U sVc*2@sdZddlmZddlmZmZddlmZmZm 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(dddddddddZ)GdddeZ*Gddde*Z+Gddde*Z,dddddZ-d d!d d"d#d$Z.d d!d d%d&d'Z/d d!d d%d(d)Z0d d!d d*d+d,Z1d dd-d.d/d0Z2dd1d2d3d4Z3dS)5z Module responsible for execution of NDFrame.describe() method. Method NDFrame.describe() delegates actual execution to function describe_ndframe(). ) annotations)ABCabstractmethod) TYPE_CHECKINGAnyCallableHashableSequencecastN) Timestamp)DtypeObjNDFrameTnpt)find_stack_level)validate_percentile) is_bool_dtypeis_complex_dtypeis_datetime64_any_dtypeis_extension_array_dtypeis_numeric_dtypeis_timedelta64_dtype)concat)format_percentiles) DataFrameSeriesr str | Sequence[str] | Noneboolz#Sequence[float] | np.ndarray | None)objincludeexcludedatetime_is_numeric percentilesreturncCsRt|}|jdkr&ttd||d}nttd||||d}|j|d}tt|S)aDescribe series or dataframe. Called from pandas.core.generic.NDFrame.describe() Parameters ---------- obj: DataFrame or Series Either dataframe or series to be described. include : 'all', list-like of dtypes or None (default), optional A white list of data types to include in the result. Ignored for ``Series``. exclude : list-like of dtypes or None (default), optional, A black list of data types to omit from the result. Ignored for ``Series``. datetime_is_numeric : bool, default False Whether to treat datetime dtypes as numeric. percentiles : list-like of numbers, optional The percentiles to include in the output. All should fall between 0 and 1. The default is ``[.25, .5, .75]``, which returns the 25th, 50th, and 75th percentiles. Returns ------- Dataframe or series description. rrr r)rrrr )r!)refine_percentilesndimSeriesDescriberr DataFrameDescriberdescriber )rrrr r!Z describerresultr+8/tmp/pip-unpacked-wheel-xj8nt62q/pandas/core/describe.pydescribe_ndframe6s  r-c@s6eZdZdZddddddZeddd d d Zd S) NDFrameDescriberAbstractzAbstract class for describing dataframe or series. Parameters ---------- obj : Series or DataFrame Object to be described. datetime_is_numeric : bool Whether to treat datetime dtypes as numeric. zDataFrame | SeriesrNone)rr r"cCs||_||_dSNr$)selfrr r+r+r,__init__tsz!NDFrameDescriberAbstract.__init__Sequence[float] | np.ndarrayr!r"cCsdS)zDo describe either series or dataframe. Parameters ---------- percentiles : list-like of numbers The percentiles to include in the output. Nr+)r1r!r+r+r,r)xsz!NDFrameDescriberAbstract.describeN)__name__ __module__ __qualname____doc__r2rr)r+r+r+r,r.is r.c@s*eZdZUdZded<dddddZdS) r'z2Class responsible for creating series description.rrr3r4cCst|j|j}||j|Sr0)select_describe_funcrr )r1r! describe_funcr+r+r,r)s zSeriesDescriber.describeN)r5r6r7r8__annotations__r)r+r+r+r,r's r'csFeZdZdZddddddfdd Zd dd d d Zd dZZS)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. rrrr/)rrrr r"cs>||_||_|jdkr*|jjdkr*tdtj||ddS)Nrz+Cannot describe a DataFrame without columns)r )rrr&columnssize ValueErrorsuperr2)r1rrrr  __class__r+r,r2s zDataFrameDescriber.__init__r3r4csn|}g}|D]$\}}t||j}||||qt|tfdd|Dddd}|j|_|S)Ncsg|]}|jddqS)F)copy)Zreindex.0xZ col_namesr+r, sz/DataFrameDescriber.describe..r#F)Zaxissort) _select_dataitemsr9r appendreorder_columnsrr=rC)r1r!dataldesc_seriesr:dr+rGr,r)s  zDataFrameDescriber.describecCs|jdkrP|jdkrPtjg}|jr,|d|jj|d}t|j dkr|j}n<|jdkrx|jdk rpd}t ||j}n|jj|j|jd}|S)zSelect columns to be described.Ndatetime)rrallz*exclude must be None when include is 'all')rr) rrnpnumberr rLrZ select_dtypeslenr=r?)r1Zdefault_includerNmsgr+r+r,rJs"   zDataFrameDescriber._select_data)r5r6r7r8r2r)rJ __classcell__r+r+rAr,r(sr(zSequence[Series]zlist[Hashable])rOr"cCsDg}tdd|Dtd}|D] }|D]}||kr&||q&q|S)z,Set a convenient order for rows for display.css|] }|jVqdSr0)indexrDr+r+r, sz"reorder_columns..)key)sortedrWrL)rOnamesZ ldesc_indexesZidxnamesnamer+r+r,rMsrMrzSequence[float])rQr!r"cCsddlm}t|}ddddg|dg}||||g||| g}t |rpt }n t |rt|std}nd }||||j|d 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. rrcountmeanstdminmaxfloatNrZr_dtype)pandasrrrarbrcrdquantiletolistrerpdZ Float64DtyperrrUrhr_)rQr!rformatted_percentiles stat_indexrRrhr+r+r,describe_numeric_1ds    ro)rNpercentiles_ignoredr"c Csddddg}|}t||dk}|dkrH|jd|jd}}d}ntjtj}}d}||||g}ddlm} | |||j |d 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. rauniquetopfreqrNobjectr`rg) value_countsrWrZilocrUnanrarirr_) rNrpr^ objcounts count_uniquerrrsrhr*rr+r+r,describe_categorical_1ds  rzc Csddg}|}t||dk}||g}d}|dkr|jd|jd}}|jj} |j d} t |}|j dk r| dk r| | }n | | }|dddd g7}|||t | | d t | | d g7}n |ddg7}|tjtjg7}d }dd lm} | |||j|d 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. rarqrNi8rrrsfirstlast)tzrtr`rg)rurWrarZrvdtr~Zdropnavaluesviewr tzinfoZ tz_convertZ tz_localizerdrerUrwrirr_) rNrpr^rxryr*rhrrrsr~Zasintrr+r+r,$describe_timestamp_as_categorical_1d!s2      r)rNr!r"cCsfddlm}t|}dddg|dg}|||g|||g}||||j dS)zDescribe series containing datetime64 dtype. Parameters ---------- data : Series Series to be described. percentiles : list-like of numbers The percentiles to include in the output. rr`rarbrdre)rZr_) rirrrarbrdrjrkrer_)rNr!rrmrnrRr+r+r,describe_timestamp_1dQs  rr)rNr r"cCsZt|jrtSt|rtSt|jrD|r,tStjdt t dt Snt |jrRtStSdS)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.) stacklevelN) rrhrzrrorrwarningswarn FutureWarningrrr)rNr r+r+r,r9is   r9z%np.ndarray[Any, np.dtype[np.float64]]r4cCsv|dkrtdddgSt|}t|d|kr:|dt|}t|}|dk sZtt|t|krrt d|S)z Ensure that percentiles are unique and sorted. Parameters ---------- percentiles : list-like of numbers, optional The percentiles to include in the output. Ng?g?g?z%percentiles cannot contain duplicates) rUarraylistrrLZasarrayrqAssertionErrorrWr?)r!Z unique_pctsr+r+r,r%s     r%)4r8 __future__rabcrrtypingrrrrr r rZnumpyrUZpandas._libs.tslibsr Zpandas._typingr r rZpandas.util._exceptionsrZpandas.util._validatorsrZpandas.core.dtypes.commonrrrrrrrirlZpandas.core.reshape.concatrZpandas.io.formats.formatrrrr-r.r'r(rMrorzrrr9r%r+r+r+r,s4        3 G  0$