Function from_array

dask/dataframe/dask_expr/_collection.py:4969–5017

Read any sliceable array into a Dask Dataframe Uses getitem syntax to pull slices out of the array. The array need not be a NumPy array but must support slicing syntax x[50000:100000] and have 2 dimensions: x.ndim == 2 or have a record dtype: x.dtype ==

(arr, chunksize=50_000, columns=None, meta=None)

def from_array(arr, chunksize=50_000, columns=None, meta=None):
    """Read any sliceable array into a Dask Dataframe

    Uses getitem syntax to pull slices out of the array.  The array need not be
    a NumPy array but must support slicing syntax

        x[50000:100000]

    and have 2 dimensions:

        x.ndim == 2

    or have a record dtype:

        x.dtype == [('name', 'O'), ('balance', 'i8')]

    Parameters
    ----------
    x : array_like
    chunksize : int, optional
        The number of rows per partition to use.
    columns : list or string, optional
        list of column names if DataFrame, single string if Series
    meta : object, optional
        An optional `meta` parameter can be passed for dask
        to specify the concrete dataframe type to use for partitions of
        the Dask dataframe. By default, pandas DataFrame is used.

    Returns
    -------
    dask.DataFrame or dask.Series
        A dask DataFrame/Series
    """
    import dask.array as da

    if isinstance(arr, da.Array):
        return from_dask_array(arr, columns=columns, meta=meta)

    from dask.dataframe.dask_expr.io.io import FromArray

    result = FromArray(
        arr,
        chunksize=chunksize,
        original_columns=columns,
        meta=meta,
    )
    if pyarrow_strings_enabled() and arr.dtype.kind in "OU":
        result = expr.ArrowStringConversion(result)
    return new_collection(result)


def from_graph(layer, _meta, divisions, keys, name_prefix):