j*ZdZddlmZddlmZmZddlmZmZddl Z ddl m Z m Z mZddlmZddlmZmZdd lmZmZmZdd lmZdd lmZdd lmZerdd lmZm Z m!Z!ddl"m#Z#m$Z$d.dZ%GddeZ&Gdde&Z'Gdde&Z(d/d!Z)d0d%Z*d1d(Z+d2d)Z,d3d+Z-d4d-Z.dS)5z 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) DataFrameSeriesobjr includestr | Sequence[str] | Noneexclude percentiles#Sequence[float] | np.ndarray | Nonereturnc t|}|jdkrttd|}n t td|||}||}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. rrr)rrr)r)_refine_percentilesndimSeriesDescriberrDataFrameDescriberdescriber )rrrr describerresults JC:\Projects\DSCons\.venv\Lib\site-packages\pandas\core\methods\describe.pydescribe_ndframer+7s8&k22K x1}}#Xs##   '[#&&     K  8 8F & ! !!c2eZdZdZd dZed d Zd S) NDFrameDescriberAbstractzAbstract class for describing dataframe or series. Parameters ---------- obj : Series or DataFrame Object to be described. rDataFrame | SeriesrNonec||_dSNr")selfrs r*__init__z!NDFrameDescriberAbstract.__init__ns r,rSequence[float] | np.ndarraycdS)zDo describe either series or dataframe. Parameters ---------- percentiles : list-like of numbers The percentiles to include in the output. N)r3rs r*r'z!NDFrameDescriberAbstract.describeqsr,N)rr/rr0)rr5rr/)__name__ __module__ __qualname____doc__r4rr'r7r,r*r.r.esR   ^   r,r.c&eZdZUdZded<d dZdS) r%z2Class responsible for creating series description.rrrr5rcLt|j}||j|Sr2)select_describe_funcr)r3r describe_funcs r*r'zSeriesDescriber.describes,, H  }TX{333r,N)rr5rr)r8r9r:r;__annotations__r'r7r,r*r%r%|s9<<KKK444444r,r%c@eZdZUdZded<dfd Zdd Zdd ZxZS)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. rrrrrrr0c||_||_|jdkr|jjdkrt dt |dS)Nrz+Cannot describe a DataFrame without columns)rrr$columnssize ValueErrorsuperr4)r3rrr __class__s r*r4zDataFrameDescriber.__init__sZ  8q==S[-22JKK K r,rr5c\|}g}|D]3\}}t|}||||4t |t fd|Dddd}|j|_|S)Nc:g|]}|Sr7)reindex).0x col_namess r* z/DataFrameDescriber.describe..s% 1 1 1aQYYy ! ! 1 1 1r,r!TF)axis ignore_indexsort) _select_dataitemsr>appendreorder_columnsrrDcopy) r3rdataldesc_seriesr?drNs @r*r'zDataFrameDescriber.describes  ""  = =IAv088M LLv{;; < < < <#E**  1 1 1 15 1 1 1     L%%'' r,c|jP|jItjdg}|j|}t |jdkr|j}nz|jdkr |jd}t||j}nO|j|j|j}t |jdkrd}t||S) zSelect columns to be described.Ndatetime)rrallz*exclude must be None when include is 'all')rrzz"reorder_columns..s$33AG333333r,)key)setsortedrcaddrU)rYnames seen_names ldesc_indexesidxnamesnames r*rVrVsE #J33U333===M!## # #D:%%t$$$ T""" # Lr,r[rSequence[float]cddlm}t|}t|dkrg}n'||}ddddg|d}|||| g|| }t|j trbt|j tr9|j jdkrd }nZdd l}t|}n4t%}n%|j jd vrt'j d }nd }||||j| S) zDescribe series containing numerical data. Parameters ---------- series : Series Series to be described. percentiles : list-like of numbers The percentiles to include in the output. rrcountmeanstdminmaxmNiufbfloatrkrudtype)pandasrrrcquantiletolistryrzr{r|r} isinstancerrrkindpyarrowfloat64rr`ru) r[rrformatted_percentiles quantiles stat_indexr\rpas r*describe_numeric_1drss.{;; ;1 OOK007799 65%O2GOOJ           A&,// flJ / / #| C''$$$$"2::<<00 NNEE  f $ $!! 6!:FKu E E EEr,rXpercentiles_ignoredcBgd}|}t||dk}|dkr|jd|jd}}d}ntjtj}}d}||||g}ddlm} | |||j |S)zDescribe series containing categorical data. Parameters ---------- data : Series Series to be described. percentiles_ignored : list-like of numbers Ignored, but in place to unify interface. )ryuniquetopfreqrNobjectrxr) value_countsrcrkilocr`nanryrrru) rXrrq objcounts count_uniquerrrr)rs r*describe_categorical_1drs / . .E!!##Iya011LaOA& q(9TFBFTjjllL#t 4F 6&DIU C C CCr,cPddlm}t|}dddg|d}|||g|||}||||j S)zDescribe series containing datetime64 dtype. Parameters ---------- data : Series Series to be described. percentiles : list-like of numbers The percentiles to include in the output. rrxryrzr|r})rkru) rrrryrzr|rrr}ru)rXrrrrr\s r*describe_timestamp_1dr.s.{;;65H+@H%HJ      { # # * * , ,     A 6!:DI 6 6 66r,rct|jrtSt|rtS|jjdkst |jtrtS|jjdkrtStS)zSelect proper function for describing series based on data type. Parameters ---------- data : Series Series to be described. Mr~) r rrr rrrrr)rXs r*r>r>HssTZ  '&& $  '"" C  :dj/#J#J $$ C  ""&&r,npt.NDArray[np.float64]c |tjgdStj|}t|tj|}|Jt |t |krt d|S)z Ensure that percentiles are unique and sorted. Parameters ---------- percentiles : list-like of numbers, optional The percentiles to include in the output. N)g?g?g?z%percentiles cannot contain duplicates)r`arrayasarrayr rrcrF)r unique_pctss r*r#r#^sx)))****[))K $$$)K((K  " " " ;#k****@AAA r,) rr rrrrrrrr )rYrgrrh)r[rrrvrr)rXrrrvrr)rXrrrvrr)rXrrr)rrrr)/r; __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.abcrrrrrrr+r.r%r&rVrrrr>r#r7r,r*rs #"""""  877777 544444------777777   +"+"+"+"\     s   . 4 4 4 4 4. 4 4 4EEEEE1EEEP    .F.F.F.FbDDDD@77774'''',r,