U f/eZ3@s~dZddlmZddlmZmZddlmZmZm Z m Z ddl Z ddl Z ddlmZddlmZmZmZddlmZdd lmZmZmZmZdd lmZdd lmZerdd lm Z m!Z!d ddddd dddZ"GdddeZ#Gddde#Z$Gddde#Z%dddddZ&dd dd!d"d#Z'dd dd$d%d&Z(dd dd$d'd(Z)dd dd)d*d+Z*ddd,d-d.d/Z+dd d0d1d2Z,dS)3z Module responsible for execution of NDFrame.describe() method. Method NDFrame.describe() delegates actual execution to function describe_ndframe(). ) annotations)ABCabstractmethod) TYPE_CHECKINGCallableSequencecastN) Timestamp) FrameOrSeriesFrameOrSeriesUnionHashable)validate_percentile) is_bool_dtypeis_datetime64_any_dtypeis_numeric_dtypeis_timedelta64_dtype)concat)format_percentiles) DataFrameSeriesr str | Sequence[str] | NoneboolzSequence[float] | 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. rrrrrrrr)r)refine_percentilesndimSeriesDescriberrDataFrameDescriberdescriber )rrrrrZ describerresultr'8/tmp/pip-unpacked-wheel-tiezk1ph/pandas/core/describe.pydescribe_ndframe0s  r)c@s4eZdZdZdddddZedddd 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. r rrcCs||_||_dSNr)selfrrr'r'r(__init__nsz!NDFrameDescriberAbstract.__init__Sequence[float]rrcCsdS)zDo describe either series or dataframe. Parameters ---------- percentiles : list-like of numbers The percentiles to include in the output. Nr')r,rr'r'r(r%rsz!NDFrameDescriberAbstract.describeN)__name__ __module__ __qualname____doc__r-rr%r'r'r'r(r*cs r*c@s*eZdZUdZded<dddddZdS) r#z2Class responsible for creating series description.rrr.r/cCst|j|j}||j|Sr+)select_describe_funcrr)r,r describe_funcr'r'r(r%s zSeriesDescriber.describeN)r0r1r2r3__annotations__r%r'r'r'r(r#}s r#csDeZdZdZdddddfdd Zddd d d Zd d ZZS)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 cs>||_||_|jdkr*|jjdkr*tdtj||ddS)Nrz+Cannot describe a DataFrame without columns)r)rrr"columnssize ValueErrorsuperr-)r,rrrr __class__r'r(r-s zDataFrameDescriber.__init__r.r/csn|}g}|D]$\}}t||j}||||qt|tfdd|Dddd}|j|_|S)Ncsg|]}|jddqS)F)copy)Zreindex.0xZ col_namesr'r( sz/DataFrameDescriber.describe..rF)Zaxissort) _select_dataitemsr4rappendreorder_columnsrr8r>)r,rdataldesc_seriesr5dr'rBr(r%s  zDataFrameDescriber.describecCs|jdkrP|jdkrPtjg}|jr,|d|jj|d}t|j dkr|j}n<|jdkrx|jdk rpd}t ||j}n|jj|j|jd}|S)zSelect columns to be described.Ndatetime)rrallz*exclude must be None when include is 'all')rr) rrnpnumberrrGrZ select_dtypeslenr8r:)r,Zdefault_includerImsgr'r'r(rEs"   zDataFrameDescriber._select_data)r0r1r2r3r-r%rE __classcell__r'r'r<r(r$sr$zSequence[Series]zlist[Hashable])rJrcCsDg}tdd|Dtd}|D] }|D]}||kr&||q&q|S)z,Set a convenient order for rows for display.css|] }|jVqdSr+)indexr?r'r'r( sz"reorder_columns..)key)sortedrRrG)rJnamesZ ldesc_indexesZidxnamesnamer'r'r(rHsrHrr.)rLrrcCsnddlm}t|}ddddg|dg}||||g||| g}||||j dS) zDescribe series containing numerical data. Parameters ---------- series : Series Series to be described. percentiles : list-like of numbers The percentiles to include in the output. rrcountmeanstdminmaxrUrZ) pandasrrr\r]r^r_quantiletolistr`rZ)rLrrformatted_percentiles stat_indexrMr'r'r(describe_numeric_1ds  rg)rIpercentiles_ignoredrc Csddddg}|}t||dk}|dkrH|jd|jd}}d}ntjtj}}d}||||g}ddlm} | |||j |d S) zDescribe series containing categorical data. Parameters ---------- data : Series Series to be described. percentiles_ignored : list-like of numbers Ignored, but in place to unify interface. r\uniquetopfreqrNobjectr[rUrZdtype) value_countsrRrUilocrPnanr\rbrrZ) rIrhrY objcounts count_uniquerjrkrnr&rr'r'r(describe_categorical_1ds  rtc Csddg}|}t||dk}||g}d}|dkr|jd|jd}}|jj} |j d} t |}|j dk r| dk r| | }n | | }|dddd g7}|||t | | d t | | d g7}n |ddg7}|tjtjg7}d }dd lm} | |||j|d S)zDescribe series containing timestamp data treated as categorical. Parameters ---------- data : Series Series to be described. percentiles_ignored : list-like of numbers Ignored, but in place to unify interface. r\rirNi8rjrkfirstlast)tzrlr[rm)rorRr\rUrpdtrxZdropnavaluesviewr tzinfoZ tz_convertZ tz_localizer_r`rPrqrbrrZ) rIrhrYrrrsr&rnrjrkrxZasintrr'r'r($describe_timestamp_as_categorical_1ds2      r})rIrrcCsfddlm}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[r\r]r_r`ra) rbrrr\r]r_rcrdr`rZ)rIrrrerfrMr'r'r(describe_timestamp_1dHs  r~r)rIrrcCsXt|jrtSt|rtSt|jrB|r,tStjdt ddt Snt |jrPtStSdS)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) rrnrtrrgrr~warningswarn FutureWarningr}r)rIrr'r'r(r4cs   r4r/cCsv|dkrtdddgSt|}t|d|kr:|dt|}t|}|dk sZtt|t|krrt d|S)zEnsure 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) rParraylistr rGZasarrayriAssertionErrorrRr:)rZ unique_pctsr'r'r(r!s    r!)-r3 __future__rabcrrtypingrrrrrZnumpyrPZpandas._libs.tslibsr Zpandas._typingr r r Zpandas.util._validatorsr Zpandas.core.dtypes.commonrrrrZpandas.core.reshape.concatrZpandas.io.formats.formatrrbrrr)r*r#r$rHrgrtr}r~r4r!r'r'r'r(s0     3 I  0$