`Vg*2dZddlmZddlmZmZddlmZmZm Z m Z m Z m Z ddl Z ddlZddlmZddlmZmZmZddlmZdd lmZdd lmZmZmZmZmZm Z ddl!Z"dd l#m$Z$dd l%m&Z&erdd l!m'Z'm(Z( ddZ)GddeZ*Gdde*Z+Gdde*Z,ddZ-ddZ. ddZ/ ddZ0d dZ1 d!dZ2 d"dZ3y)#z Module responsible for execution of NDFrame.describe() method. Method NDFrame.describe() delegates actual execution to function describe_ndframe(). ) annotations)ABCabstractmethod) TYPE_CHECKINGAnyCallableHashableSequencecastN) Timestamp)DtypeObjNDFrameTnpt)find_stack_level)validate_percentile) is_bool_dtypeis_complex_dtypeis_datetime64_any_dtypeis_extension_array_dtypeis_numeric_dtypeis_timedelta64_dtype)concat)format_percentiles) DataFrameSeriesct|}|jdk(rttd||}nt td||||}|j |}tt |S)aDescribe series or dataframe. Called from pandas.core.generic.NDFrame.describe() Parameters ---------- obj: DataFrame or Series Either dataframe or series to be described. include : 'all', list-like of dtypes or None (default), optional A white list of data types to include in the result. Ignored for ``Series``. exclude : list-like of dtypes or None (default), optional, A black list of data types to omit from the result. Ignored for ``Series``. datetime_is_numeric : bool, default False Whether to treat datetime dtypes as numeric. percentiles : list-like of numbers, optional The percentiles to include in the output. All should fall between 0 and 1. The default is ``[.25, .5, .75]``, which returns the 25th, 50th, and 75th percentiles. Returns ------- Dataframe or series description. robjdatetime_is_numericr)rincludeexcluder ) percentiles)refine_percentilesndimSeriesDescriberr DataFrameDescriberdescriber)rr!r"r r# describerresults U/var/www/html/hubwallet-dev/venv/lib/python3.12/site-packages/pandas/core/describe.pydescribe_ndframer,6ss>%[1K xx1}#Xs# 3 '[#& 3    K  8F & !!c*eZdZdZddZeddZy)NDFrameDescriberAbstractzAbstract class for describing dataframe or series. Parameters ---------- obj : Series or DataFrame Object to be described. datetime_is_numeric : bool Whether to treat datetime dtypes as numeric. c ||_||_yNr)selfrr s r+__init__z!NDFrameDescriberAbstract.__init__ts#6 r-cy)zDo describe either series or dataframe. Parameters ---------- percentiles : list-like of numbers The percentiles to include in the output. N)r2r#s r+r(z!NDFrameDescriberAbstract.describexsr-N)rDataFrame | Seriesr boolreturnNone)r#Sequence[float] | np.ndarrayr8r6)__name__ __module__ __qualname____doc__r3rr(r5r-r+r/r/is 7  r-r/c$eZdZUdZded<ddZy)r&z2Class responsible for creating series description.rrcht|j|j}||j|Sr1)select_describe_funcrr )r2r# describe_funcs r+r(zSeriesDescriber.describes/, HH  $ $ TXX{33r-N)r#r:r8r)r;r<r=r>__annotations__r(r5r-r+r&r&s< K4r-r&cFeZdZdZ dfd ZddZdZxZS)r'aClass responsible for creating dataobj description. Parameters ---------- obj : DataFrame DataFrame to be described. include : 'all', list-like of dtypes or None A white list of data types to include in the result. exclude : list-like of dtypes or None A black list of data types to omit from the result. datetime_is_numeric : bool Whether to treat datetime dtypes as numeric. c||_||_|jdk(r$|jjdk(r t dt |||y)Nrz+Cannot describe a DataFrame without columns)r )r!r"r%columnssize ValueErrorsuperr3)r2rr!r"r __class__s r+r3zDataFrameDescriber.__init__sN  88q=S[[--2JK K 2EFr-c n|j}g}|jD]3\}}t||j}|j |||5t |}t |Dcgc]}|j|dc}dd} |jj| _| Scc}w)NF)copyr)axissort) _select_dataitemsrAr appendreorder_columnsrreindexrGrM) r2r#dataldesc_seriesrB col_namesxds r+r(zDataFrameDescriber.describes  "  =IAv09Q9QRM LLv{; < =$E* 7< =!QYYyuY - =  LL%%'  >s-B2c|j||jptjg}|jr|j d|j j|}t|jdk(r |j }|S|jdk(r'|j d}t||j }|S|j j|j|j}|S)zSelect columns to be described.datetime)r!rallz*exclude must be None when include is 'all')r!r") r!r"npnumberr rRr select_dtypeslenrGrI)r2default_includerUmsgs r+rPzDataFrameDescriber._select_datas LL t||';46II;O''&&z288))/)BD4<< A%xx \\U "||'B o%88D  88))  *D r-) rrr!str | Sequence[str] | Noner"rer r7r8r9)r#r:r8r)r;r<r=r>r3r(rP __classcell__)rKs@r+r'r'sM G G, G , G " G G "r-r'cg}td|Dt}|D]}|D]}||vs|j|!|S)z,Set a convenient order for rows for display.c34K|]}|jywr1)index).0rZs r+ z"reorder_columns..s3AGG3s)key)sortedrbrR)rVnames ldesc_indexesidxnamesnames r+rSrSsRE3U3=M!# #D5  T" ## Lr-cddlm}t|}gd|zdgz}|j|j |j |j g|j|jz|jgz}t|rtj}n.t|r!t|stj d}nd}||||j"|S)zDescribe series containing numerical data. Parameters ---------- series : Series Series to be described. percentiles : list-like of numbers The percentiles to include in the output. rr)countmeanstdminmaxfloatNrirqdtype)pandasrrrtrurvrwquantiletolistrxrpd Float64Dtyperrr_r{rq)rXr#rformatted_percentiles stat_indexr[r{s r+describe_numeric_1drs.{;03HHE7RJ  fjjlC //+ & - - / 0 ::<.  '! & !*:6*B! !:FKKu EEr-c<gd}|j}t||dk7}|dkDr!|jd|jd}}d}n"tj tj }}d}|j |||g}ddlm} | |||j|S)zDescribe series containing categorical data. Parameters ---------- data : Series Series to be described. percentiles_ignored : list-like of numbers Ignored, but in place to unify interface. )rtuniquetopfreqrNobjectrsrz) value_countsrbriilocr_nanrtr|rrq) rUpercentiles_ignoredrn objcounts count_uniquerrr{r*rs r+describe_categorical_1drs /E!!#Iya01LaOOA& q(9TFFBFFTjjlL#t 4F &DIIU CCr-cddg}|j}t||dk7}|j|g}d}|dkDr|jd|jd}}|j j } |jjjd} t|}|j| |j| }n|j| }|gdz }|||t| j| t| j| gz }n,|dd gz }|t j"t j"gz }d }dd lm} | |||j(| S) zDescribe series containing timestamp data treated as categorical. Parameters ---------- data : Series Series to be described. percentiles_ignored : list-like of numbers Ignored, but in place to unify interface. rtrrNi8)rrfirstlast)tzrrrrsrz)rrbrtrirdtrdropnavaluesviewr tzinfo tz_convert tz_localizerwrxr_rr|rrq) rUrrnrrr*r{rrrasintrs r+$describe_timestamp_as_categorical_1dr!sGh E!!#Iya01LjjlL )F EaOOA& q(9T WWZZ $$))$/n :: !bn..$C//"%C 11   eiikb ) eiikb )    % 266266"" &DIIU CCr-c&ddlm}t|}gd|zdgz}|j|j |j g|j |jz|jgz}||||jS)zDescribe series containing datetime64 dtype. Parameters ---------- data : Series Series to be described. percentiles : list-like of numbers The percentiles to include in the output. rrs)rtrurwrx)rirq) r|rrrtrurwr}r~rxrq)rUr#rrrr[s r+describe_timestamp_1drQs.{;),AAUGKJ tyy{DHHJ/ -- $ + + - . 88:,  !:DII 66r-c*t|jrtSt|rtSt |jr2|rt StjdtttSt|jrtStS)zSelect proper function for describing series based on data type. Parameters ---------- data : Series Series to be described. datetime_is_numeric : bool Whether to treat datetime dtypes as numeric. zTreating datetime data as categorical rather than numeric in `.describe` is deprecated and will be removed in a future version of pandas. Specify `datetime_is_numeric=True` to silence this warning and adopt the future behavior now.) stacklevel) rr{rrrrrwarningswarn FutureWarningrrr)rUr s r+rArAisvTZZ && $ ""  , ( ( MMJ+-  8 7 djj )""&&r-c.|tjgdSt|}t|d|vr|j dtj |}tj |}|Jt|t|kr td|S)z Ensure that percentiles are unique and sorted. Parameters ---------- percentiles : list-like of numbers, optional The percentiles to include in the output. )g??g?rz%percentiles cannot contain duplicates) r_arraylistrrRasarrayrrbrI)r# unique_pctss r+r$r$sxx)**{#K $ +3**[)K))K(K  "" " ;#k**@AA r-) rrr!rer"rer r7r##Sequence[float] | np.ndarray | Noner8r)rVzSequence[Series]r8zlist[Hashable])rXrr#Sequence[float]r8r)rUrrrr8r)rUrr#rr8r)rUrr r7r8r)r#rr8z%np.ndarray[Any, np.dtype[np.float64]])4r> __future__rabcrrtypingrrrr r r rnumpyr_pandas._libs.tslibsr pandas._typingr rrpandas.util._exceptionsrpandas.util._validatorsrpandas.core.dtypes.commonrrrrrrr|rpandas.core.reshape.concatrpandas.io.formats.formatrrrr,r/r&r'rSrrrrrAr$r5r-r+rsN #) 57-7 0" 0"(0"( 0"  0" 5 0"0"f s 4 4. 4D1DNF>D D(D D@-D -D(-D -D`70!' !'!'!'H 4 * r-