*j:)vdZddlmZddlmZmZddlmZmZddl Z ddl m Z m Z mZddlmZddlmZmZdd lmZmZmZdd lmZdd lmZdd lmZerdd lmZm Z m!Z!ddl"m#Z#m$Z$ ddZ%GddeZ&Gdde&Z'Gdde&Z(ddZ)ddZ* ddZ+d dZ, d!dZ- d"dZ.y)#z Module responsible for execution of NDFrame.describe() method. Method NDFrame.describe() delegates actual execution to function describe_ndframe(). ) annotations)ABCabstractmethod) TYPE_CHECKINGcastN)DtypeObjNDFrameTnpt)validate_percentile) is_bool_dtypeis_numeric_dtype) ArrowDtypeDatetimeTZDtypeExtensionDtype) Float64Dtype)concat)format_percentiles)CallableHashableSequence) DataFrameSeriesct|}|jdk(rttd|}nt td|||}|j |}tt |S)a Describe 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``. 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. robjr)rincludeexclude) percentiles)_refine_percentilesndimSeriesDescriberrDataFrameDescriberdescriber )rrrr describerresults >C:\FundamentalWorkbench\vendor\pandas\core\methods\describe.pydescribe_ndframer(7sm8&k2K xx1}#Xs# '[#&   K  8F & !!c*eZdZdZddZeddZy)NDFrameDescriberAbstractzAbstract class for describing dataframe or series. Parameters ---------- obj : Series or DataFrame Object to be described. c||_yNr)selfrs r'__init__z!NDFrameDescriberAbstract.__init__ns r)cy)zDo describe either series or dataframe. Parameters ---------- percentiles : list-like of numbers The percentiles to include in the output. N)r.rs r'r$z!NDFrameDescriberAbstract.describeqsr)N)rDataFrame | SeriesreturnNone)rSequence[float] | np.ndarrayr3r2)__name__ __module__ __qualname____doc__r/rr$r1r)r'r+r+es   r)r+c$eZdZUdZded<ddZy)r"z2Class responsible for creating series description.rrcRt|j}||j|Sr-)select_describe_funcr)r.r describe_funcs r'r$zSeriesDescriber.describes&, HH TXX{33r)N)rr5r3r)r6r7r8r9__annotations__r$r1r)r'r"r"|s< K4r)r"cPeZdZUdZded< dfd ZddZd dZxZS) r#abClass responsible for creating dataobj description. Parameters ---------- obj : DataFrame DataFrame to be described. include : 'all', list-like of dtypes or None A white list of data types to include in the result. exclude : list-like of dtypes or None A black list of data types to omit from the result. rrc||_||_|jdk(r$|jjdk(r t dt ||y)Nrz+Cannot describe a DataFrame without columns)rrr!columnssize ValueErrorsuperr/)r.rrr __class__s r'r/zDataFrameDescriber.__init__sH  88q=S[[--2JK K r)cV|j}g}|jD](\}}t|}|j|||*t |}t |Dcgc]}|j |c}ddd} |jj| _| Scc}w)NrTF)axis ignore_indexsort) _select_dataitemsr<appendreorder_columnsrreindexrBcopy) r.rdataldesc_seriesr= col_namesxds r'r$zDataFrameDescriber.describes  " IAv08M LLv{; <&$E* +0 15aQYYy !5 1   LL%%'  2s"B&c|j`|jTtjdg}|jj |}t |jdk(r |j}|S|jdk(r'|j d}t||j}|S|jj |j|j}t |jdk(r d}t||S)zSelect columns to be described.datetime)rrallz*exclude must be None when include is 'all')rrzr/r$rK __classcell__)rFs@r'r#r#sD  N   ,  ,   $r)r#cg}t}td|Dt}|D]0}|D])}||vs|j||j |+2|S)z,Set a convenient order for rows for display.c34K|]}|jywr-)index).0rVs r' z"reorder_columns..s3UAGGUs)key)setsortedr^addrM)rRnames seen_names ldesc_indexesidxnamesnames r'rNrNs[E #J3U3=M!D:%t$ T"" Lr)cddlm}t|}t|dk(rg}n|j |j }ddddg|d}|j |j|j|jg||j}t|jtr_t|jtr:|jjdk(rd }nYdd l}t|j#}n;t%}n0|jjd vrt'jd }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. rrcountmeanstdminmaxmNiufbfloatrerpdtype)pandasrrr^quantiletolistrsrtrurvrw isinstancer|rrkindpyarrowfloat64rr[rp) rTrrformatted_percentiles quantiles stat_indexrWr|pas r'describe_numeric_1drs".{; ;1 OOK0779 65%O2GOOJ           A&,,/ fllJ /||  C'$"2::<0 NE   f $! !: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. )rsuniquetopfreqrNobjectrrr{) value_countsr^reilocr[nanrsr}rrp) rQpercentiles_ignoredrl objcounts count_uniquerrr|r&rs r'describe_categorical_1drs /E!!#Iya01LaOOA& q(9TFFBFFTjjlL#t 4F &DIIU CCr)cddlm}t|}dddg|d}|j|j |j g|j |j|j}||||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. rrrrsrtrvrw)rerp) r}rrrsrtrvr~rrwrp)rQrrrrrWs r'describe_timestamp_1dr.s.{;65H+@H%HJ      { # * * ,     A !:DII 66r)ct|jrtSt|rtS|jj dk(st |jtrtS|jj dk(rtStS)zSelect proper function for describing series based on data type. Parameters ---------- data : Series Series to be described. Mrx) r r|rr rrrrr)rQs r'r<r<HscTZZ && $ "" C :djj/#J$$ C ""&&r)c|tjgdStj|}t|tj|}|Jt |t |kr t d|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?g?z%percentiles cannot contain duplicates)r[arrayasarrayr rr^rD)r unique_pctss r'r r ^srxx)****[)K $))K(K  "" " ;#k**@AA r)) rr rrarrar#Sequence[float] | np.ndarray | Noner3r )rRzSequence[Series]r3zlist[Hashable])rTrrSequence[float]r3r)rQrrrr3r)rQrrrr3r)rQrr3r)rrr3znpt.NDArray[np.float64])/r9 __future__rabcrrtypingrrnumpyr[pandas._typingrr r pandas.util._validatorsr pandas.core.dtypes.commonr r pandas.core.dtypes.dtypesrrrpandas.core.arrays.floatingrpandas.core.reshape.concatrpandas.io.formats.formatrcollections.abcrrrr}rrr(r+r"r#rNrrrr<r r1r)r'rs #  8 5-7  +" +"(+"( +" 5 +"  +"\ s . 4. 4E1EP .FbD D(D D@74' ' ',4r)