      & f 4 3