def digitize(
column: ColumnBase, bins: np.ndarray, right: bool = False
) -> ColumnBase:
"""Return the indices of the bins to which each value in column belongs.
Parameters
----------
column : Column
Input column.
bins : Column-like
1-D column-like object of bins with same type as `column`, should be
monotonically increasing.
right : bool
Indicates whether interval contains the right or left bin edge.
Returns
-------
A column containing the indices
"""
if not column.dtype == bins.dtype:
raise ValueError(
"Digitize() expects bins and input column have the same dtype."
)
bin_col = as_column(bins, dtype=bins.dtype)
if bin_col.nullable:
raise ValueError("`bins` cannot contain null entries.")
return as_column(
libcudf.sort.digitize(column.as_frame(), bin_col.as_frame(), right)
)
def digitize(column, bins, right=False):
"""Return the indices of the bins to which each value in column belongs.
Parameters
----------
column : Column
Input column.
bins : np.array
1-D monotonically increasing array of bins with same type as `column`.
right : bool
Indicates whether interval contains the right or left bin edge.
Returns
-------
A device array containing the indices
"""
assert column.dtype == bins.dtype
bins_buf = Buffer(bins.view("|u1"))
bin_col = NumericalColumn(data=bins_buf, dtype=bins.dtype)
return as_column(
libcudf.sort.digitize(column.as_frame(), bin_col.as_frame(), right))
