You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
ORPA-pyOpenRPA/Resources/WPy64-3720/python-3.7.2.amd64/Lib/site-packages/dask/datasets.py

143 lines
4.3 KiB

from __future__ import absolute_import, print_function, division
import random
from .utils import import_required
def timeseries(
start='2000-01-01',
end='2000-01-31',
freq='1s',
partition_freq='1d',
dtypes={'name': str, 'id': int, 'x': float, 'y': float},
seed=None,
):
""" 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
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
"""
from dask.dataframe.io.demo import make_timeseries
return make_timeseries(start=start, end=end, freq=freq,
partition_freq=partition_freq,
seed=seed, dtypes=dtypes)
def _generate_mimesis(field, schema_description, records_per_partition, seed):
""" Generate data for a single partition of a dask bag
See Also
--------
_make_mimesis
"""
from mimesis.schema import Schema, Field
field = Field(seed=seed, **field)
schema = Schema(schema=lambda: schema_description(field))
for i in range(records_per_partition):
yield schema.create(iterations=1)[0]
def _make_mimesis(field, schema, npartitions, records_per_partition, seed=None):
"""
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
"""
import dask.bag as db
from dask.base import tokenize
field = field or {}
if seed is None:
seed = random.random()
seeds = db.core.random_state_data_python(npartitions, seed)
name = 'mimesis-' + tokenize(field, schema, npartitions, records_per_partition, seed)
dsk = {(name, i): (_generate_mimesis, field, schema, records_per_partition, seed)
for i, seed in enumerate(seeds)}
return db.Bag(dsk, name, npartitions)
def make_people(npartitions=10, records_per_partition=1000, seed=None, locale='en'):
""" 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
"""
import_required('mimesis',
'The mimesis module is required for this function. Try:\n'
' pip install mimesis')
schema = lambda field: {
'age': field('person.age'),
'name': (field('person.name'), field('person.surname')),
'occupation': field('person.occupation'),
'telephone': field('person.telephone'),
'address': {'address': field('address.address'),
'city': field('address.city')},
'credit-card': {'number': field('payment.credit_card_number'),
'expiration-date': field('payment.credit_card_expiration_date')},
}
return _make_mimesis({'locale': locale}, schema, npartitions, records_per_partition, seed)