o Tj.@sXdZddlmZddlmZmZddlmZmZm Z ddl Z ddl m Z ddlmZmZmZddlmZdd lmZmZdd lmZmZmZdd lmZdd lmZdd lm Z erjddl!m"Z"m#Z#ddl$m%Z%m&Z&d8ddZ'GdddeZ(Gddde(Z)Gddde(Z*d9d#d$Z+d:d(d)Z,d;d,d-Z-d;d.d/Z.dd6d7Z1dS)?z 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) DataFrameSeriesobjr includestr | Sequence[str] | Noneexclude percentiles#Sequence[float] | np.ndarray | NonereturncCsNt|}|jdkrttd|d}n ttd|||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 )rrrr describerresultr)_/home/dinkstrade/pdmp-scanner/venv/lib/python3.10/site-packages/pandas/core/methods/describe.pydescribe_ndframe7s   r+c@s(eZdZdZd ddZedd d Zd S)NDFrameDescriberAbstractzAbstract class for describing dataframe or series. Parameters ---------- obj : Series or DataFrame Object to be described. rDataFrame | SeriesrNonecCs ||_dSNr!)selfrr)r)r*__init__ns z!NDFrameDescriberAbstract.__init__rSequence[float] | np.ndarraycCsdS)zDo describe either series or dataframe. Parameters ---------- percentiles : list-like of numbers The percentiles to include in the output. Nr))r0rr)r)r*r&qsz!NDFrameDescriberAbstract.describeN)rr-rr.)rr2rr-)__name__ __module__ __qualname____doc__r1rr&r)r)r)r*r,es  r,c@s$eZdZUdZded<d ddZd S) r$z2Class responsible for creating series description.rrrr2rcCst|j}||j|Sr/)select_describe_funcr)r0r describe_funcr)r)r*r&s zSeriesDescriber.describeN)rr2rr)r3r4r5r6__annotations__r&r)r)r)r*r$|s r$cs@eZdZUdZded<dfd d Zdd dZdddZZS)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. rrrrrrr.cs:||_||_|jdkr|jjdkrtdt|dS)Nrz+Cannot describe a DataFrame without columns)rrr#columnssize ValueErrorsuperr1)r0rrr __class__r)r*r1s zDataFrameDescriber.__init__rr2csj|}g}|D]\}}t|}||||q t|tfdd|Dddd}|j|_|S)Ncsg|] }|jddqS)F)copy)reindex.0x col_namesr)r* sz/DataFrameDescriber.describe..r F)axissort) _select_dataitemsr7appendreorder_columnsrr;rA)r0rdataldesc_seriesr8dr)rFr*r&s zDataFrameDescriber.describecCs|jdur"|jdur"tjdg}|jj|d}t|jdkr |j}|S|jdkr7|jdur2d}t||j}|S|jj|j|jd}|S)zSelect columns to be described.Ndatetime)rrallz*exclude must be None when include is 'all')rr) rrnpnumberr select_dtypeslenr;r=)r0default_includerOmsgr)r)r*rKs"  zDataFrameDescriber._select_data)rrrrrrrr.)rr2rr)rr) r3r4r5r6r9r1r&rK __classcell__r)r)r?r*r%s   r%rPSequence[Series]list[Hashable]cCsTg}t}tdd|Dtd}|D]}|D]}||vr&||||qq|S)z,Set a convenient order for rows for display.css|]}|jVqdSr/)indexrCr)r)r* sz"reorder_columns..)key)setsortedrYaddrM)rPnames seen_names ldesc_indexesidxnamesnamer)r)r*rNs  rNrRrSequence[float]cCsddlm}t|}gd|dg}||||g||| g}t |j t rQt |j t rM|j jdkrBd}nddl}t |}nt}n|j jdvr]t 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)countmeanstdminmaxmNiufbfloatr_ridtype)pandasrrrlrmrnroquantiletolistrp isinstancerurrkindpyarrowfloat64rrVri)rRrrformatted_percentiles stat_indexrSrupar)r)r*describe_numeric_1ds(       rrOpercentiles_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. )rluniquetopfreqrNobjectrkrt) value_countsrYr_ilocrVnanrlrvrri) rOrre objcounts count_uniquerrrur(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. rlrrNi8)rrfirstlast)tzrrrrkrt)rrYrlr_rdtrdropnavaluesviewrtzinfo tz_convert tz_localizerorprVrrvrri) rOrrerrr(rurrrasintrr)r)r*$describe_timestamp_as_categorical_1d"s2       rcCsdddlm}t|}gd|dg}|||g|||g}||||j dS)zDescribe series containing datetime64 dtype. Parameters ---------- data : Series Series to be described. percentiles : list-like of numbers The percentiles to include in the output. rrk)rlrmrorp)r_ri) rvrrrlrmrorwrxrpri)rOrrr}r~rSr)r)r*describe_timestamp_1dRs  rrcCsJt|jrtSt|r tS|jjdkst|jtrtS|jjdkr#tStS)zSelect proper function for describing series based on data type. Parameters ---------- data : Series Series to be described. Mrq) r rurrrrzryrr)rOr)r)r*r7js  r7npt.NDArray[np.float64]cCst|dur tgdSt|}t|d|vr|dt|}t|}|dus,Jt|t|kr8td|S)z Ensure that percentiles are unique and sorted. Parameters ---------- percentiles : list-like of numbers, optional The percentiles to include in the output. N)g??g?rz%percentiles cannot contain duplicates) rVarraylistr rMasarrayrrYr=)r unique_pctsr)r)r*r"s     r") rr rrrrrrrr )rPr]rr^)rRrrrjrr)rOrrrjrr)rOrrrjrr)rOrrr)rrrr)2r6 __future__rabcrrtypingrrrnumpyrVpandas._libs.tslibsrpandas._typingr r r pandas.util._validatorsr pandas.core.dtypes.commonr rpandas.core.dtypes.dtypesrrrpandas.core.arrays.floatingrpandas.core.reshape.concatrpandas.io.formats.formatrcollections.abcrrrvrrr+r,r$r%rNrrrrr7r"r)r)r)r*s6       . D ) 0