o i*2@s`dZddlmZddlmZmZddlmZmZm Z m Z m Z m Z ddl Z ddlZddlmZddlmZmZmZddlmZdd lmZdd lmZmZmZmZmZm Z ddl!Z"dd l#m$Z$dd l%m&Z&erndd l!m'Z'm(Z(d8ddZ)GdddeZ*Gddde*Z+Gddde*Z,d9d#d$Z-d:d(d)Z.d;d,d-Z/d;d.d/Z0dd6d7Z3dS)?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) DataFrameSeriesobjr includestr | Sequence[str] | Noneexcludedatetime_is_numericbool percentiles#Sequence[float] | np.ndarray | NonereturncCsRt|}|jdkrttd||d}n ttd||||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. rrrr)rrrr)r!)refine_percentilesndimSeriesDescriberr DataFrameDescriberdescriber )rrrrr! describerresultr-O/var/www/edux/Edux_v2/venv/lib/python3.10/site-packages/pandas/core/describe.pydescribe_ndframe6s   r/c@s(eZdZdZddd Zedd d ZdS)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. rDataFrame | Seriesrr r#NonecCs||_||_dSNr%)selfrrr-r-r.__init__ts z!NDFrameDescriberAbstract.__init__r!Sequence[float] | np.ndarraycCsdS)zDo describe either series or dataframe. Parameters ---------- percentiles : list-like of numbers The percentiles to include in the output. Nr-)r4r!r-r-r.r*xsz!NDFrameDescriberAbstract.describeN)rr1rr r#r2)r!r6r#r1)__name__ __module__ __qualname____doc__r5rr*r-r-r-r.r0is  r0c@s$eZdZUdZded<d ddZd S) r(z2Class responsible for creating series description.rrr!r6r#cCst|j|j}||j|Sr3)select_describe_funcrr)r4r! describe_funcr-r-r.r*s  zSeriesDescriber.describeN)r!r6r#r)r7r8r9r:__annotations__r*r-r-r-r.r(s r(cs4eZdZdZdfd d ZdddZddZZS)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. rrrrrrr r#r2cs>||_||_|jdkr|jjdkrtdtj||ddS)Nrz+Cannot describe a DataFrame without columns)r)rrr'columnssize ValueErrorsuperr5)r4rrrr __class__r-r.r5s zDataFrameDescriber.__init__r!r6csn|}g}|D]\}}t||j}||||q t|tfdd|Dddd}|j|_|S)Ncsg|] }|jddqS)F)copy)reindex.0x col_namesr-r. sz/DataFrameDescriber.describe..r$F)axissort) _select_dataitemsr;rappendreorder_columnsrr?rE)r4r!dataldesc_seriesr<dr-rJr.r*s  zDataFrameDescriber.describecCs|jdur)|jdur)tjg}|jr|d|jj|d}t|j dkr'|j}|S|jdkr>|jdur9d}t ||j}|S|jj|j|jd}|S)zSelect columns to be described.Ndatetime)rrallz*exclude must be None when include is 'all')rr) rrnpnumberrrQr select_dtypeslenr?rA)r4default_includerSmsgr-r-r.rOs&  zDataFrameDescriber._select_data) rrrrrrrr r#r2)r!r6r#r)r7r8r9r:r5r*rO __classcell__r-r-rCr.r)s  r)rTSequence[Series]list[Hashable]cCsDg}tdd|Dtd}|D]}|D] }||vr||qq|S)z,Set a convenient order for rows for display.css|]}|jVqdSr3)indexrGr-r-r. sz"reorder_columns..)key)sortedr]rQ)rTnames ldesc_indexesidxnamesnamer-r-r.rRs rRrVrSequence[float]cCsddlm}t|}gd|dg}||||g||| g}t |r6t }nt |rDt|sDtd}nd}||||j|dS)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)countmeanstdminmaxfloatNrcrjdtype)pandasrrrmrnrorpquantiletolistrqrpd Float64DtyperrrZrtrj)rVr!rformatted_percentiles stat_indexrWrtr-r-r.describe_numeric_1ds    r|rSpercentiles_ignoredc Csgd}|}t||dk}|dkr"|jd|jd}}d}n tjtj}}d}||||g}ddlm} | |||j |dS)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. )rmuniquetopfreqrNobjectrlrs) value_countsr]rcilocrZnanrmrurrj) rSr}rg objcounts count_uniquerrrtr,rr-r-r.describe_categorical_1ds  rc Cs ddg}|}t||dk}||g}d}|dkrf|jd|jd}}|jj} |j d} t |}|j durF| durF| | }n| | }|gd7}|||t | | dt | | dg7}n|dd g7}|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. rmr~rNi8)rrfirstlast)tzrrrrlrs)rr]rmrcrdtrdropnavaluesviewr tzinfo tz_convert tz_localizerprqrZrrurrj) rSr}rgrrr,rtrrrasintrr-r-r.$describe_timestamp_as_categorical_1d!s2       rcCsdddlm}t|}gd|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. rrl)rmrnrprq)rcrj) rurrrmrnrprvrwrqrj)rSr!rrzr{rWr-r-r.describe_timestamp_1dQs  rrcCsTt|jrtSt|r tSt|jr!|rtStjdt t dt St |jr(tStS)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) rrtrrr|rrwarningswarn FutureWarningrrr)rSrr-r-r.r;is   r;%np.ndarray[Any, np.dtype[np.float64]]cCst|dur tgdSt|}t|d|vr|dt|}t|}|dus,Jt|t|kr8td|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?rz%percentiles cannot contain duplicates) rZarraylistrrQasarrayr~r]rA)r! unique_pctsr-r-r.r&s     r&) rr rrrrrr r!r"r#r )rTrar#rb)rVrr!rkr#r)rSrr}rkr#r)rSrr!rkr#r)rSrrr r#r)r!r"r#r)4r: __future__rabcrrtypingrrrrr r rnumpyrZpandas._libs.tslibsr pandas._typingr r rpandas.util._exceptionsrpandas.util._validatorsrpandas.core.dtypes.commonrrrrrrrurxpandas.core.reshape.concatrpandas.io.formats.formatrrrr/r0r(r)rRr|rrrr;r&r-r-r-r.s6         3 G  0 $