a tDf@sVddlmZddlZddlmZddlmZdd d Zd d Zdd dZ dddZ dS)) annotationsN)Version)import_required 2000-01-01 2000-01-311s1dc Ks>ddlm}|dur"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.demor strintfloat)rrrrrrkwargsr rZ/nfs/NAS7/SABIOD/METHODE/ermites/ermites_venv/lib/python3.9/site-packages/dask/datasets.py timeseries s0 rcsddl}ddlm}m}|fd|iii}t|jtdkrPdd<nd|d<|fdfd d i|fd d t|DS) zdGenerate data for a single partition of a dask bag See Also -------- _make_mimesis rN)FieldSchemarz9.0.0Z iterationsschemacsS)Nrr)fieldschema_descriptionrr\z#_generate_mimesis..cs g|]}jfidqS)r)create).0i) create_kwargsrrr ]r"z%_generate_mimesis..)mimesisZmimesis.schemarrr __version__range)rr records_per_partitionrr(rrZ schema_kwargsr)r&rrr r_generate_mimesisJs  r,c s~ddlm}ddlm}pit|fddt|D}d|||fddt|D}|||S) a Make a Dask Bag filled with data randomly generated by the mimesis project 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$_) random_staterrr'}r"z!_make_mimesis..zmimesis-cs$i|]\}}|ft|fqSr)r,)r$r%r)rr r+rrr sz!_make_mimesis..) Zdask.bagZbagZ dask.baser-randomRandomr* enumerateZBag) rr npartitionsr+rdbr-ZseedsZdskr)rr r0r+rr _make_mimesis`s    r7 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 r(zWThe mimesis module is required for this function. Try: python -m pip install mimesiscSsL|dddd|d|df|d|d|d |d d |d |d ddS)Nzrandom.randintrx)abz person.namezperson.surnamezperson.occupationzperson.telephonezaddress.addressz address.city)addressZcityzpayment.credit_card_numberz#payment.credit_card_expiration_date)numberzexpiration-date)Zager Z occupationZ telephoner>z credit-cardr)rrrrr!s zmake_people..locale)rr7)r5r+rr@rrrr make_peoples rA)rrrrNN)N)r8r9Nr:) __future__rr2Zpackaging.versionrZ dask.utilsrrr,r7rArrrrs    @ *