Function timeseries

dask/dataframe/dask_expr/datasets.py:186–250

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 (optional) Mapping of column names to types.

(
    start="2000-01-01",
    end="2000-01-31",
    freq="1s",
    partition_freq="1D",
    dtypes=None,
    seed=None,
    **kwargs,
)

def timeseries(
    start="2000-01-01",
    end="2000-01-31",
    freq="1s",
    partition_freq="1D",
    dtypes=None,
    seed=None,
    **kwargs,
):
    """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 (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
    --------
    >>> from dask.dataframe.dask_expr.datasets import timeseries
    >>> df = timeseries(
    ...     start='2000', end='2010',
    ...     dtypes={'value': float, 'name': str, 'id': int},
    ...     freq='2h', partition_freq='1D', seed=1
    ... )
    >>> df.head()  # doctest: +SKIP
                           id      name     value
    2000-01-01 00:00:00   969     Jerry -0.309014
    2000-01-01 02:00:00  1010       Ray -0.760675
    2000-01-01 04:00:00  1016  Patricia -0.063261
    2000-01-01 06:00:00   960   Charlie  0.788245
    2000-01-01 08:00:00  1031     Kevin  0.466002
    """
    if dtypes is None:
        dtypes = {"name": "string", "id": int, "x": float, "y": float}

    if seed is None:
        seed = np.random.randint(2e9)

    expr = Timeseries(
        start,
        end,
        dtypes,
        freq,
        partition_freq,