ó ¦–Õ\c@`sddlmZmZmZddlZddlmZddddied 6ed 6e d 6e d 6dd „Z d„Z dd„Z ddddd„ZdS(i(tabsolute_importtprint_functiontdivisionNi(timport_requireds 2000-01-01s 2000-01-31t1st1dtnametidtxtycK`s>ddlm}|d|d|d|d|d|d||S( sê Create 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 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 >>> df = dask.datasets.timeseries() >>> df.head() # doctest: +SKIP timestamp id name x y 2000-01-01 00:00:00 967 Jerry -0.031348 -0.040633 2000-01-01 00:00:01 1066 Michael -0.262136 0.307107 2000-01-01 00:00:02 988 Wendy -0.526331 0.128641 2000-01-01 00:00:03 1016 Yvonne 0.620456 0.767270 2000-01-01 00:00:04 998 Ursula 0.684902 -0.463278 >>> df = dask.datasets.timeseries( ... '2000', '2010', ... freq='2H', partition_freq='1D', seed=1, # data frequency ... dtypes={'value': float, 'name': str, 'id': int}, # data types ... id_lam=1000 # control number of items in id column ... ) i(tmake_timeserieststarttendtfreqtpartition_freqtseedtdtypes(tdask.dataframe.io.demoR (R R R RRRtkwargsR ((s,lib/python2.7/site-packages/dask/datasets.pyt timeseriess0c#`ssddlm}m}|d|ˆ‰|d‡‡fd†ƒ}x)t|ƒD]}|jddƒdVqPWdS( se Generate data for a single partition of a dask bag See Also -------- _make_mimesis i(tSchematFieldRtschemac`s ˆˆƒS(N(((tfieldtschema_description(s,lib/python2.7/site-packages/dask/datasets.pytGtt iterationsiN(tmimesis.schemaRRtrangetcreate(RRtrecords_per_partitionRRRRti((RRs,lib/python2.7/site-packages/dask/datasets.pyt_generate_mimesis>s c `s¯ddlj}ddlm}ˆp(i‰|dkrFtjƒ}n|jj||ƒ}d|ˆˆ|ˆ|ƒ‰‡‡‡‡fd†t|ƒDƒ}|j |ˆ|ƒS(s Make a Dask Bag filled with data randomly generated by the mimesis projet Parameters ---------- field: dict keyword arguments to pass to ``mimesis.Field`` schema: Callable[Field] -> dict The schema to use to generate the data npartitions: int records_per_partition: int seed: int, None Seed for random data Returns ------- Dask Bag See Also -------- make_people iN(ttokenizesmimesis-c`s4i|]*\}}tˆˆˆ|fˆ|f“qS((R!(t.0R R(RRRR(s,lib/python2.7/site-packages/dask/datasets.pys ns ( tdask.bagtbagt dask.baseR"tNonetrandomtcoretrandom_state_data_pythont enumeratetBag( RRt npartitionsRRtdbR"tseedstdsk((RRRRs,lib/python2.7/site-packages/dask/datasets.pyt _make_mimesisLs  i iètencC`s3tddƒd„}ti|d6||||ƒS(sû Make a dataset of random people This makes a Dask Bag with dictionary records of randomly generated people. This requires the optional library ``mimesis`` to generate records. Paramters --------- npartitions : int Number of partitions records_per_partition : int Number of records in each partition seed : int, (optional) Random seed locale : str Language locale, like 'en', 'fr', 'zh', or 'ru' Returns ------- b: Dask Bag tmimesissMThe mimesis module is required for this function. Try: pip install mimesiscS`s†i|dƒd6|dƒ|dƒfd6|dƒd6|dƒd 6i|d ƒd 6|d ƒd 6d 6i|dƒd6|dƒd6d6S(Ns person.agetages person.namesperson.surnameRsperson.occupationt occupationsperson.telephonet telephonesaddress.addresstaddresss address.citytcityspayment.credit_card_numbertnumbers#payment.credit_card_expiration_datesexpiration-dates credit-card((R((s,lib/python2.7/site-packages/dask/datasets.pyRs   tlocale(RR1(R-RRR:R((s,lib/python2.7/site-packages/dask/datasets.pyt make_peoplets (t __future__RRRR(tutilsRtstrtinttfloatR'RR!R1R;(((s,lib/python2.7/site-packages/dask/datasets.pyts  0  (