B T\  @shddlmZmZmZddlZddlmZddddeee e d dfd d Z d d Z dddZ dddZ dS))absolute_importprint_functiondivisionN)import_requiredz 2000-01-01z 2000-01-31Z1sZ1d)nameidxyc Ks(ddlm}|f||||||d|S)a 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 ... ) r)make_timeseries)startendfreqpartition_freqseeddtypes)Zdask.dataframe.io.demor )r r rrrrkwargsr r,lib/python3.7/site-packages/dask/datasets.py timeseriess0  rc#s^ddlm}m}|fd|i|fddd}x"t|D]}|jdddVq@Wd S) ze Generate data for a single partition of a dask bag See Also -------- _make_mimesis r)SchemaFieldrcsS)Nrr)fieldschema_descriptionrrGsz#_generate_mimesis..)schemar)Z iterationsN)Zmimesis.schemarrrangeZcreate)rrrecords_per_partitionrrrrir)rrr_generate_mimesis>s rc s|ddlm}ddlm}pi|dkr0t}|j||}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)tokenizezmimesis-cs$i|]\}}t|f|fqSr)r).0rr)rrrrrr nsz!_make_mimesis..) Zdask.bagZbagZ dask.baser randomZcoreZrandom_state_data_python enumerateZBag) rr npartitionsrrZdbr ZseedsZdskr)rrrrr _make_mimesisLs   r& encCs&tdddd}td|i||||S)a 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 ZmimesiszMThe mimesis module is required for this function. Try: 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)Znumberzexpiration-date)ZagerZ occupationZ telephoner*z credit-cardr)rrrrrs zmake_people..locale)rr&)r%rrr+rrrr make_peoplets r,)N)r'r(Nr))Z __future__rrrr#Zutilsrstrintfloatrrr&r,rrrrs   0 (