U +if2@sdZddlmZddlmZmZddlmZmZm Z m Z m Z m Z ddl Z ddlZddlmZddlmZddlmZdd lmZdd lmZmZmZmZdd lmZdd lm 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)Z+d d!d d*d+d,Z,d dd-d.d/d0Z-dd1d2d3d4Z.dS)5z Module responsible for execution of NDFrame.describe() method. Method NDFrame.describe() delegates actual execution to function describe_ndframe(). ) annotations)ABCabstractmethod) TYPE_CHECKINGAnyCallableHashableSequencecastN) Timestamp)NDFrameT)find_stack_level)validate_percentile) is_bool_dtypeis_datetime64_any_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. rrrrrrrr)r)refine_percentilesndimSeriesDescriberr DataFrameDescriberdescriber )rrrrrZ describerresultr(G/home/mars/bis/venv/lib/python3.8/site-packages/pandas/core/describe.pydescribe_ndframe/s  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. zDataFrame | Seriesrr cCs||_||_dSNr )selfrrr(r(r)__init__msz!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+bs r+c@s*eZdZUdZded<dddddZdS) r$z2Class responsible for creating series description.rrr/r0cCst|j|j}||j|Sr,)select_describe_funcrr)r-r describe_funcr(r(r)r&s zSeriesDescriber.describeN)r1r2r3r4__annotations__r&r(r(r(r)r$|s r$csDeZdZdZdddddfdd Zddd d d Zd d ZZS)r%aClass responsible for creating dataobj description. Parameters ---------- obj : DataFrame DataFrame to be described. include : 'all', list-like of dtypes or None A white list of data types to include in the result. exclude : list-like of dtypes or None A black list of data types to omit from the result. datetime_is_numeric : bool Whether to treat datetime dtypes as numeric. rrrr!cs>||_||_|jdkr*|jjdkr*tdtj||ddS)Nrz+Cannot describe a DataFrame without columns)r)rrr#columnssize ValueErrorsuperr.)r-rrrr __class__r(r)r.s zDataFrameDescriber.__init__r/r0csn|}g}|D]$\}}t||j}||||qt|tfdd|Dddd}|j|_|S)Ncsg|]}|jddqS)F)copy)Zreindex.0xZ col_namesr(r) sz/DataFrameDescriber.describe..rF)Zaxissort) _select_dataitemsr5rappendreorder_columnsrr9r?)r-rdataldesc_seriesr6dr(rCr)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) rrnpnumberrrHrZ select_dtypeslenr9r;)r-Zdefault_includerJmsgr(r(r)rFs"   zDataFrameDescriber._select_data)r1r2r3r4r.r&rF __classcell__r(r(r=r)r%sr%zSequence[Series]zlist[Hashable])rKrcCsDg}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)sortedrSrH)rKnamesZ ldesc_indexesZidxnamesnamer(r(r)rIsrIrzSequence[float])rMrrcCsnddlm}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. rrcountmeanstdminmaxrVr[) pandasrrr]r^r_r`quantiletolistrar[)rMrrformatted_percentiles stat_indexrNr(r(r)describe_numeric_1ds  rh)rJpercentiles_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\rVr[dtype) value_countsrSrVilocrQnanr]rcrr[) rJrirZ objcounts count_uniquerkrlror'rr(r(r)describe_categorical_1ds  ruc 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]rjrNi8rkrlfirstlast)tzrmr\rn)rprSr]rVrqdtryZdropnavaluesviewr tzinfoZ tz_convertZ tz_localizer`rarQrrrcrr[) rJrirZrsrtr'rorkrlryZasintrr(r(r)$describe_timestamp_as_categorical_1ds2      r~)rJrrcCsfddlm}t|}dddg|dg}|||g|||g}||||j dS)zDescribe series containing datetime64 dtype. Parameters ---------- data : Series Series to be described. percentiles : list-like of numbers The percentiles to include in the output. rr\r]r^r`rarb) rcrrr]r^r`rdrerar[)rJrrrfrgrNr(r(r)describe_timestamp_1dGs  rr)rJrrcCsZt|jrtSt|rtSt|jrD|r,tStjdt t dt Snt |jrRtStSdS)zSelect proper function for describing series based on data type. Parameters ---------- data : Series Series to be described. datetime_is_numeric : bool Whether to treat datetime dtypes as numeric. zTreating datetime data as categorical rather than numeric in `.describe` is deprecated and will be removed in a future version of pandas. Specify `datetime_is_numeric=True` to silence this warning and adopt the future behavior now.) stacklevelN) rrorurrhrrwarningswarn FutureWarningr r~r)rJrr(r(r)r5bs   r5z%np.ndarray[Any, np.dtype[np.float64]]r0cCsv|dkrtdddgSt|}t|d|kr:|dt|}t|}|dk sZtt|t|krrt d|S)z Ensure that percentiles are unique and sorted. Parameters ---------- percentiles : list-like of numbers, optional The percentiles to include in the output. Ng?g?g?z%percentiles cannot contain duplicates) rQarraylistrrHZasarrayrjAssertionErrorrSr;)rZ unique_pctsr(r(r)r"s     r")/r4 __future__rabcrrtypingrrrrr r rnumpyrQZpandas._libs.tslibsr Zpandas._typingr Zpandas.util._exceptionsr Zpandas.util._validatorsrZpandas.core.dtypes.commonrrrrZpandas.core.reshape.concatrZpandas.io.formats.formatrrcrrr*r+r$r%rIrhrur~rr5r"r(r(r(r)s2        3 I  0$