U /eq@sddlZddlZddlmZddlmZddlm Z ddl m Z dgZ ddZ d4d d Zd d ddddddddddddddddddd d!d"d#d$d%gZd&d'Zd(d)Zee eeeeeed*eiZGd+d,d,e Zd-d.Zd5d3dZdS)6N)tokenize)from_map)DataFrameIOFunction)random_state_datamake_timeseriescCs||ddS)N)Zrandnrstater :/tmp/pip-unpacked-wheel-dbjnr7gq/dask/dataframe/io/demo.py make_float srcCs|j||dSNsize)Zpoisson)r r Zlamr r r make_intsrZAliceZBobZCharlieZDanZEdithZFrankZGeorgeZHannahZIngridZJerryZKevinZLauraZMichaelZNorbertZOliverZPatriciaZQuinnZRayZSarahZTimZUrsulaZVictorZWendyZXavierZYvonneZZeldacCs|jt|dSr)choicenamesr r r r make_string2srcCstj|jdtt|dtS)Nrr)pdZ CategoricalZ from_codesrandintlenrr r r r make_categorical6srcategoryc@s6eZdZdZd ddZeddZddZd d ZdS) MakeTimeseriesPartzV Wrapper Class for ``make_timeseries_part`` Makes a timeseries partition. NcCs(|pt||_||_||_||_dSN)listkeys_columnsdtypesfreqkwargs)selfr!r"r#columnsr r r __init__IszMakeTimeseriesPart.__init__cCs|jSr)r )r$r r r r%OszMakeTimeseriesPart.columnscCs$||jkr|St|j|j|j|dS)zUReturn a new MakeTimeseriesPart object with a sub-column projection. )r%)r%rr!r"r#)r$r%r r r project_columnsSs z"MakeTimeseriesPart.project_columnscCs@|\}}t|trtd|}t|d|d|j|j|j||jS)Nrr) isinstanceintrmake_timeseries_partr!r%r"r#)r$part divisions state_datar r r __call__`s  zMakeTimeseriesPart.__call__)N) __name__ __module__ __qualname____doc__r&propertyr%r'r.r r r r rCs    rcstj|||dd}tj|}i} |D]D\} fdd|D} t| t||f| } |kr*| | <q*tj| ||d} | j d|kr| j dd} | S)N timestamp)startendr"namecs6i|].\}}|dddkr|ddd|qS)_rr)rsplit).0kkvkr r tsz(make_timeseries_part..)indexr%) r date_rangenprandomZ RandomStateitemsmakerZ DataFramer@Ziloc)r5r6r!r%r"r-r#r@statedatadtkwsresultZdfr r=r r*os    r* 2000-01-01 2000-12-3110s1Mc Ks|dkrttttd}ttj|||d}t|d}|dkrPtjj d|d} n t ||} g} t t|dD]"} | || | d| | fqnt t|||| tdd|t|d | d ||d t|||||| d d S)aSCreate timeseries dataframe with random data Parameters ---------- start: datetime (or datetime-like string) Start of time series end: datetime (or datetime-like string) End of time series dtypes: dict (optional) Mapping of column names to types. Valid types include {float, int, str, 'category'} freq: string String like '2s' or '1H' or '12W' for the time series frequency partition_freq: string String like '1M' or '2Y' to divide the dataframe into partitions seed: int (optional) Randomstate seed kwargs: Keywords to pass down to individual column creation functions. Keywords should be prefixed by the column name and then an underscore. Examples -------- >>> import dask.dataframe as dd >>> df = dd.demo.make_timeseries('2000', '2010', ... {'value': float, 'name': str, 'id': int}, ... freq='2H', partition_freq='1D', seed=1) >>> df.head() # doctest: +SKIP id name value 2000-01-01 00:00:00 969 Jerry -0.309014 2000-01-01 02:00:00 1010 Ray -0.760675 2000-01-01 04:00:00 1016 Patricia -0.063261 2000-01-01 06:00:00 960 Charlie 0.788245 2000-01-01 08:00:00 1031 Kevin 0.466002 N)r7idxy)r5r6r"rgeArr2000Z1Hrzmake-timeseriesF)metar,labeltokenZenforce_metadata)strr)floatrrrBrrCrDrrrangeappendrrr*rr) r5r6r!r"Zpartition_freqseedr#r,Z npartitionsr-partsir r r rs6,     )r)rLrMNrNrON)ZnumpyrCZpandasrZdask.dataframe.corerZdask.dataframe.io.iorZdask.dataframe.io.utilsrZ dask.utilsr__all__rrrrrrXr)rWobjectrFrr*rr r r r sr      ,