a Of.@sdZddlmZddlmZmZddlmZmZm Z ddl Z ddl m Z ddlmZmZmZddlmZdd lmZmZdd lmZmZmZdd lmZdd lmZdd lm Z erddl!m"Z"m#Z#ddl$m%Z%m&Z&ddddddddZ'GdddeZ(Gddde(Z)Gddde(Z*ddddd Z+d!d"d!d#d$d%Z,d!d"d!d&d'd(Z-d!d"d!d&d)d*Z.d!d"d!d+d,d-Z/d!d.d/d0d1Z0dd2d3d4d5Z1dS)6z Module responsible for execution of NDFrame.describe() method. Method NDFrame.describe() delegates actual execution to function describe_ndframe(). ) annotations)ABCabstractmethod) TYPE_CHECKINGCallablecastN) Timestamp)DtypeObjNDFrameTnpt)validate_percentile) is_bool_dtypeis_numeric_dtype) ArrowDtypeDatetimeTZDtypeExtensionDtype) Float64Dtype)concat)format_percentiles)HashableSequence) DataFrameSeriesr str | Sequence[str] | Nonez#Sequence[float] | np.ndarray | None)objincludeexclude percentilesreturncCsNt|}|jdkr$ttd|d}nttd|||d}|j|d}tt|S)a Describe series or dataframe. Called from pandas.core.generic.NDFrame.describe() Parameters ---------- obj: DataFrame or Series Either dataframe or series to be described. include : 'all', list-like of dtypes or None (default), optional A white list of data types to include in the result. Ignored for ``Series``. exclude : list-like of dtypes or None (default), optional, A black list of data types to omit from the result. Ignored for ``Series``. percentiles : list-like of numbers, optional The percentiles to include in the output. All should fall between 0 and 1. The default is ``[.25, .5, .75]``, which returns the 25th, 50th, and 75th percentiles. Returns ------- Dataframe or series description. rrr)rrr)r)_refine_percentilesndimSeriesDescriberrDataFrameDescriberdescriber )rrrrZ describerresultr'U/var/www/ai-form-bot/venv/lib/python3.9/site-packages/pandas/core/methods/describe.pydescribe_ndframe7s  r)c@s4eZdZdZdddddZedddd d Zd S) NDFrameDescriberAbstractzAbstract class for describing dataframe or series. Parameters ---------- obj : Series or DataFrame Object to be described. zDataFrame | SeriesNone)rrcCs ||_dSNr )selfrr'r'r(__init__nsz!NDFrameDescriberAbstract.__init__Sequence[float] | np.ndarrayrrcCsdS)zDo describe either series or dataframe. Parameters ---------- percentiles : list-like of numbers The percentiles to include in the output. Nr')r-rr'r'r(r%qsz!NDFrameDescriberAbstract.describeN)__name__ __module__ __qualname____doc__r.rr%r'r'r'r(r*esr*c@s*eZdZUdZded<dddddZdS) r#z2Class responsible for creating series description.rrr/r0cCst|j}||j|Sr,)select_describe_funcr)r-r describe_funcr'r'r(r%szSeriesDescriber.describeN)r1r2r3r4__annotations__r%r'r'r'r(r#|s r#csTeZdZUdZded<dddddfdd Zd dd d d Zdd ddZZS)r$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. rrrr+)rrrrcs:||_||_|jdkr*|jjdkr*tdt|dS)Nrz+Cannot describe a DataFrame without columns)rrr"columnssize ValueErrorsuperr.)r-rrr __class__r'r(r.s zDataFrameDescriber.__init__r/r0csj|}g}|D] \}}t|}||||qt|tfdd|Dddd}|j|_|S)Ncsg|]}|jddqS)F)copy)Zreindex.0xZ col_namesr'r( z/DataFrameDescriber.describe..rF)Zaxissort) _select_dataitemsr5appendreorder_columnsrr9r?)r-rdataldesc_seriesr6dr'rCr(r%s zDataFrameDescriber.describe)rcCs|jdurB|jdurBtjdg}|jj|d}t|jdkr~|j}n<|jdkrj|jdurbd}t||j}n|jj|j|jd}|S)zSelect columns to be described.Ndatetime)rrallz*exclude must be None when include is 'all')rr) rrnpnumberrZ select_dtypeslenr9r;)r-Zdefault_includerKmsgr'r'r(rGs   zDataFrameDescriber._select_data) r1r2r3r4r7r.r%rG __classcell__r'r'r=r(r$s  r$zSequence[Series]zlist[Hashable])rLrcCsTg}t}tdd|Dtd}|D]*}|D] }||vr,||||q,q$|S)z,Set a convenient order for rows for display.css|] }|jVqdSr,)indexr@r'r'r( rEz"reorder_columns..)key)setsortedrTaddrI)rLnamesZ seen_namesZ ldesc_indexesZidxnamesnamer'r'r(rJs rJrzSequence[float])rNrrcCsddlm}t|}gd|dg}||||g||| g}t |j t rt |j t r|j jdkrd}qddl}t |}qt}n|j jdvrt d}nd}||||j|d S) zDescribe series containing numerical data. Parameters ---------- series : Series Series to be described. percentiles : list-like of numbers The percentiles to include in the output. rr)countmeanstdminmaxmNZiufbfloatrWr^dtype)pandasrrr`rarbrcquantiletolistrd isinstancerhrrkindZpyarrowZfloat64rrRr^)rNrrformatted_percentiles stat_indexrOrhpar'r'r(describe_numeric_1ds(       rq)rKpercentiles_ignoredrc Csgd}|}t||dk}|dkrD|jd|jd}}d}ntjtj}}d}||||g}ddlm} | |||j |dS)zDescribe series containing categorical data. Parameters ---------- data : Series Series to be described. percentiles_ignored : list-like of numbers Ignored, but in place to unify interface. )r`uniquetopfreqrNobjectr_rg) value_countsrTrWilocrRnanr`rirr^) rKrrr] objcounts count_uniquertrurhr&rr'r'r(describe_categorical_1ds  r|c Cs ddg}|}t||dk}||g}d}|dkr|jd|jd}}|jj} |j d} t |}|j dur| dur| | }n | | }|gd7}|||t | | dt | | dg7}n |dd g7}|tjtjg7}d }dd lm} | |||j|d S) zDescribe series containing timestamp data treated as categorical. Parameters ---------- data : Series Series to be described. percentiles_ignored : list-like of numbers Ignored, but in place to unify interface. r`rsrNi8)rtrufirstlast)tzrtrurvr_rg)rwrTr`rWrxdtrZdropnavaluesviewrtzinfoZ tz_convertZ tz_localizercrdrRryrirr^) rKrrr]rzr{r&rhrtrurZasintrr'r'r($describe_timestamp_as_categorical_1d"s2       r)rKrrcCsdddlm}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. rr_)r`rarcrd)rWr^) rirrr`rarcrjrkrdr^)rKrrrnrorOr'r'r(describe_timestamp_1dRs  rr)rKrcCsNt|jrtSt|rtS|jjdks2t|jtr6tS|jjdkrFtStSdS)zSelect proper function for describing series based on data type. Parameters ---------- data : Series Series to be described. MreN) r rhr|rrqrmrlrr)rKr'r'r(r5js  r5znpt.NDArray[np.float64]r0cCst|durtgdSt|}t|d|vr8|dt|}t|}|dusXJt|t|krptd|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) rRarraylistr rIZasarrayrsrTr;)rZ unique_pctsr'r'r(r!s     r!)2r4 __future__rabcrrtypingrrrnumpyrRZpandas._libs.tslibsrZpandas._typingr r r Zpandas.util._validatorsr Zpandas.core.dtypes.commonr rZpandas.core.dtypes.dtypesrrrZpandas.core.arrays.floatingrZpandas.core.reshape.concatrZpandas.io.formats.formatrcollections.abcrrrirrr)r*r#r$rJrqr|rrr5r!r'r'r'r(s4      . D ) 0