U /e%@s>ddlZddlmZdddZd d Zdd d ZdddZdS)N)import_required 2000-01-01 2000-01-311s1dc Ks>ddlm}|dkr"ttttd}|f||||||d|S)aCreate 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 >>> 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 ... ) r)make_timeseriesN)nameidxy)startendfreqpartition_freqseeddtypes)Zdask.dataframe.io.demorstrintfloat)r r rrrrkwargsrr1/tmp/pip-unpacked-wheel-dbjnr7gq/dask/datasets.py timeseriess0 rcsLddlm}m}|fd|i|fdddfddt|DS) zdGenerate data for a single partition of a dask bag See Also -------- _make_mimesis r)FieldSchemarcsS)Nrr)fieldschema_descriptionrrPz#_generate_mimesis..schemacsg|]}jdddqS))Z iterationsr)create).0irrr Qsz%_generate_mimesis..)Zmimesis.schemarrrange)rrrecords_per_partitionrrrr)rr rr_generate_mimesisFsr(c s~ddlm}ddlm}pit|fddt|D}d|||fddt|D}|||S) a 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 rN)tokenizecsg|]}ddqS)rl)randint)r#_) random_staterrr%qsz!_make_mimesis..zmimesis-cs$i|]\}}|ft|fqSr)r()r#r$r)rrr'r rr vsz!_make_mimesis..) Zdask.bagZbagZ dask.baser)randomRandomr& enumerateZBag) rr npartitionsr'rdbr)ZseedsZdskr)rrr,r'r r _make_mimesisTs    r3 encCs&tdddd}td|i||||S)aMake 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. Parameters ---------- 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 ZmimesiszWThe mimesis module is required for this function. Try: python -m pip install mimesiscSsF|d|d|df|d|d|d|dd|d |d d d S) Nz person.agez person.namezperson.surnamezperson.occupationzperson.telephonezaddress.addressz address.city)addressZcityzpayment.credit_card_numberz#payment.credit_card_expiration_date)numberzexpiration-date)ZagerZ occupationZ telephoner7z credit-cardr)rrrrrszmake_people..locale)rr3)r1r'rr9r rrr make_people~s r:)rrrrNN)N)r4r5Nr6)r.Z dask.utilsrrr(r3r:rrrrs  @ *