Function from_dask_array

dask/dataframe/io/io.py:102–225

Create a Dask DataFrame from a Dask Array. Converts a 2d array into a DataFrame and a 1d array into a Series. Parameters ---------- x : da.Array columns : list or string list of column names if DataFrame, single string if Series index : dask.dataframe.Index, optiona

(x, columns=None, index=None, meta=None)

def from_dask_array(x, columns=None, index=None, meta=None):
    """Create a Dask DataFrame from a Dask Array.

    Converts a 2d array into a DataFrame and a 1d array into a Series.

    Parameters
    ----------
    x : da.Array
    columns : list or string
        list of column names if DataFrame, single string if Series
    index : dask.dataframe.Index, optional
        An optional *dask* Index to use for the output Series or DataFrame.

        The default output index depends on whether `x` has any unknown
        chunks. If there are any unknown chunks, the output has ``None``
        for all the divisions (one per chunk). If all the chunks are known,
        a default index with known divisions is created.

        Specifying `index` can be useful if you're conforming a Dask Array
        to an existing dask Series or DataFrame, and you would like the
        indices to match.
    meta : object, optional
        An optional `meta` parameter can be passed for dask
        to specify the concrete dataframe type to be returned.
        By default, pandas DataFrame is used.

    Examples
    --------
    >>> import dask.array as da
    >>> import dask.dataframe as dd
    >>> x = da.ones((4, 2), chunks=(2, 2))
    >>> df = dd.io.from_dask_array(x, columns=['a', 'b'])
    >>> df.compute()
         a    b
    0  1.0  1.0
    1  1.0  1.0
    2  1.0  1.0
    3  1.0  1.0

    See Also
    --------
    dask.bag.to_dataframe: from dask.bag
    """
    meta = _meta_from_array(x, columns, index, meta=meta)

    name = "from-dask-array-" + tokenize(x, columns)
    graph_dependencies = [x]
    arrays_and_indices = [x.name, "ij" if x.ndim == 2 else "i"]
    numblocks = {x.name: x.numblocks}

    if index is not None:
        # An index is explicitly given by the caller, so we can pass it through to the
        # initializer after a few checks.
        if index.npartitions != x.numblocks[0]:
            msg = (
                "The index and array have different numbers of blocks. "
                f"({index.npartitions} != {x.numblocks[0]})"
            )