U
|
¬ý°d/ ã @ s d Z ddlmZ ddlmZmZ ddlmZmZm Z m
|
Z
|
m Z m Z ddl ZddlmZ ddlmZmZmZ ddlmZ dd lmZmZmZmZm Z m Z dd
|
l m Z dd l m!Z! dd l"m#Z# dd l$m%Z% erØddl&m'Z'm(Z( ddddddddZ)G dd deZ*G dd de*Z+G dd de*Z,dd d d d Z-d d!d d"d#d$Z.d d!d d%d&d'Z/d d!d d%d(d)Z0d d!d d*d+d,Z1d d-d.d/d0Z2dd1d2d3d4Z3dS )5z
|
Module responsible for execution of NDFrame.describe() method.
|
|
Method NDFrame.describe() delegates actual execution to function describe_ndframe().
|
é )Ú annotations)ÚABCÚabstractmethod)Ú TYPE_CHECKINGÚAnyÚCallableÚHashableÚSequenceÚcastN)Ú Timestamp)ÚDtypeObjÚNDFrameTÚnpt)Úvalidate_percentile)Ú is_bool_dtypeÚis_complex_dtypeÚis_datetime64_any_dtypeÚis_extension_array_dtypeÚis_numeric_dtypeÚis_timedelta64_dtype)Ú
|
ArrowDtype)Ú Float64Dtype)Úconcat)Úformat_percentiles)Ú DataFrameÚSeriesr ústr | Sequence[str] | Nonez#Sequence[float] | np.ndarray | None)ÚobjÚincludeÚexcludeÚ percentilesÚreturnc C sN t |}| 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.
|
é r ©r r )r r r )r )Úrefine_percentilesÚndimÚSeriesDescriberr
|
ÚDataFrameDescriberÚdescriber )r r r r Z describerÚresult© r* úSd:\z\workplace\vscode\pyvenv\venv\Lib\site-packages\pandas/core/methods/describe.pyÚdescribe_ndframe5 s
|
ÿý r, c @ s4 e Zd ZdZdddddZedddd d
|
Zd S ) ÚNDFrameDescriberAbstractzAbstract class for describing dataframe or series.
|
|
Parameters
|
----------
|
obj : Series or DataFrame
|
Object to be described.
|
zDataFrame | SeriesÚNone)r r! c C s
|
|| _ d S ©Nr# )Úselfr r* r* r+ Ú__init__l s z!NDFrameDescriberAbstract.__init__ú Sequence[float] | np.ndarray©r r! c C s dS )z¸Do describe either series or dataframe.
|
|
Parameters
|
----------
|
percentiles : list-like of numbers
|
The percentiles to include in the output.
|
Nr* )r0 r r* r* r+ r( o s z!NDFrameDescriberAbstract.describeN)Ú__name__Ú
|
__module__Ú __qualname__Ú__doc__r1 r r( r* r* r* r+ r- c s r- c @ s* e Zd ZU dZded< dddddZdS ) r& z2Class responsible for creating series description.r r r2 r3 c C s t | j}|| j|S r/ )Úselect_describe_funcr )r0 r Ú describe_funcr* r* r+ r( s ÿzSeriesDescriber.describeN)r4 r5 r6 r7 Ú__annotations__r( r* r* r* r+ r& z s
|
r& c sD e Zd ZdZddddd fdd Zddd d
|
d Zd d Z ZS )r' ab Class 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.
|
r r r. )r r r r! c s: || _ || _|jdkr*|jjdkr*tdt |¡ d S )Né r z+Cannot describe a DataFrame without columns)r r r% ÚcolumnsÚsizeÚ
|
ValueErrorÚsuperr1 )r0 r r r ©Ú __class__r* r+ r1 s
|
zDataFrameDescriber.__init__r2 r3 c sj | ¡ }g }| ¡ D ] \}}t|}| |||¡ qt| t fdd|D ddd}|j ¡ |_|S )Nc s g | ]}|j d dqS )F)Úcopy)Zreindex©Ú.0Úx©Z col_namesr* r+ Ú
|
<listcomp>¬ s z/DataFrameDescriber.describe.<locals>.<listcomp>r" F)ZaxisÚsort)Ú _select_dataÚitemsr8 ÚappendÚreorder_columnsr r< rB )r0 r ÚdataÚldescÚ_Úseriesr9 Údr* rF r+ r( ¢ s ý zDataFrameDescriber.describec C s | j dkrB| jdkrBtjdg}| jj|d}t|jdkr~| j}n<| j dkrj| jdk rbd}t|| j}n| jj| j | jd}|S )z Select columns to be described.NÚdatetime)r r Úallz*exclude must be None when include is 'all')r r ) r r ÚnpÚnumberr Z select_dtypesÚlenr< r> )r0 Zdefault_includerM Úmsgr* r* r+ rI ³ s
|
|
|
þz DataFrameDescriber._select_data)r4 r5 r6 r7 r1 r( rI Ú __classcell__r* r* r@ r+ r' s r' zSequence[Series]zlist[Hashable])rN r! c C sD g }t dd | D td}|D ] }|D ]}||kr&| |¡ q&q |S )z,Set a convenient order for rows for display.c s s | ] }|j V qd S r/ )ÚindexrC r* r* r+ Ú <genexpr>Ë s z"reorder_columns.<locals>.<genexpr>)Úkey)ÚsortedrV rK )rN ÚnamesZ ldesc_indexesZidxnamesÚnamer* r* r+ rL È s rL r zSequence[float])rP r r! c C s ddl m} t|}ddddg| dg }| ¡ | ¡ | ¡ | ¡ g| |¡ ¡ | ¡ g }t
|
| rt | j t rddl}t | ¡ }q°t }n t| r¬t| s¬t d ¡}nd}|||| j|d
|
S ) zÛDescribe series containing numerical data.
|
|
Parameters
|
----------
|
series : Series
|
Series to be described.
|
percentiles : list-like of numbers
|
The percentiles to include in the output.
|
r ©r ÚcountÚmeanÚstdÚminÚmaxNÚfloat©rY r^ Údtype)Úpandasr r r` ra rb rc ÚquantileÚtolistrd r Ú
|
isinstancerg r ZpyarrowÚfloat64r r r rT r^ )rP r r Úformatted_percentilesÚ
|
stat_indexrQ Úparg r* r* r+ Údescribe_numeric_1dÓ s$
|
ÿþÿ rp )rM Úpercentiles_ignoredr! c
|
C s ddddg}| ¡ }t||dk }|dkrH|jd |jd }}d}ntjtj }}d}| ¡ |||g}ddlm} | ||| j |d S )
|
zãDescribe 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` ÚuniqueÚtopÚfreqr NÚobjectr_ rf )
|
Ú value_countsrV rY ÚilocrT Únanr` rh r r^ )
|
rM rq r] Ú objcountsÚ count_uniquers rt rg r) r r* r* r+ Údescribe_categorical_1d÷ s r{ c C s ddg}| ¡ }t||dk }| ¡ |g}d}|dkrÐ|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 )zøDescribe 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` rr r NÚi8rs rt ÚfirstÚlast)Útzru r_ rf )rv rV r` rY rw Údtr ZdropnaÚvaluesÚviewr ÚtzinfoZ
|
tz_convertZ tz_localizerc rd rT rx rh r r^ ) rM rq r] ry rz r) rg rs rt r Zasintr r* r* r+ Ú$describe_timestamp_as_categorical_1d s2
|
ü
|
r )rM r r! c C sf ddl m} t|}dddg| dg }| ¡ | ¡ | ¡ g| |¡ ¡ | ¡ g }|||| j dS )zÛDescribe series containing datetime64 dtype.
|
|
Parameters
|
----------
|
data : Series
|
Series to be described.
|
percentiles : list-like of numbers
|
The percentiles to include in the output.
|
r r_ r` ra rc rd )rY r^ )
|
rh r r r` ra rc ri rj rd r^ )rM r r rm rn rQ r* r* r+ Údescribe_timestamp_1dG s ÿþÿr
r )rM r! c C s> t | jrtS t| rtS t| jr(tS t| jr6tS tS dS )zSelect proper function for describing series based on data type.
|
|
Parameters
|
----------
|
data : Series
|
Series to be described.
|
N)r rg r{ r rp r r
r )rM r* r* r+ r8 _ s
|
|
|
|
r8 z%np.ndarray[Any, np.dtype[np.float64]]r3 c C sv | dkrt dddg¡S t| } t| d| kr:| d¡ t | ¡} t | ¡}| dk sZtt|t| k rrt d|S )zº
|
Ensure that percentiles are unique and sorted.
|
|
Parameters
|
----------
|
percentiles : list-like of numbers, optional
|
The percentiles to include in the output.
|
Ng Ð?g à?g è?z%percentiles cannot contain duplicates)
|
rT ÚarrayÚlistr rK Zasarrayrr ÚAssertionErrorrV r> )r Z unique_pctsr* r* r+ r$ u s
|
|
|
r$ )4r7 Ú
|
__future__r Úabcr r Útypingr r r r r r
|
ÚnumpyrT Zpandas._libs.tslibsr Zpandas._typingr r r Zpandas.util._validatorsr Zpandas.core.dtypes.commonr r r r r r Z pandas.core.arrays.arrow.dtyper Zpandas.core.arrays.floatingr Zpandas.core.reshape.concatr Zpandas.io.formats.formatr rh r r r, r- r& r' rL rp r{ r r
r8 r$ r* r* r* r+ Ú<module> s2 . B $ 0
|
